Artificial Intelligence – Avi Kopelman, Align Technology Inc
Abstract for “Systems and Methods for Positioning a Patient’s Mandible in Response to Sleep Apnea Status”
These systems, methods, devices and apparatus are for positioning the patient’s lower jaw in response to their sleep apnea status. One aspect of a system to monitor and treat sleep apnea includes one or several sensors that monitor the patient for signs and symptoms of sleep apnea. An intraoral appliance is worn by the patient and one or two processors. The memory contains instructions to instruct the processors to send a control signal (to the intraoral device) to move the lower jaw of the patient’s patient from one position to another in order to treat the event.
Background for “Systems and Methods for Positioning a Patient’s Mandible in Response to Sleep Apnea Status”
“Obstructive sleep apnea (hereinafter ?OSA?) A medical condition that causes a blockage in the upper airway, either completely or partially, during sleep. It could be caused by relaxation of soft tissues or muscles around the throat (e.g. the soft palate, back, tongue, tonsils, uvula and pharynx) during sleeping. OSA episodes can occur several times per night, disrupting the patient’s sleeping cycle. Chronic OSA suffers may experience sleep deprivation and excessive daytime sleepiness. They might also experience chronic fatigue, chronic headaches, snoring, hypoxia, and chronic fatigue.
To treat OSA, mandibular advancement devices have been suggested. The mandibular advancement device can be worn in the mouth above the lower and upper jaws. This device is used to treat sleep apnea. It moves the lower jaw in the anterior direction relative the upper jaw. This may tighten the tissues in the upper airway and prevent obstruction during sleep.
In some cases, however, mandibular advancement devices used to treat OSA can have undesirable side effects such as jaw discomfort, tooth repositioning, or muscle strain. It would be beneficial to have improved techniques and apparatus for treating sleep apnea or snoring. It would be beneficial to have improved apparatus and methods that allow mandibular advancement without undesirable side effects like tooth repositioning and jaw discomfort.
The systems, methods, devices and apparatus described herein offer improved treatment for obstructive sleeping apnea. They also have fewer side effects such as jaw discomfort, tooth repositioning, muscle strain, and jaw discomfort. The mandibular advancement device may be used in combination with patient monitoring and personalized treatment to treat sleep apnea. This will improve the detection and treatment of symptoms related to sleep apnea. Machine learning algorithms can accurately detect and terminate sleep apnea events. These algorithms can also be customized for each patient. They improve the position and durations of jaw displacement, which allows patients to effectively treat sleep apnea. The systems described herein include sensors that monitor patients for sleep apnea symptoms and processors that interpret instructions from the sensors to detect sleep events more accurately based on the patient data. The processors may execute machine learning algorithms to optimize the treatment course and detect symptoms. These algorithms can be based on patient-specific data and factors, such as past sleep apnea events. The processors described herein can transmit control signals to an oral appliance to treat sleep apnea symptoms. Control signals can cause an intraoral appliance to move the lower jaw to a position specified by the machine learning algorithm in order to effectively treat sleep apnea. This will reduce unwanted side effects and increase effectiveness.
“One aspect of the invention relates to a system for monitoring and treating insomnia in patients. The system comprises: one or multiple sensors that monitor the patient’s symptoms; an intraoral device worn by the patient; one to three processors; and memory containing instructions executable by one or two processors. These instructions cause the processors: to receive sensor data from the sensors; to detect the onset of sleep apnea using a machine-learning algorithm; to transmit to the intraoral apparatus a control signal to move the lower jaw
“Another aspect of the invention is a system for monitoring and treating insomnia in a patient. The system comprises: one or multiple processors; and memory containing instructions executable by one or several processors. These instructions cause the processors: to receive sensor data from one of more sensors, to detect the onset of sleep apnea and to transmit to an intraoral appliance a control signal to move the lower jaw of the patient’s from a first to a second position to treat the sleep disorder.
“Another aspect of the invention is a method of monitoring and treating sleep disordered breathing in a patient. The method involves: receiving sensor data from one or several sensors to monitor the patient’s sleep patterns; detecting the onset of sleep apnea events in response to the sensor data; and transmitting control signals to an intraoral device worn by the patient to move the lower jaw from a first to a second position to treat the sleep disordered breathing event.
“Other objects or features of this invention will be apparent through a review the specification, claims and attached figures.”
“INCORPORATION BY RESEARCH”
“All publications, patents and patent applications mentioned herein are herein incorporated as if each publication, patent, and/or patent application were specifically and individually indicated that they would be incorporated by refer.”
The following detailed description will help you to understand the features and benefits of the disclosure. It also includes illustrative embodiments in which the principles and embodiments of this disclosure are used.
“As used in this article, the term ‘and/or’ is It is used to indicate that two words, expressions or sentences are to be taken together or separately. Example: A and/or A can be used to indicate that A or B includes A, B, and both A and B.
These systems, methods, devices, and apparatus are for positioning the patient’s lower jaw in response to their sleep apnea status. Systems are available for treating and monitoring sleep apnea. The systems include: one or several sensors that monitor the patient’s symptoms; an intraoral device worn by the patient; one to three processors; and memory containing instructions to instruct the processors to trigger the one or two processors to: Receive sensor data from the sensors; detect the onset of sleep apnea using a machine-learning algorithm; transmit a control signal (to the intraoral apparatus) to move the lower jaw of the patient to a second to treat the event
“In various aspects, methods for monitoring and treating sleep disordered breathing in a patient are provided. These methods include: receiving sensor data from one of more sensors to monitor for sleep disorders; detecting the onset of sleep apnea using a machine-learning algorithm executed by one to more processors; transmitting a control signal for an intraoral device worn by the patient to move the lower jaw from a first to a second location in order to treat the sleep disordered breathing event.
“In various ways, one or several non-transitory computer readable storage media are provided. They contain instructions that, when executed on one or multiple processors of a system monitoring and treating sleep disordered breathing in a patient’s system, cause the system at least to: Receive a set sensor data from one of more sensors to monitor the patient for signs and symptoms of sleep apnea. Using the sensor data, detect the onset of a sleep disordered event using a machine-learning algorithm
One or more sensors can be used to measure breathing sounds, snoring, breathing rate, respiratory flow, chest expansion and oxygen level. They also can be used to determine sleeping position or combination thereof. This data may indicate symptoms that are associated with sleep apnea. The machine learning algorithm can also be tailored to each patient. The patient’s previous sleep apnea events can be used to customize the machine learning algorithm. You can customize the machine learning algorithm to your patient by using previous sleep patterns. Instructions can also cause the system detect a discrepancy in a patient’s current sleeping patterns and previous sleep patterns and generate an alert.
The methods also include: identifying, using one or more processing units, a discrepancy in a patient’s current and previous sleeping patterns; and creating an alert with the aid of one or more processing units to indicate the discrepancy. The first position could be a normal jaw position, while the second can be advanced jaw position.
“The instructions may also cause the system: to receive a second set sensor data from one or more sensors; to detect, using machine learning algorithms, the termination of the sleep-apnea event based upon the second set sensor data; to transmit a second control signal (to the intraoral device) to cause the intraoral apparatus to move the lower jaw of a patient from the second to the first positions. Instructions can also cause the system using the machine learning algorithm to determine the second position of the lower jaw. Further, the instructions could cause the system: to receive a third set sensor data from one or more sensors while lower jaw is in second position; and to determine the effectiveness of the second lower jaw position in treating sleep apnea events based on that third set sensor data. Based on the results, the instructions may also cause the system’s machine learning algorithm to be updated. Further, the instructions could cause the system to: use the machine learning algorithm to determine a modified lower jaw position to improve the effectiveness in treating sleep apnea events; transmit a third control signal (to the intraoral appliance) to move the lower jaw into the modified position.
“The methods also include: receiving, using one or multiple processors, another set of sensor information from the one/more sensors; detecting, using the one/more processors and the machine learning algorithm; terminating the sleep apnea episode based on this second set sensor data; and transmitting, via the one/more processors, a control signal to the intraoral device to cause the intraoral appliances to move the lower jaw of a patient from the second to the first positions. Methods can also include determining the second position of the lower jaw with the machine learning algorithm. Further, the methods may include receiving data from one or more sensors with the lower jaw in the second position. Based on this data, the one or two processors can determine the effectiveness of the lower jaw position in treating sleep apnea events. Based on the results, the methods may also include updating the machine-learning algorithm. These methods may also include determining the position of the lower jaw using one or more processors. This is done to increase the effectiveness of treatment for sleep apnea. The third control signal can be transmitted to the intraoral device to move the lower jaw into the new position with the aid of one or more processors.
The second set of sensor data may indicate a decrease in symptoms related to sleep apnea. An intraoral appliance may consist of an upper shell that fits on the patient’s upper jaw; a lowershell that fits on the patient’s lower jaw; and an advancement device coupling the upper and lower shells. The advancement apparatus is designed to move the lower shell relative the upper shell according to control signals from one or more processors. This allows the patient to lose their lower jaw. The advancement apparatus may be configured to move the lower shell in a variety of positions relative to its upper counterpart. An advancement apparatus may include an upper advancement structure that is coupled to an upper shell, and a lower advancement mechanism that is coupled to an lower shell. A control signal can be used to cause the lower advancement and upper advancement structures to engage with one another. This will displace the lower shell relative the upper shell. An actuator can be used to adjust the length of the tether elements extending between the upper and lower shells in response to control signals. This will cause the lower shell to be displace relative to the upper.
“Intraoral appliances are used to treat sleep apnea by mandibular advancement in various ways. The apparatus comprises an upper shell that fits on the upper jaw of the patient and a lower shell that fits on the lower jaw. An advancement apparatus coupling the upper and lower shells, wherein the advancement device is designed to move the lower shell relative the upper shell in response control signals from one or more processors.
“The present disclosure, in various aspects, provides a patient-specific approach for sleep apnea. It uses a feedback control system that monitors the patient’s sleep apnea status and actively controls the mandibular position to respond and reduce snoring.
A system for mandibular advancement can be described as an oral appliance, sensor and controller. An oral appliance can be used to advance the mandible of a patient relative to the upper jaw (maxilla).
“The present disclosure, in various aspects, provides a motorized? An intraoral appliance that can selectively move and retract the mandible of a patient relative to their upper jaw (maxilla) is provided. The oral appliances can be removed from the mandible if the patient is not snoring or experiencing other symptoms associated with sleep apnea. configuration. However, the present disclosure allows for the monitoring of sleep apnea and the activation of the intraoral appliance to activate the mandible to provide treatment. The system can optionally retract the mandible if the apnea event has stopped.
An oral appliance can be described in many ways. It may include an upper anchor, lower anchor and a motor or some other mechanism that allows the lower attachment to be moved and retracted relative to the upper attachment. The oral appliance may be used in conjunction with the above-described system. In this case, the motor or another mechanism can be controlled by a signal, usually generated by a controller and sensor in response to sleep apnea symptoms.
“In different aspects, a method of advancing a patient?s mandible to cure sleep apnea involves monitoring the patient for signs and generating a signal when their sleep apnea status changes. Then, selectively moving and/or retracting an anchor that is attached to the patient?s lower jaw relative to an anchor that is secured to his/her mandible.
“The systems, methods and devices described herein include systems for mandibular advance. They can be described as: An oral appliance that advances a patient’s mandible relative the upper jaw; a sensor to detect when the patient is eligible for mandibular advance; and a controller or processor that receives a signal (from the sensor) to indicate whether the patient is eligible and sends it to the oral device to retract or advance the mandible. An upper anchor that is secured to the patient?s upper jaw and a lower anchor that is secured to the lower jaw of the patient can be used as the oral appliance. A motor, which is coupled between the lower and upper anchors, will respond to the processor and controller to move or retract the mandible. The sensor can sense at least one of the following: breathing sounds, cardiac data, respiratory airflow, cardiac data, or sleep position. An external device can also be included in the system. The controller or processor can include the sensor. The sensor can also be integrated into the oral appliance. A controller or processor can be programmed to send a signal to the mouth to move the mandible if it receives an alert from the sensor. A controller or processor can also be configured to send a signal to the mouth to retract the mandible if it receives a signal associated with an onset of an apnea event. A controller and/or processor may be configured to send a signal to the appliance to retract it after a set time. The controller and/or the processor can be programmed to collect data over time about patient’s apnea patterns and then use this data to predict when an apnea event will occur.
“In different aspects, the systems, methods and devices described herein include oral appliances that consist of an upper anchor that couples to the patient?s upper jaw and a lower anchor that couples to the mandible. A motor is used to move the lower anchor relative the upper anchor according to a signal triggered by sleep apnea symptoms. You can have the upper and lower anchors removably attached over the patient’s teeth. You can attach the upper and lower anchors to the mandible and upper jaw bones of patients. A motor may consist of a rotor for one of the lower anchors or a follower for the other anchor. A translator can be attached to one of the lower and upper anchors, and a follower on another of the anchors. A spindle can be mounted on one of the lower anchors. The spindle can also attach a tether to one anchor.
“In different aspects, the systems, methods and devices described herein include methods of advancing a patient?s mandible in order to treat sleep apnea. These methods include: monitoring the patient for signs and symptoms; generating a signal when their sleep apnea status changes. And selectively moving a lower anchor relative to an anchor attached to the patient?s upper jaw. Monitoring may include monitoring at least one of the following: breathing sounds, respiratory airflow, cardiac data and sleep position. A sensor can be attached to the patient for monitoring. A sensor attached to an appliance worn by a patient can perform monitoring. The act of generating can be described as a signal to move the mandible when there are symptoms that indicate an onset or recurrence of an apnea episode.
“Generating” can be described as the act of generating a signal to retract a mandible when there is a decrease in symptoms due to an apnea episode. The act of generating can be described as producing a signal to retract a mandible after a certain time. This method may also include collecting data over time about the patient’s apnea patterns and using these data to predict when an apnea event will occur. The motor can be activated between the lower anchor and the upper anchor to selectively advance the anchor.
“Mandibular Advancement Apparatus”
“Now, let’s turn to the drawings. In which like numbers designate similar elements in the various figures FIG. 1A shows an upper jaw 100 and lower jaw 102, respectively, of a patient in a habitual position. This is in accordance to embodiments. The normal closed position of the lower and upper jaws 100, 101 can be called the habitual occlusal. If the upper and lower jaws 100,102 are in their normal occlusal relationship during sleep, patients suffering from sleep apnea can experience blocked airflow. This is due to relaxation of soft tissue around the upper or upper airway.
“FIG. “FIG. In accordance with embodiments, the occlusal position. The advanced position has the lower jaw102 moved from its normal position in an anterior direction (indicated with arrow 104) so that the lower jaw102 is now anteriorly relative the upper jaw100. You can use the advanced position of lower jaw 102 to tighten the soft tissues and maintain unobstructed airflow while sleeping.
An intraoral appliance is a device that the patient wears to move the lower jaw anteriorly relative the upper jaw in order to treat sleep apnea. An intraoral appliance is a removable appliance that can be placed into the patient’s jaw prior to sleep. This allows the patient to keep the lower jaw in a forward position while they are awake. Alternate embodiments of the intraoral appliance may include attachments or brackets attached to teeth or anchoring devices placed in the tissue within the intraoral cavity.
The intraoral appliance may take many forms. The intraoral appliance may include at least one shell with multiple cavities that can be used to accommodate the teeth of one jaw (e.g. the upper or lower jaws). You can make the appliance with any combination of metal, glass or reinforced fibers. You can make the appliance in many different ways, including thermoforming and direct fabrication. Alternately, or in combination with other methods, the appliance can also be manufactured with machining. For example, an appliance made from a block material with computer numeric controlled (CNC) machining. The appliances can also be manufactured using additive manufacturing processes like stereolithography and 3-D printing.
“In some cases, the intraoral appliance may include upper and/or lower shells or anchors that are designed to attach to the patient’s lower and upper jaws. The shells are removable and can be used to temporarily cover the patient’s teeth. However, one or both of the lower shells can be attached directly to the bones of the lower and upper jaws. This attachment is described in a co-pending U.S. patent application Ser. No. No. The complete disclosure is included herein by reference. Other cases, the upper or lower shells could be designed to distribute the displacement forces through patient’s teeth and minimize forces that may displace individual teeth relative the jaw. These structures are described in a co-pending U.S. patent Ser. No. No. The complete disclosure is included herein by reference. The upper and lower shells can be permanently or removably mounted and can have any configurations.
“Alternatively, or in combination with other devices, an intraoral appliance may include an upper appliance shell that fits the patient’s upper jaw, and a lower appliance shell that fits the patient?s lower jaw. The appliance may include an advancement device that connects the lower and upper shells in some cases. The advancement apparatus can be set up to move the lower shell anteriorly relative the upper shell. This will allow the patient to advance his mandible. The advancement apparatus can also be configured to limit the movements of the upper or lower jaws by up to six degrees of freedom. This will prevent the jaws returning to their normal position. You can modify the design of the advancement device described in this article to create the forces necessary for mandibular progress. An advancement apparatus may include protruding or recessing members, tension members (e.g. elastics, tension springs), and compression members (e.g. compression springs) as well as combinations of these elements. Components of an advancement apparatus may be located on either the upper or lower shell. An advancement apparatus’ components can be found on any part of the appliance. This includes the buccal, lingual, occlusal, and other surfaces.
“In some embodiments, an advance apparatus can be used for moving the lower jaw to multiple positions, e.g. along the anterior-posterior directions. The lower shell may be moved to and from a number of predetermined positions in order to activate the intraoral appliance. Alternately, the lower shell can be set to move continuously between a position with maximum mandibular advancement/protrusion and a position with minimal or neutral protrusion. The advancement apparatus may be used in various ways to move the lower jaw in an anterior-posterior, vertical, or lateral direction. The advancement apparatus can be used in some instances to move the lower jaw in a substantially anterior-posterior orientation. A plurality of positions may include discrete, continuous, or mixed positions. In some embodiments, the plurality is a finite number of positions that the lower jaw may assume. In other embodiments, the plurality is defined as a continuous range or positions that are bounded by one, more, or more lower boundaries. These include an anterior-posterior or vertical boundary and a lower border in the lateral direction.
The advancement apparatus can control the position of the lower jaw relative to the upper. The amount of mandibular advancement and vertical displacement between the upper and lower jaws can be adjusted according to a treatment plan. The best position for the lower jaw relative the lower jaw to treat sleep apnea depends on many factors. These factors include patient-specific factors like the patient’s anatomy and jaw opening trajectory. Also, how severe and frequent the symptoms are, as well as other factors. The machine learning algorithms described herein can optimize the lower jaw position of a patient based on any combination of these and other factors.
The mandibular advancement treatment can be controlled and advanced to different positions to suit the patient’s current sleep apnea status. The mandible can be moved in a selective manner when the patient has a sleep apnea episode. It can also be pulled back when the event is over. The lower jaw can be advanced only for the time and amount that is necessary to treat sleep apnea. This may help reduce or eliminate unwanted side effects of mandibular advance therapy such as tooth repositioning, muscle strain and jaw discomfort, TMJ discomfort, pain in the teeth, and bite alterations. As described in this article, machine learning algorithms can be used for optimizing the timing and extents of selective mandibular advance.
An advancement apparatus of a mandibular advance appliance can be controlled to control a variety of configurations to produce different amounts jaw displacement (e.g. anterior-posterior or vertical displacement). An advancement apparatus may include one or more advancement mechanisms that can be controlled to move the lower jaw to one of several positions. Protrusions and posts are some examples of advancement structures. The advancement structure’s action can include translating, sliding or rotating, shrinking, winding and expanding, twisting, folding, unfolding. Telescoping is also possible.
“The advancement apparatus may also include at least one actuator that actuates the advancement structures to move the lower jaw to one of several positions. An actuator could be a motor or any other mechanical device that can cause displacement of the mandible. The motor may be programmed to receive control signals from the processor. This will allow the motor to move the advancement structures in accordance with the control signal. Optionally, the motor may transmit signals to the processor indicating the current configuration and progress of the advancements structures, e.g. as feedback.
“Example: The oral appliances described herein may also include a motor or another actuator that is connected between the upper shell and lower shells. It is designed to respond to the processor’s signal to advance or retract a mandible. Motors can move the lower shell relative the upper shell continuously or incrementally over a range of distances, typically between 0.01mm and 20mm, but more commonly between 0.05mm and 8mm. Below are some examples of actuators and motors that can be used to move the mandible.
The motor can include any motor or effector that is self-contained and can be connected to the first or second shells. It will be activated or energized in order to move the lower shell relative the upper shell in response the received signal. The motor may include a rotor attached to one of the lower or upper shells and a follower attached to the other. A lever, or another rotating element that can engage a fixed follower can be included in the rotor to produce relative movement. Other embodiments may include a translator on one shell and a follower the other. A translator is an element that generally converts in the anterior and posterior directions in a plane coplanar with the patient’s jaws. Another alternative is to have the motor consist of a spindle mounted on one of the lower and upper shells, and a tether with one end mounted to be pulled in and out of the spinal and the other attached to one of the shells.
“Referring to FIGS. 2A-2C shows an exemplary intraoral appliance 10. It consists of an upper shell 12 as well as a lower shell 14. The upper and lower shells can be used to attach retainer-like, or aligner-like, devices to the upper and/or lower jaws of patients, as shown. The advancement apparatus that connects the upper and lower shells includes, in this example, a lower advancement mechanism coupled to the 14th shell, the lower advancement structure consisting of a rotor 16 connected to a pivot 19. Pivot 19 may include an actuator, or be coupled to one (not shown), which can rotate the rotor element 16 around the pivot axis. FIG. 2A shows that rotor element 16 can rotate clockwise so that there is sufficient clearance with the upper advancement structure 18, which is coupled to uppershell 12. FIG. 2A shows the patient with his upper and lower jaws free of movement and the lower shell 14 not protruding or advanced. FIG. 2B also shows this position. 2B. As shown in FIG. 2C. Rotor element 16 can be rotated counterclockwise in order to engage the upper advancement structure 18. Lower shell 14 will be displaced relative to upper Shell 12, displacing lower jaw of patient from the first position. You can configure the actuator that rotates rotor 16 to respond to a first control signal from one or more processors, as described below. You can reverse the advancement by rotating the rotor element 16 clockwise in response to another control signal from one or more processors. In FIGS. 2A-2C, the rotor 16 is located on the lower shell 14. 2A-2C in FIGS. 2A-2C. However, it is possible to position the rotor 18 on the upper shell 12 in other embodiments. Both the lower and upper shells may contain a rotor element which can rotate to engage with each other in order to produce mandibular advancement.
FIGS. 3A-3C. Intraoral appliance 20 consists of an upper shell 22, lower shell 24, an advancement apparatus coupling upper and lower shell 22, and an advancement device consisting, in this embodiment, of an upper advancement structure 26 that is coupled to upper shell 22 as well as a lower advancement mechanism 28 that is coupled to lower shell 24. This embodiment’s upper advancement structure 26 has a fixed component 26a and a mobile component 26b that can be moved from a retracted state (as shown in FIG. 3A, and in full-line in FIG. 3B) To an advanced position (shown as full line in FIG. 3A, and in full-line in FIG. 3C) by an actuator, not shown, in response to a initial control signal from one or more processors. The actuator can be coupled to or comprise the upper advancement structure 26 in this example. Lower advancement structure 28 engages lower component 26 b when it is in an advanced position. This displaces lower shell 24 relative upper shell 22. The lower jaw of the patient is then moved from the original position to the second. Retraction of the moveable component 26 can reverse this displacement in response to a second signal from one or more processors. In FIGS. 3A-3C, the movable part 26 b is located on the lower shell 24. 3A-3C. However, it is possible to position the movable part 26 b on the upper shell 22 in other embodiments. Optionally, the upper and lower shells may contain movable components that can interact to produce mandibular advancement.
FIGS. 4A-4B. Intraoral appliance 30 consists of an upper shell 32, and a lower shell 34. An advancement apparatus coupling upper and lower shells 32 and 34 is also included. This advancement apparatus comprises, in this embodiment, an actuator36, a fixed attachment points 40, and a tether elements 38. Upper shell 32 houses the actuator 36. It is connected to lower shell 34 by the tether element 38. In response to one or more processors’ control signals, actuator 36 can adjust the length 38 of the tether elements 38. This includes winding or unwinding 38. As an example, actuator 36 could respond to a control signal from one or more processors and increase the length of tether elements 38 so that upper shell 32, 34, and lower shell 34 remain in an unconstrained state. FIG. 4A. Actuator 36 can also react to another control signal from one or more processors. For example, lower shell 34 may be displace by tether element 38. FIG. 4B. As shown in FIG. 4B, lower shell 34 is displace relative to upper shell 32. 4B results in the lower jaw being moved from the original position to the second position. In FIGS. 2A-2C, the actuator 36 is located on the lower shell 34. 2A-2C in FIGS. 2, it is understood that the actuator 36 may be placed on the lower shell 34 in the embodiment of FIGS. Optionally, the upper and lower shells may include an actuator that winds and unwinds tether 38 to control displacement of the lower 34.
“Alternative embodiments of the systems and methods described in this disclosure can use other types of intraoral devices than motorized or actuator-based appliances.” An ordinary person skilled in the art will recognize that the various embodiments described herein can be applied to any type of appliance for treating sleep apnea.
“Sleep Apnea Monitoring & Treatment System”
The present disclosure also provides methods and systems for collecting and analysing health data, and making healthcare decisions, such as regarding the patient’s sleep patterns and sleep apnea. This is in order to provide selective and controllable mandibular advance. The controllable mandibular advance appliances described herein can be used in conjunction with a system to monitor and treat sleep apnea in patients. The system can monitor the patient’s sleep status and physiological characteristics in order to detect if a sleep disorder is developing. The system can monitor the patient’s physiological characteristics and/or sleep status to detect a possible sleep apnea event. It can then control the mandibular advance appliance to move the patient’s mouth, e.g. by a predetermined amount or until the symptoms are resolved. You can adjust the amount of mandibular advancement to achieve optimal sleep apnea treatment. You can keep the mandible in an advanced position for a set amount of time or until the sleep apnea event has been terminated. At that point, the appliance can be adjusted to return it to its normal position.
“Mandibles can be moved over various distances according to different embodiments. For example, from 0.01 mm up to 0.1mm, 0.1mm to 1.5 mm or 0.5mm to 1mm, 1 mm up to 5 mm and 10 mm respectively, as well as 10 mm upwards relative to the habitual location. Some embodiments allow the mandible to be moved over distances of 0.05 mm up to 5 mm, or 0.05mm to 8 mm anteriorly relative the habitual position.
“In some cases, sensors that are embedded in or external to the appliance may be programmed to continuously collect data during sleep to create a patient-specific profile, including information about patient status. Sleep sounds, temperature, heart rate and EKG can all be recorded. Sensors in the appliance, advancement apparatus, or any other mechanism can track the degree of mandibular advance. A processor that generates the advancement signals can also be used to determine the progress signal. Load sensors are built into the upper or lower shells to track the load on the jaws, arches, and sometimes individual teeth.
These data can be used to track the wearer’s movements and for other purposes. The data could be used to provide feedback. The data may be used to allow?feedback? The processor may apply control algorithms to optimize patient treatment. These algorithms include machine learning algorithms, described herein. The data can be analysed individually or collectively to determine the mandibular advancement and timing required for a patient at a given time. The control could be to activate the device as needed and then deactivate it when the apnea event is over. Other embodiments may control the activation of the device to a minimum level, and then adjust the device to reduce arch/tooth pressure and maintain sufficient mandibular advancement in order to stop the apnea. Alternately, data (especially the arch and tooth loads data) can be used to reduce the load on the teeth/arches while still allowing sufficient mandibular advancement for the treatment of snoring or apnea.
The collected data could also be used to generate alarms for patients and reports about patient treatment and status. The collected data could be used to detect irregularities in sleep patterns, and if necessary, take action (e.g., send an alarm for help). Data collected over time may be used to detect problems early, such as worsening breathing patterns or sleeping problems. Data can be reviewed by the healthcare professional or automatically assessed by the processor.
“In certain embodiments, the appliance can be activated prior to snoring if the system identifies patient parameters or data that indicate that snoring is about to start. The system can learn by collecting data over time from each patient. The system can learn patient-specific patterns of sleep and snoring by collecting data over time. The system can also learn from similar experiences to determine when the device should be deactivated.
Other features of the disclosed systems can detect pressure on the appliance. This allows the system to control or balance the pressure. The system can reduce the protrusion position of the appliance if the patient feels discomfort or if the appliance pressure is too high. The system can also control minor movements of the oral appliance, such as to reduce or eliminate pressure at one point of the temporomandibular (TMJ) joint.
The data can be used to create a patient-specific profile, which can be used for diagnosis, prescription preparation, and control and improvement of the intraoral appliance. The system can reduce or eliminate sleep problems by adjusting the load on the arches and minimizing the burden on them. When the system is in use, it can detect irregularities in sleep patterns and send an alert or alarm to other people. To identify problems early, patient-specific data can be collected. This includes information about the severity of breathing patterns, increased frequency or problems sleeping. These comparisons can be made with prior data from the same patient, or statistical data from a group of patients. A patient-specific profile is useful for providing personalized sleep apnea treatment.
“FIG. “FIG. The ‘processor 504 is also known as an?controller? Processor 504 can be referred to herein as a processor and/or a controller. Except where otherwise noted, the term?controller’ is used herein. As used herein,?controller? und?processor? are interchangeable. Both terms can be interchanged. Processor 504 may be a single processor, or a combination of multiple processors in different embodiments. System 500 may also include a memory device (not illustrated) that contains executable instructions. The processor 504 can then be configured to execute those instructions. As described below, sensors 502 can be used to monitor sleep apnea symptoms in patients. The instructions for processor 504 to receive sensor data and detect, identify and/or assess physiological events can be executed by the processor 504. As described in this article, processor 504 can execute instructions to transmit control signals for intraoral appliance 506. The processor 504 can execute any number of algorithms including machine learning algorithms.
“Systems disclosed in the present disclosure include one or more processors that are capable of receiving sensor data and using the sensor data to assess the symptoms of a patient, including those associated with sleep apnea. In some embodiments processor 504 may execute instructions to detect physiological events, such as the onset and termination of a sleep-apnea event. In some embodiments processor 504 may be able to execute instructions to detect physiological discrepancies, such as discrepancies between a current and previous sleeping pattern. Processor 504 may be able to execute instructions to perform physiological assessments, such as determining whether an apnea event is likely to occur or not. One or more microprocessors can be included in processor 504 and can receive data from sensors 502 regarding patient status. This can be done in either a wired or wireless configuration or a combination of both. The processor 504 can be combined with one or more sensors 502 in certain embodiments to form an integrated system. This could include a computer, digital workstation or computer housed within a single housing component.
“Systems disclosed in the present disclosure include one or more processors that transmit control signals to intraoral appliances. In some embodiments processor 504 can be programmed to execute instructions to detect, forecast, or assess a pre or post-apnea condition based on sensor data from sensors 502, and to transmit instructions to intraoral device 506 to cause intraoral appliances 506 to move the lower jaw of the patient to an advanced position or protruded position in order to treat sleep apnea and/or suppress snoring. As described further herein, actuator 508 can move the patient’s lower jaw in response to the control signal. The processor 504 can control the position of the intraoral device 506 or actuator 508 by placing it in the mouth. In some embodiments, the processor 504 can adjust the distance or the direction in which the appliance is in the patient’s mouth. The processor 504 can be set up to send a control signal to the intraoral appliance 506 or actuator 508 via wired, wireless, or combination thereof. Actuator 508 could be an embedded motor or mechanism that allows for mandibular movement, e.g. Advancement can be in an anterior-posterior, vertical, or combination thereof.
In some embodiments, the processor 504 can send an intraoral signal to actuator 508 and/or intraoral appliance 506 to cause the device to retract the lower jaw from its normal position. This is done based on sensor data 502. A first control signal can be sent to intraoral device 506 or actuator 508, causing intraoral appliances 506 to move from one position to another when an onset of sleep apnea is detected. Then, processor 504 may send a second control signal, triggering intraoral apparatus 506 to retract from the second to first position, when the end of a sleeping apnea is detected. Alternately, processor 504 could be set up to send control signals and actuator 508 to intraoral appliance 506. This will cause intraoral appliance 508 to retract the mandible partially or completely after a predetermined period. The predetermined time can range between 1 minute and 10 minutes. The predetermined time period may be as short as 1 minute, 2 minutes or 5 minutes, 10 mins, 15 minutes or 20 minutes, depending on the embodiment.
“The systems of the present disclosure allow for the collection of data over time on patient’s sleep apnea patterns and the use of such data to improve treatment. Some embodiments of processor 504 allow for the collection of sensor data from sensors 502, which includes patient data regarding sleep apnea patterns. The patient data can be saved on a memory device, downloaded, or uploaded to the patient’s doctor, other treatment management personnel to system management personnel, as well as to a database like a cloud database for future retrieval. Other processors, including processor 504, can access the patient data. They may use algorithms (including machine learning algorithms) or other artificial intelligence-based methods that will improve patient treatment protocols. Processor 504 may execute instructions to analyze patient data and improve methods or algorithms for detection and prediction of physiological events. In some embodiments processor 504 is able to evaluate patient data in order to improve accuracy of machine learning algorithms for predicting the onset or termination of apnea events. This can be done based on past symptoms and/or any other relevant data.
“Physiological Sensors & Data”
“Systems, methods and devices, as well as apparatus, of the present disclosure, can include one or more sensors that are adapted to monitor patient parameters such physiological data. The physiological data may be linked to the patient’s sleep patterns and sleep apnea episodes, normal physiological events, or abnormal physiological events. The sensors can monitor the physiological data of a patient in real time and transmit it as one or several signals that can be received by one (e.g., a suitable system for sleep apnea monitoring or treatment). Sensor data can indicate events or patient symptoms. For example, symptoms that are associated with the onset and/or decrease in sleep apnea events. The sensor data may be indicative of patient sleep patterns and/or physiological information during sleep in some embodiments.
“Sensors used in the systems disclosed (e.g. sensor(s) 502 or 500) may monitor any of a number of patient symptoms or status indicators. This includes sounds such as breathing, cessation or snoring and heartbeat. The sensors may be used to monitor breathing patterns. This includes changes in breathing rate, inhalation length, inhalation length, and length between breaths. Temperature, temperature changes and other symptoms can also be detected. You can also measure saliva and other data, even if they are not directly related to sleep disorder. The sensors described herein can monitor physiological information, including breathing sounds, snoring, breathing rate and respiratory airflow, chest expansion, oxygen levels, and cardiac data (e.g. heart rate, EKG data), sleep position, sleeping movements, blood sugar, and brain activity (e.g. EEG data) or variants and/or combinations thereof.
You can use any combination of sensors, including one, two or three, four, five or more types. Examples of sensor types that can be used in accordance with the embodiment include, but are not limited, audio sensors (e.g. microphones), video sensors. oxygen sensors (e.g. pulse oximeters), motion sensors. temperature sensors. strain gauges. force sensors. pressure sensors. heart rate monitors. blood pressure monitors. EKG sensors. EEG sensors. Any other type of sensor suitable for obtaining physiological data relating to the patient’s sleeping status and/or sleep disorder.
The sensors described in this article can be placed on the patient’s skin, inside or outside of their bodies (internally positioned), as well as on the patient’s surface. The sensors can be external to the patient in some embodiments. For example, they may include an external microphone that detects breathing sounds, an external camera to detect sleeping position, or an EKG machine to determine the heart rate. Some embodiments incorporate externally-positioned sensors as part of an external process, such as a processor mounted on a table and positioned next to the patient while they sleep.
“In some embodiments, monitoring can be performed by a sensor on or inside the patient, such a sensor mounted on an intraoral device worn by the patient. The sensors can be mounted on an intraoral appliance. They can communicate wirelessly with other components of the system such as processors or wired. The sensor may be mounted or placed in the upper or lower shells of intraoral appliances. Monitoring intraoral breathing sounds, respiration rate, sleep position and/or variations thereof can all be included in intraoral monitoring. You can integrate sensors that are internally positioned into your oral appliance in a variety of ways and in a variety of places, depending on the embodiments.
“The sensors described in this document can communicate with and transmit data to a processor through a wired connection (such as a USB link), a wireless link, such as Bluetooth, and/or variants thereof or combinations thereof.”
“Machine Learning Based Control of Mandibular Advancement
“Some embodiments include one or more processors (e.g. the processor 504 in the system 500). These processors can automatically collect and analyze any or all patient parameters that have been sensed via one or more sensors. These parameters can be tracked and monitored over time to identify changes. This may allow certain symptoms and parameters of patients to be linked with sleep apnea or snoring. These patient parameters can be used to predict when an apnea event will occur, and to initiate treatment with mandibular advancement. The processor may be configured to use a machine-learning algorithm to identify patient-specific correlations between physiological parameters, symptoms, and sleep apnea events. These patient-specific correlations are used to predict when a sleep disorder will occur. Some symptoms that could be associated with the onset of sleep apnea events include, but are not limited, changes to blood oxygen levels, heart rate, breathing rate, rhythm changes, changes, body temperature, electrical resistance changes (e.g. skin), increased sweating or decreased sweating. Machine learning algorithms, which are computer-based, can be used to identify combinations of physiological parameters or symptoms that may help detect the onset sleep apnea.
“FIG. “FIG. 6A shows a method 600 to detect and treat sleep apnea events, according to embodiments. As with all the methods described herein. The method 600 can be performed using any of the apparatus, devices and systems. One or more processors can perform one or more of the steps in the method 600 (e.g. processor 504 from the system 500) to monitor and treat a patient with sleep apnea.
“In step 602, one or more sensors sends a set of sensor data. As described in this article, the sensors can be set up to monitor the patient for signs and symptoms that may indicate sleep apnea. The sensors can transmit their respective sensor data to the controlling processor at predetermined intervals or continuously throughout the monitoring period. To ensure accurate monitoring of the patient?s sleep and/or sleep apnea, you can adjust the rate at which sensor data are provided.
“In step 604, the onset or response of a sleep disorder is detected using the sensor data. The sensor data may indicate physiological parameters or symptoms that could be associated with the onset sleep apnea events. The sensor data could indicate, for example, that a sleep apnea episode has occurred or is currently occurring. The sensor data may also indicate, in combination with other information, that a sleep-apnea event is imminent or likely to occur. Step 604 may be performed with a computer-implemented algorithm. This algorithm may or may not include a machine learning algorithm. For example, a machine learning algorithm can be used to determine physiological parameters and/or the symptoms that are represented by the set sensor data and/or whether these parameters and/or the symptoms indicate the onset or continuation of a sleep disorder. The machine learning algorithm output can be used to detect the onset or recurrence of sleep apnea events. It can also be used with other patient-specific criteria (e.g. patient-specific changes such as heart rate and breathing rate). These are just a few examples of machine learning algorithms that can be used with the methods disclosed.
“In step 606, an intraoral device is sent a control signal to move the lower jaw of the patient’s from a first to a second position in order to treat sleep apnea. Any of the mandibular advance appliances described herein can be used as an intraoral appliance. The current position of the patient?s jaw can be used as the first position. The first position may be the current position of the patient’s jaw. In other embodiments, it can also be a normal position, such as a position that the patient assumes during sleep. A second position could be one in which the jaw is advanced relative to the maxilla.
“In some embodiments the second jaw position can be a patient-specific position, which is tailored for each patient. Optionally, the second position of the jaw can be determined by a machine learning algorithm. The machine learning algorithm can be used, for example, to determine the optimal amount of mandibular advance that will treat the patient’s sleep disorder. This is e.g. in terms of effectiveness and mitigating side effects such as discomfort. Patient-specific factors, such as anatomy, physiology or tolerance for discomfort, can affect the optimal amount of advancement. The optimal amount of advancement may also vary depending on the circumstances of the sleep apnea episode, such as its severity. The machine learning algorithm can therefore be used to determine the optimal amount of advancement based on the physiological parameters and/or symptoms, patient-specific factors, the circumstances surrounding the sleep apnea episode, or combinations thereof. The machine learning algorithm may be trained using data from the patient’s previous sleep apnea episodes to establish patient-specific correlations between treatment efficacy and mandibular advancement.
“In some embodiments the step 606 is causing the intraoral device to move the lower jaw anteriorly, until the reduction or cessation or occurrence of sleep apnea symptoms are detected (e.g. via one or more sensors). The control signal may cause the appliance’s mandible to move in an incremental fashion until sensor data indicates that sleep apnea symptoms are reduced or stopped. It is possible for changes in sleep apnea symptoms, such as slow advancement, to be detected. This can be used to reduce the jaw displacement that is applied to treat sleep apnea. It may also be helpful in mitigating side effects like patient discomfort, muscle strain and TMJ dysfunction.
The length of time that the jaw remains in an advanced position can vary depending on the patient. It can take from a few seconds up to several hours. Some patients only need a few jaw movements to cause muscles in the upper airway and prevent snoring and sleep apnea. The processors described herein can be configured to retract the patient?s mandible back to its original position after the sleep apnea event subsides and/or after a predetermined interval. The processor can be programmed to keep the jaw in an elevated position for less that 75%, less then 50%, less over 40%, less about 30%, less under 20%, less below 10%, and less than 5% of total sleep time. The processor can also be set up to keep the jaw in an advanced position for a maximum of 5 hours, not more than 2 hours or more than 30 mins, and no longer than 20 minutes. It should also stop the processor from storing more than 10 minutes or more information at once. The processor may be able to analyze the sensor data and determine whether sleep apnea symptoms are decreasing or stopping (e.g. with the aid of a machine-learning algorithm), and then retract the patient’s jaw accordingly. This can be helpful in mitigating side effects like patient discomfort, muscle strain and TMJ dysfunction.
Alternative embodiments of the method 600 do not require the jaw to be advanced to a static position. Instead, the intraoral appliance can cause the mandible to move through a sequence of movements. Patients may have different preferences regarding the types of movements that they use to treat sleep apnea. The machine learning algorithms described in this article can be used to identify patient-specific movements for treating sleep apnea.
“FIG. “FIG. 6B shows a method 610 to terminate treatment for a sleep apnea episode, according to embodiments. One or more of the steps in the method 610 may be executed by processors within a system that monitors and treats a patient with sleep apnea (e.g. processor 504 in the system 500). The method 610 can be performed following the method 600 in some embodiments to allow automatic advancement or retraction of mandibles based on the patient’s status with sleep apnea.
“In step 612, one or more sensors provide a set of sensor information. Each sensor can either provide data at predetermined times or continuously, similar to step 602 in the method 600. You can adjust the rate at which data is sent to monitor patient’s sleep and/or sleep apnea.
“In step 614 the termination of sleep-apnea events is detected based or in response to the collection of sensor data. Sensor data may indicate physiological parameters or symptoms that can be associated with the end of a sleep apnea episode. The sensor data could indicate that the sleep disorder has ended or is about to end, for example, due to the appearance of less severe symptoms. The sensor data may also indicate, in combination with other information, that a sleep-apnea event is nearing or is likely to end. Step 614 may be performed with a computer-implemented algorithm. This algorithm may or may not include a machine learning algorithm. For example, a machine learning algorithm can be used to determine physiological parameters and/or the symptoms that are represented by the set sensor data and/or whether these parameters and/or the symptoms indicate the termination of a sleeping apnea episode. The machine learning algorithm output can be used to detect the end of a sleep-apnea episode. The machine learning algorithm could be the same as the one used in method 600 or a different algorithm.
“In step 616, an intraoral device is sent a control signal to move the lower jaw of the patient’s from the second to the first position. The first position may be the current or usual position of the patient’s lower jaw. The second position may be a mandible advanced jaw position. Some embodiments allow the patient to have their jaw moved to the second position prior to treating sleep apnea (e.g. according to the method 600). The step 616 retracts mandible back to the original position to end the mandibular advancement treatment.
“In addition to detecting the onset and/or end of sleep apnea events in real time, the processors can be set up to receive feedback about the efficacy of the mandibular enhancement treatment. The processor can, for example, receive feedback data from one or more sensors and then analyze it to determine if the patient’s symptoms and physiological parameters have improved. The processor can make adjustments to the mandible position if the current treatment is not effective. This can be done in real-time to allow for dynamic adjustments in order to improve the treatment of sleep apnea.
“FIG. “FIG. 6C shows a method 620 to improve the effectiveness of a sleep-apnea treatment. It is in accordance with embodiments. One or more of the steps in the method 620 may be performed by processors within a system that monitors and treats a patient with sleep apnea (e.g. processor 504 of system 500). Some embodiments of the method 620 are performed after the method 600 or before the method 610 to allow dynamic changes to the treatment plan.
“In step 622, one or more sensors provide a set data while the lower jaw remains in the second position (e.g. the advanced position). Sensor data can be provided at predetermined times or continuously. The rate at which the sensor data is delivered can also be adjusted to ensure that the patient has accurate monitoring of their sleep and/or sleep apnea.
“Based on the sensor data, step 624 determines the effectiveness of the second position for treating the sleep apnea episode. Sensor data may indicate physiological parameters or symptoms associated with sleep apnea events. It is possible to determine the effectiveness of the treatment by checking whether patient’s physiological parameters have improved or fallen back to normal, and whether symptoms are less severe or more severe. A treatment that is effective may be associated to normal physiological parameters, or the absence of/reduction in sleep apneasymptoms. An ineffective treatment could be associated with abnormal physiological conditions and/or the existence of sleep apnea signs. Step 624 may be performed by a computer-implemented algorithm. This algorithm may or may not include a machine learning algorithm. For example, a machine learning algorithm can be used to determine physiological parameters and/or the symptoms that are represented by the set sensor data and/or whether these parameters and/or the symptoms indicate an effective treatment. The machine learning algorithm could be the same as the one used in other methods, or it may be a completely different algorithm.
The determined effectiveness can be used to improve the machine learning algorithm. To improve the algorithm’s performance, input data can include the determined effectiveness, jaw position that is associated with it, and/or sensor data. This data could include information about the patient’s current physiological parameters, symptoms, and/or other relevant data. Feedback data can be used to improve the algorithm’s accuracy in determining the most effective treatment plan for the patient with sleep apnea.
“In step 626, the modified position of the lower jaw is determined to increase the effectiveness of treating the sleep disorder. A machine learning algorithm, or another computer-implemented algorithm, can be used to determine the best position for the mandible. A machine learning algorithm can also be used to determine whether there is a change in mandibular progress. The algorithm can also determine changes in jaw configurations, such as the amount of mouth opening. This is an option that could improve efficiency. The patient’s physiological parameters, symptoms, and circumstances, as well as combinations thereof, can determine the change. Some embodiments allow the machine learning algorithm to be trained using patient-specific data, such as previous sleep apnea event data, in order to identify patient-specific correlations between treatment effectiveness and jaw position.
“In step 628, an intraoral appliance is sent a control signal to move the lower jaw to the new position. The method 620 can then be repeated as many times as necessary to provide continuous feedback on treatment effectiveness and allow for the system to adjust the appliance to ensure that it is performing at its best.
The various data collected during the mandibular advance treatment can be stored (e.g. on one or more memory devices associated to the treatment system) for further processing and analysis. These data could include information about the patient’s past sleep patterns (e.g. duration and physiological parameters during sleep), prior sleep apnea (e.g. number, duration and/or severity sleep apnea episodes, symptoms during sleep events, physiological parameters during these events), and any previous mandibular advances treatments (e.g. amount and/or length of advancement, number and effectiveness of advancement in treating sleeping apnea). The data collected can also include data about patient preferences, such as patient preferences regarding pain, treatment effectiveness, satisfaction, and so forth. The processor could be programmed to determine if the mandibular advancement time and length is related to success in treating snoring and apnea. As data is collected over time, it may be possible to optimize treatment parameters and use them moving forward. This data collection and analysis may be done within the system (e.g. a microprocessor) or externally via communication over the internet or other suitable remote access methods. A system can also be used to contact a doctor periodically and/or automatically in order for him to give data or alerts about serious conditions.
“In some embodiments the data collected (e.g. previous sleep patterns, past sleep apnea events patterns, patient preferences) can be used to update machine learning algorithms. The stored data can be used as training data to update the machine learning algorithm. The update of the machine-learning algorithm may include updating the models, classifications, correlations or other data structures that are used by the algorithm to generate the predictions and determinations described. This allows the system to adapt to patient’s sleeping patterns and sleep apnea, and to improve the efficacy of the mandibular advance treatment regimen for treating sleep apnea. As the system is used more often, it can be made more customized for each patient.
“Optionally, patient-specific data can also be added to a sleep apnea database for multiple patients. This database can then be processed and analyzed in order to identify information that could be useful in improving sleep apnea understanding and designing effective treatments. These analysis results can be used for patient-specific treatments such as those based on the selective and permanent mandibular advancement methods, methods, or devices described herein.
Other features that may be optionally provided by the system include activating other functions or devices which could contribute to cessation or cessation of snoring or apnea, and providing alerts locally or remotely under certain circumstances. The processor may be programmed to execute instructions to detect physiological discrepancies in patients, such as those identified by sensor data. These discrepancies may include discrepancies between the patient’s normal or expected physiological parameters and the patient’s current physiological parameters. The discrepancy could be between the expected or normal sleeping patterns of the patient and the current sleeping patterns of the patient in some embodiments. The processor can use a machine-learning algorithm in various embodiments to detect discrepancies. This could be done by comparing historical or predicted data with patient’s current state. The processor can create an alert if a discrepancy in data is detected. This could be on a user device, such as a digital processing gadget. To inform the patient or their care provider of potential medical issues, the alert can be sent to them. If the discrepancy is indicative that there is a medical emergency, you can take immediate action. The alert can be used to call the emergency department, wake the patient and/or contact their care provider.
The systems described herein can implement many different types of machine-learning algorithms to provide patient-specific monitoring and treatment. The machine learning algorithms described in this document can include supervised learning methods such as classification and regression. The machine learning algorithms described in this document can also include unsupervised learning methods such as clustering. These examples of machine learning are not intended to be exhaustive. Other methods and approaches are available to those skilled in the art to generate and apply predictive models, make physiological assessments, and are included within the scope and capabilities of the systems, methods devices, and apparatus described herein.
“Machine Learning Algorithms” can include reinforcement learning algorithms and representation learning algorithm, similarity learning algorithm, similarity learning algorithm, recommendation systems, metric learning methods, metric learning programs, recommendation systems and sparse dictionary learning algoritms, genetic algorithms, genetic algorithms, inductive programming and/or variations thereof, or combinations thereof.
“Machine Learning Algorithms” can include supervised learning methods such as regression, classification, regression methods and/or variations thereof.
“Machine-learning algorithms described herein may include decision tree learning. This can be used to map observations regarding physiological data from patients in order to make predictions. Regression tree learning and classification tree learning are two examples of decision tree learning.
“Machine learning algorithms described in this article can include association rule learning. This can be used to determine relationships between variables obtained via physiological data to make predictions. Associative rule learning may include, but not be limited to: a priori algorithms; equivalence-class transformation algorithms; frequent pattern growth algorithms; context-based association rule mining algorithms; node set based algorithms; general unary hypothesis automata, including ASSOC procedures, OPUS and/or variants thereof or combinations thereof.
Summary for “Systems and Methods for Positioning a Patient’s Mandible in Response to Sleep Apnea Status”
“Obstructive sleep apnea (hereinafter ?OSA?) A medical condition that causes a blockage in the upper airway, either completely or partially, during sleep. It could be caused by relaxation of soft tissues or muscles around the throat (e.g. the soft palate, back, tongue, tonsils, uvula and pharynx) during sleeping. OSA episodes can occur several times per night, disrupting the patient’s sleeping cycle. Chronic OSA suffers may experience sleep deprivation and excessive daytime sleepiness. They might also experience chronic fatigue, chronic headaches, snoring, hypoxia, and chronic fatigue.
To treat OSA, mandibular advancement devices have been suggested. The mandibular advancement device can be worn in the mouth above the lower and upper jaws. This device is used to treat sleep apnea. It moves the lower jaw in the anterior direction relative the upper jaw. This may tighten the tissues in the upper airway and prevent obstruction during sleep.
In some cases, however, mandibular advancement devices used to treat OSA can have undesirable side effects such as jaw discomfort, tooth repositioning, or muscle strain. It would be beneficial to have improved techniques and apparatus for treating sleep apnea or snoring. It would be beneficial to have improved apparatus and methods that allow mandibular advancement without undesirable side effects like tooth repositioning and jaw discomfort.
The systems, methods, devices and apparatus described herein offer improved treatment for obstructive sleeping apnea. They also have fewer side effects such as jaw discomfort, tooth repositioning, muscle strain, and jaw discomfort. The mandibular advancement device may be used in combination with patient monitoring and personalized treatment to treat sleep apnea. This will improve the detection and treatment of symptoms related to sleep apnea. Machine learning algorithms can accurately detect and terminate sleep apnea events. These algorithms can also be customized for each patient. They improve the position and durations of jaw displacement, which allows patients to effectively treat sleep apnea. The systems described herein include sensors that monitor patients for sleep apnea symptoms and processors that interpret instructions from the sensors to detect sleep events more accurately based on the patient data. The processors may execute machine learning algorithms to optimize the treatment course and detect symptoms. These algorithms can be based on patient-specific data and factors, such as past sleep apnea events. The processors described herein can transmit control signals to an oral appliance to treat sleep apnea symptoms. Control signals can cause an intraoral appliance to move the lower jaw to a position specified by the machine learning algorithm in order to effectively treat sleep apnea. This will reduce unwanted side effects and increase effectiveness.
“One aspect of the invention relates to a system for monitoring and treating insomnia in patients. The system comprises: one or multiple sensors that monitor the patient’s symptoms; an intraoral device worn by the patient; one to three processors; and memory containing instructions executable by one or two processors. These instructions cause the processors: to receive sensor data from the sensors; to detect the onset of sleep apnea using a machine-learning algorithm; to transmit to the intraoral apparatus a control signal to move the lower jaw
“Another aspect of the invention is a system for monitoring and treating insomnia in a patient. The system comprises: one or multiple processors; and memory containing instructions executable by one or several processors. These instructions cause the processors: to receive sensor data from one of more sensors, to detect the onset of sleep apnea and to transmit to an intraoral appliance a control signal to move the lower jaw of the patient’s from a first to a second position to treat the sleep disorder.
“Another aspect of the invention is a method of monitoring and treating sleep disordered breathing in a patient. The method involves: receiving sensor data from one or several sensors to monitor the patient’s sleep patterns; detecting the onset of sleep apnea events in response to the sensor data; and transmitting control signals to an intraoral device worn by the patient to move the lower jaw from a first to a second position to treat the sleep disordered breathing event.
“Other objects or features of this invention will be apparent through a review the specification, claims and attached figures.”
“INCORPORATION BY RESEARCH”
“All publications, patents and patent applications mentioned herein are herein incorporated as if each publication, patent, and/or patent application were specifically and individually indicated that they would be incorporated by refer.”
The following detailed description will help you to understand the features and benefits of the disclosure. It also includes illustrative embodiments in which the principles and embodiments of this disclosure are used.
“As used in this article, the term ‘and/or’ is It is used to indicate that two words, expressions or sentences are to be taken together or separately. Example: A and/or A can be used to indicate that A or B includes A, B, and both A and B.
These systems, methods, devices, and apparatus are for positioning the patient’s lower jaw in response to their sleep apnea status. Systems are available for treating and monitoring sleep apnea. The systems include: one or several sensors that monitor the patient’s symptoms; an intraoral device worn by the patient; one to three processors; and memory containing instructions to instruct the processors to trigger the one or two processors to: Receive sensor data from the sensors; detect the onset of sleep apnea using a machine-learning algorithm; transmit a control signal (to the intraoral apparatus) to move the lower jaw of the patient to a second to treat the event
“In various aspects, methods for monitoring and treating sleep disordered breathing in a patient are provided. These methods include: receiving sensor data from one of more sensors to monitor for sleep disorders; detecting the onset of sleep apnea using a machine-learning algorithm executed by one to more processors; transmitting a control signal for an intraoral device worn by the patient to move the lower jaw from a first to a second location in order to treat the sleep disordered breathing event.
“In various ways, one or several non-transitory computer readable storage media are provided. They contain instructions that, when executed on one or multiple processors of a system monitoring and treating sleep disordered breathing in a patient’s system, cause the system at least to: Receive a set sensor data from one of more sensors to monitor the patient for signs and symptoms of sleep apnea. Using the sensor data, detect the onset of a sleep disordered event using a machine-learning algorithm
One or more sensors can be used to measure breathing sounds, snoring, breathing rate, respiratory flow, chest expansion and oxygen level. They also can be used to determine sleeping position or combination thereof. This data may indicate symptoms that are associated with sleep apnea. The machine learning algorithm can also be tailored to each patient. The patient’s previous sleep apnea events can be used to customize the machine learning algorithm. You can customize the machine learning algorithm to your patient by using previous sleep patterns. Instructions can also cause the system detect a discrepancy in a patient’s current sleeping patterns and previous sleep patterns and generate an alert.
The methods also include: identifying, using one or more processing units, a discrepancy in a patient’s current and previous sleeping patterns; and creating an alert with the aid of one or more processing units to indicate the discrepancy. The first position could be a normal jaw position, while the second can be advanced jaw position.
“The instructions may also cause the system: to receive a second set sensor data from one or more sensors; to detect, using machine learning algorithms, the termination of the sleep-apnea event based upon the second set sensor data; to transmit a second control signal (to the intraoral device) to cause the intraoral apparatus to move the lower jaw of a patient from the second to the first positions. Instructions can also cause the system using the machine learning algorithm to determine the second position of the lower jaw. Further, the instructions could cause the system: to receive a third set sensor data from one or more sensors while lower jaw is in second position; and to determine the effectiveness of the second lower jaw position in treating sleep apnea events based on that third set sensor data. Based on the results, the instructions may also cause the system’s machine learning algorithm to be updated. Further, the instructions could cause the system to: use the machine learning algorithm to determine a modified lower jaw position to improve the effectiveness in treating sleep apnea events; transmit a third control signal (to the intraoral appliance) to move the lower jaw into the modified position.
“The methods also include: receiving, using one or multiple processors, another set of sensor information from the one/more sensors; detecting, using the one/more processors and the machine learning algorithm; terminating the sleep apnea episode based on this second set sensor data; and transmitting, via the one/more processors, a control signal to the intraoral device to cause the intraoral appliances to move the lower jaw of a patient from the second to the first positions. Methods can also include determining the second position of the lower jaw with the machine learning algorithm. Further, the methods may include receiving data from one or more sensors with the lower jaw in the second position. Based on this data, the one or two processors can determine the effectiveness of the lower jaw position in treating sleep apnea events. Based on the results, the methods may also include updating the machine-learning algorithm. These methods may also include determining the position of the lower jaw using one or more processors. This is done to increase the effectiveness of treatment for sleep apnea. The third control signal can be transmitted to the intraoral device to move the lower jaw into the new position with the aid of one or more processors.
The second set of sensor data may indicate a decrease in symptoms related to sleep apnea. An intraoral appliance may consist of an upper shell that fits on the patient’s upper jaw; a lowershell that fits on the patient’s lower jaw; and an advancement device coupling the upper and lower shells. The advancement apparatus is designed to move the lower shell relative the upper shell according to control signals from one or more processors. This allows the patient to lose their lower jaw. The advancement apparatus may be configured to move the lower shell in a variety of positions relative to its upper counterpart. An advancement apparatus may include an upper advancement structure that is coupled to an upper shell, and a lower advancement mechanism that is coupled to an lower shell. A control signal can be used to cause the lower advancement and upper advancement structures to engage with one another. This will displace the lower shell relative the upper shell. An actuator can be used to adjust the length of the tether elements extending between the upper and lower shells in response to control signals. This will cause the lower shell to be displace relative to the upper.
“Intraoral appliances are used to treat sleep apnea by mandibular advancement in various ways. The apparatus comprises an upper shell that fits on the upper jaw of the patient and a lower shell that fits on the lower jaw. An advancement apparatus coupling the upper and lower shells, wherein the advancement device is designed to move the lower shell relative the upper shell in response control signals from one or more processors.
“The present disclosure, in various aspects, provides a patient-specific approach for sleep apnea. It uses a feedback control system that monitors the patient’s sleep apnea status and actively controls the mandibular position to respond and reduce snoring.
A system for mandibular advancement can be described as an oral appliance, sensor and controller. An oral appliance can be used to advance the mandible of a patient relative to the upper jaw (maxilla).
“The present disclosure, in various aspects, provides a motorized? An intraoral appliance that can selectively move and retract the mandible of a patient relative to their upper jaw (maxilla) is provided. The oral appliances can be removed from the mandible if the patient is not snoring or experiencing other symptoms associated with sleep apnea. configuration. However, the present disclosure allows for the monitoring of sleep apnea and the activation of the intraoral appliance to activate the mandible to provide treatment. The system can optionally retract the mandible if the apnea event has stopped.
An oral appliance can be described in many ways. It may include an upper anchor, lower anchor and a motor or some other mechanism that allows the lower attachment to be moved and retracted relative to the upper attachment. The oral appliance may be used in conjunction with the above-described system. In this case, the motor or another mechanism can be controlled by a signal, usually generated by a controller and sensor in response to sleep apnea symptoms.
“In different aspects, a method of advancing a patient?s mandible to cure sleep apnea involves monitoring the patient for signs and generating a signal when their sleep apnea status changes. Then, selectively moving and/or retracting an anchor that is attached to the patient?s lower jaw relative to an anchor that is secured to his/her mandible.
“The systems, methods and devices described herein include systems for mandibular advance. They can be described as: An oral appliance that advances a patient’s mandible relative the upper jaw; a sensor to detect when the patient is eligible for mandibular advance; and a controller or processor that receives a signal (from the sensor) to indicate whether the patient is eligible and sends it to the oral device to retract or advance the mandible. An upper anchor that is secured to the patient?s upper jaw and a lower anchor that is secured to the lower jaw of the patient can be used as the oral appliance. A motor, which is coupled between the lower and upper anchors, will respond to the processor and controller to move or retract the mandible. The sensor can sense at least one of the following: breathing sounds, cardiac data, respiratory airflow, cardiac data, or sleep position. An external device can also be included in the system. The controller or processor can include the sensor. The sensor can also be integrated into the oral appliance. A controller or processor can be programmed to send a signal to the mouth to move the mandible if it receives an alert from the sensor. A controller or processor can also be configured to send a signal to the mouth to retract the mandible if it receives a signal associated with an onset of an apnea event. A controller and/or processor may be configured to send a signal to the appliance to retract it after a set time. The controller and/or the processor can be programmed to collect data over time about patient’s apnea patterns and then use this data to predict when an apnea event will occur.
“In different aspects, the systems, methods and devices described herein include oral appliances that consist of an upper anchor that couples to the patient?s upper jaw and a lower anchor that couples to the mandible. A motor is used to move the lower anchor relative the upper anchor according to a signal triggered by sleep apnea symptoms. You can have the upper and lower anchors removably attached over the patient’s teeth. You can attach the upper and lower anchors to the mandible and upper jaw bones of patients. A motor may consist of a rotor for one of the lower anchors or a follower for the other anchor. A translator can be attached to one of the lower and upper anchors, and a follower on another of the anchors. A spindle can be mounted on one of the lower anchors. The spindle can also attach a tether to one anchor.
“In different aspects, the systems, methods and devices described herein include methods of advancing a patient?s mandible in order to treat sleep apnea. These methods include: monitoring the patient for signs and symptoms; generating a signal when their sleep apnea status changes. And selectively moving a lower anchor relative to an anchor attached to the patient?s upper jaw. Monitoring may include monitoring at least one of the following: breathing sounds, respiratory airflow, cardiac data and sleep position. A sensor can be attached to the patient for monitoring. A sensor attached to an appliance worn by a patient can perform monitoring. The act of generating can be described as a signal to move the mandible when there are symptoms that indicate an onset or recurrence of an apnea episode.
“Generating” can be described as the act of generating a signal to retract a mandible when there is a decrease in symptoms due to an apnea episode. The act of generating can be described as producing a signal to retract a mandible after a certain time. This method may also include collecting data over time about the patient’s apnea patterns and using these data to predict when an apnea event will occur. The motor can be activated between the lower anchor and the upper anchor to selectively advance the anchor.
“Mandibular Advancement Apparatus”
“Now, let’s turn to the drawings. In which like numbers designate similar elements in the various figures FIG. 1A shows an upper jaw 100 and lower jaw 102, respectively, of a patient in a habitual position. This is in accordance to embodiments. The normal closed position of the lower and upper jaws 100, 101 can be called the habitual occlusal. If the upper and lower jaws 100,102 are in their normal occlusal relationship during sleep, patients suffering from sleep apnea can experience blocked airflow. This is due to relaxation of soft tissue around the upper or upper airway.
“FIG. “FIG. In accordance with embodiments, the occlusal position. The advanced position has the lower jaw102 moved from its normal position in an anterior direction (indicated with arrow 104) so that the lower jaw102 is now anteriorly relative the upper jaw100. You can use the advanced position of lower jaw 102 to tighten the soft tissues and maintain unobstructed airflow while sleeping.
An intraoral appliance is a device that the patient wears to move the lower jaw anteriorly relative the upper jaw in order to treat sleep apnea. An intraoral appliance is a removable appliance that can be placed into the patient’s jaw prior to sleep. This allows the patient to keep the lower jaw in a forward position while they are awake. Alternate embodiments of the intraoral appliance may include attachments or brackets attached to teeth or anchoring devices placed in the tissue within the intraoral cavity.
The intraoral appliance may take many forms. The intraoral appliance may include at least one shell with multiple cavities that can be used to accommodate the teeth of one jaw (e.g. the upper or lower jaws). You can make the appliance with any combination of metal, glass or reinforced fibers. You can make the appliance in many different ways, including thermoforming and direct fabrication. Alternately, or in combination with other methods, the appliance can also be manufactured with machining. For example, an appliance made from a block material with computer numeric controlled (CNC) machining. The appliances can also be manufactured using additive manufacturing processes like stereolithography and 3-D printing.
“In some cases, the intraoral appliance may include upper and/or lower shells or anchors that are designed to attach to the patient’s lower and upper jaws. The shells are removable and can be used to temporarily cover the patient’s teeth. However, one or both of the lower shells can be attached directly to the bones of the lower and upper jaws. This attachment is described in a co-pending U.S. patent application Ser. No. No. The complete disclosure is included herein by reference. Other cases, the upper or lower shells could be designed to distribute the displacement forces through patient’s teeth and minimize forces that may displace individual teeth relative the jaw. These structures are described in a co-pending U.S. patent Ser. No. No. The complete disclosure is included herein by reference. The upper and lower shells can be permanently or removably mounted and can have any configurations.
“Alternatively, or in combination with other devices, an intraoral appliance may include an upper appliance shell that fits the patient’s upper jaw, and a lower appliance shell that fits the patient?s lower jaw. The appliance may include an advancement device that connects the lower and upper shells in some cases. The advancement apparatus can be set up to move the lower shell anteriorly relative the upper shell. This will allow the patient to advance his mandible. The advancement apparatus can also be configured to limit the movements of the upper or lower jaws by up to six degrees of freedom. This will prevent the jaws returning to their normal position. You can modify the design of the advancement device described in this article to create the forces necessary for mandibular progress. An advancement apparatus may include protruding or recessing members, tension members (e.g. elastics, tension springs), and compression members (e.g. compression springs) as well as combinations of these elements. Components of an advancement apparatus may be located on either the upper or lower shell. An advancement apparatus’ components can be found on any part of the appliance. This includes the buccal, lingual, occlusal, and other surfaces.
“In some embodiments, an advance apparatus can be used for moving the lower jaw to multiple positions, e.g. along the anterior-posterior directions. The lower shell may be moved to and from a number of predetermined positions in order to activate the intraoral appliance. Alternately, the lower shell can be set to move continuously between a position with maximum mandibular advancement/protrusion and a position with minimal or neutral protrusion. The advancement apparatus may be used in various ways to move the lower jaw in an anterior-posterior, vertical, or lateral direction. The advancement apparatus can be used in some instances to move the lower jaw in a substantially anterior-posterior orientation. A plurality of positions may include discrete, continuous, or mixed positions. In some embodiments, the plurality is a finite number of positions that the lower jaw may assume. In other embodiments, the plurality is defined as a continuous range or positions that are bounded by one, more, or more lower boundaries. These include an anterior-posterior or vertical boundary and a lower border in the lateral direction.
The advancement apparatus can control the position of the lower jaw relative to the upper. The amount of mandibular advancement and vertical displacement between the upper and lower jaws can be adjusted according to a treatment plan. The best position for the lower jaw relative the lower jaw to treat sleep apnea depends on many factors. These factors include patient-specific factors like the patient’s anatomy and jaw opening trajectory. Also, how severe and frequent the symptoms are, as well as other factors. The machine learning algorithms described herein can optimize the lower jaw position of a patient based on any combination of these and other factors.
The mandibular advancement treatment can be controlled and advanced to different positions to suit the patient’s current sleep apnea status. The mandible can be moved in a selective manner when the patient has a sleep apnea episode. It can also be pulled back when the event is over. The lower jaw can be advanced only for the time and amount that is necessary to treat sleep apnea. This may help reduce or eliminate unwanted side effects of mandibular advance therapy such as tooth repositioning, muscle strain and jaw discomfort, TMJ discomfort, pain in the teeth, and bite alterations. As described in this article, machine learning algorithms can be used for optimizing the timing and extents of selective mandibular advance.
An advancement apparatus of a mandibular advance appliance can be controlled to control a variety of configurations to produce different amounts jaw displacement (e.g. anterior-posterior or vertical displacement). An advancement apparatus may include one or more advancement mechanisms that can be controlled to move the lower jaw to one of several positions. Protrusions and posts are some examples of advancement structures. The advancement structure’s action can include translating, sliding or rotating, shrinking, winding and expanding, twisting, folding, unfolding. Telescoping is also possible.
“The advancement apparatus may also include at least one actuator that actuates the advancement structures to move the lower jaw to one of several positions. An actuator could be a motor or any other mechanical device that can cause displacement of the mandible. The motor may be programmed to receive control signals from the processor. This will allow the motor to move the advancement structures in accordance with the control signal. Optionally, the motor may transmit signals to the processor indicating the current configuration and progress of the advancements structures, e.g. as feedback.
“Example: The oral appliances described herein may also include a motor or another actuator that is connected between the upper shell and lower shells. It is designed to respond to the processor’s signal to advance or retract a mandible. Motors can move the lower shell relative the upper shell continuously or incrementally over a range of distances, typically between 0.01mm and 20mm, but more commonly between 0.05mm and 8mm. Below are some examples of actuators and motors that can be used to move the mandible.
The motor can include any motor or effector that is self-contained and can be connected to the first or second shells. It will be activated or energized in order to move the lower shell relative the upper shell in response the received signal. The motor may include a rotor attached to one of the lower or upper shells and a follower attached to the other. A lever, or another rotating element that can engage a fixed follower can be included in the rotor to produce relative movement. Other embodiments may include a translator on one shell and a follower the other. A translator is an element that generally converts in the anterior and posterior directions in a plane coplanar with the patient’s jaws. Another alternative is to have the motor consist of a spindle mounted on one of the lower and upper shells, and a tether with one end mounted to be pulled in and out of the spinal and the other attached to one of the shells.
“Referring to FIGS. 2A-2C shows an exemplary intraoral appliance 10. It consists of an upper shell 12 as well as a lower shell 14. The upper and lower shells can be used to attach retainer-like, or aligner-like, devices to the upper and/or lower jaws of patients, as shown. The advancement apparatus that connects the upper and lower shells includes, in this example, a lower advancement mechanism coupled to the 14th shell, the lower advancement structure consisting of a rotor 16 connected to a pivot 19. Pivot 19 may include an actuator, or be coupled to one (not shown), which can rotate the rotor element 16 around the pivot axis. FIG. 2A shows that rotor element 16 can rotate clockwise so that there is sufficient clearance with the upper advancement structure 18, which is coupled to uppershell 12. FIG. 2A shows the patient with his upper and lower jaws free of movement and the lower shell 14 not protruding or advanced. FIG. 2B also shows this position. 2B. As shown in FIG. 2C. Rotor element 16 can be rotated counterclockwise in order to engage the upper advancement structure 18. Lower shell 14 will be displaced relative to upper Shell 12, displacing lower jaw of patient from the first position. You can configure the actuator that rotates rotor 16 to respond to a first control signal from one or more processors, as described below. You can reverse the advancement by rotating the rotor element 16 clockwise in response to another control signal from one or more processors. In FIGS. 2A-2C, the rotor 16 is located on the lower shell 14. 2A-2C in FIGS. 2A-2C. However, it is possible to position the rotor 18 on the upper shell 12 in other embodiments. Both the lower and upper shells may contain a rotor element which can rotate to engage with each other in order to produce mandibular advancement.
FIGS. 3A-3C. Intraoral appliance 20 consists of an upper shell 22, lower shell 24, an advancement apparatus coupling upper and lower shell 22, and an advancement device consisting, in this embodiment, of an upper advancement structure 26 that is coupled to upper shell 22 as well as a lower advancement mechanism 28 that is coupled to lower shell 24. This embodiment’s upper advancement structure 26 has a fixed component 26a and a mobile component 26b that can be moved from a retracted state (as shown in FIG. 3A, and in full-line in FIG. 3B) To an advanced position (shown as full line in FIG. 3A, and in full-line in FIG. 3C) by an actuator, not shown, in response to a initial control signal from one or more processors. The actuator can be coupled to or comprise the upper advancement structure 26 in this example. Lower advancement structure 28 engages lower component 26 b when it is in an advanced position. This displaces lower shell 24 relative upper shell 22. The lower jaw of the patient is then moved from the original position to the second. Retraction of the moveable component 26 can reverse this displacement in response to a second signal from one or more processors. In FIGS. 3A-3C, the movable part 26 b is located on the lower shell 24. 3A-3C. However, it is possible to position the movable part 26 b on the upper shell 22 in other embodiments. Optionally, the upper and lower shells may contain movable components that can interact to produce mandibular advancement.
FIGS. 4A-4B. Intraoral appliance 30 consists of an upper shell 32, and a lower shell 34. An advancement apparatus coupling upper and lower shells 32 and 34 is also included. This advancement apparatus comprises, in this embodiment, an actuator36, a fixed attachment points 40, and a tether elements 38. Upper shell 32 houses the actuator 36. It is connected to lower shell 34 by the tether element 38. In response to one or more processors’ control signals, actuator 36 can adjust the length 38 of the tether elements 38. This includes winding or unwinding 38. As an example, actuator 36 could respond to a control signal from one or more processors and increase the length of tether elements 38 so that upper shell 32, 34, and lower shell 34 remain in an unconstrained state. FIG. 4A. Actuator 36 can also react to another control signal from one or more processors. For example, lower shell 34 may be displace by tether element 38. FIG. 4B. As shown in FIG. 4B, lower shell 34 is displace relative to upper shell 32. 4B results in the lower jaw being moved from the original position to the second position. In FIGS. 2A-2C, the actuator 36 is located on the lower shell 34. 2A-2C in FIGS. 2, it is understood that the actuator 36 may be placed on the lower shell 34 in the embodiment of FIGS. Optionally, the upper and lower shells may include an actuator that winds and unwinds tether 38 to control displacement of the lower 34.
“Alternative embodiments of the systems and methods described in this disclosure can use other types of intraoral devices than motorized or actuator-based appliances.” An ordinary person skilled in the art will recognize that the various embodiments described herein can be applied to any type of appliance for treating sleep apnea.
“Sleep Apnea Monitoring & Treatment System”
The present disclosure also provides methods and systems for collecting and analysing health data, and making healthcare decisions, such as regarding the patient’s sleep patterns and sleep apnea. This is in order to provide selective and controllable mandibular advance. The controllable mandibular advance appliances described herein can be used in conjunction with a system to monitor and treat sleep apnea in patients. The system can monitor the patient’s sleep status and physiological characteristics in order to detect if a sleep disorder is developing. The system can monitor the patient’s physiological characteristics and/or sleep status to detect a possible sleep apnea event. It can then control the mandibular advance appliance to move the patient’s mouth, e.g. by a predetermined amount or until the symptoms are resolved. You can adjust the amount of mandibular advancement to achieve optimal sleep apnea treatment. You can keep the mandible in an advanced position for a set amount of time or until the sleep apnea event has been terminated. At that point, the appliance can be adjusted to return it to its normal position.
“Mandibles can be moved over various distances according to different embodiments. For example, from 0.01 mm up to 0.1mm, 0.1mm to 1.5 mm or 0.5mm to 1mm, 1 mm up to 5 mm and 10 mm respectively, as well as 10 mm upwards relative to the habitual location. Some embodiments allow the mandible to be moved over distances of 0.05 mm up to 5 mm, or 0.05mm to 8 mm anteriorly relative the habitual position.
“In some cases, sensors that are embedded in or external to the appliance may be programmed to continuously collect data during sleep to create a patient-specific profile, including information about patient status. Sleep sounds, temperature, heart rate and EKG can all be recorded. Sensors in the appliance, advancement apparatus, or any other mechanism can track the degree of mandibular advance. A processor that generates the advancement signals can also be used to determine the progress signal. Load sensors are built into the upper or lower shells to track the load on the jaws, arches, and sometimes individual teeth.
These data can be used to track the wearer’s movements and for other purposes. The data could be used to provide feedback. The data may be used to allow?feedback? The processor may apply control algorithms to optimize patient treatment. These algorithms include machine learning algorithms, described herein. The data can be analysed individually or collectively to determine the mandibular advancement and timing required for a patient at a given time. The control could be to activate the device as needed and then deactivate it when the apnea event is over. Other embodiments may control the activation of the device to a minimum level, and then adjust the device to reduce arch/tooth pressure and maintain sufficient mandibular advancement in order to stop the apnea. Alternately, data (especially the arch and tooth loads data) can be used to reduce the load on the teeth/arches while still allowing sufficient mandibular advancement for the treatment of snoring or apnea.
The collected data could also be used to generate alarms for patients and reports about patient treatment and status. The collected data could be used to detect irregularities in sleep patterns, and if necessary, take action (e.g., send an alarm for help). Data collected over time may be used to detect problems early, such as worsening breathing patterns or sleeping problems. Data can be reviewed by the healthcare professional or automatically assessed by the processor.
“In certain embodiments, the appliance can be activated prior to snoring if the system identifies patient parameters or data that indicate that snoring is about to start. The system can learn by collecting data over time from each patient. The system can learn patient-specific patterns of sleep and snoring by collecting data over time. The system can also learn from similar experiences to determine when the device should be deactivated.
Other features of the disclosed systems can detect pressure on the appliance. This allows the system to control or balance the pressure. The system can reduce the protrusion position of the appliance if the patient feels discomfort or if the appliance pressure is too high. The system can also control minor movements of the oral appliance, such as to reduce or eliminate pressure at one point of the temporomandibular (TMJ) joint.
The data can be used to create a patient-specific profile, which can be used for diagnosis, prescription preparation, and control and improvement of the intraoral appliance. The system can reduce or eliminate sleep problems by adjusting the load on the arches and minimizing the burden on them. When the system is in use, it can detect irregularities in sleep patterns and send an alert or alarm to other people. To identify problems early, patient-specific data can be collected. This includes information about the severity of breathing patterns, increased frequency or problems sleeping. These comparisons can be made with prior data from the same patient, or statistical data from a group of patients. A patient-specific profile is useful for providing personalized sleep apnea treatment.
“FIG. “FIG. The ‘processor 504 is also known as an?controller? Processor 504 can be referred to herein as a processor and/or a controller. Except where otherwise noted, the term?controller’ is used herein. As used herein,?controller? und?processor? are interchangeable. Both terms can be interchanged. Processor 504 may be a single processor, or a combination of multiple processors in different embodiments. System 500 may also include a memory device (not illustrated) that contains executable instructions. The processor 504 can then be configured to execute those instructions. As described below, sensors 502 can be used to monitor sleep apnea symptoms in patients. The instructions for processor 504 to receive sensor data and detect, identify and/or assess physiological events can be executed by the processor 504. As described in this article, processor 504 can execute instructions to transmit control signals for intraoral appliance 506. The processor 504 can execute any number of algorithms including machine learning algorithms.
“Systems disclosed in the present disclosure include one or more processors that are capable of receiving sensor data and using the sensor data to assess the symptoms of a patient, including those associated with sleep apnea. In some embodiments processor 504 may execute instructions to detect physiological events, such as the onset and termination of a sleep-apnea event. In some embodiments processor 504 may be able to execute instructions to detect physiological discrepancies, such as discrepancies between a current and previous sleeping pattern. Processor 504 may be able to execute instructions to perform physiological assessments, such as determining whether an apnea event is likely to occur or not. One or more microprocessors can be included in processor 504 and can receive data from sensors 502 regarding patient status. This can be done in either a wired or wireless configuration or a combination of both. The processor 504 can be combined with one or more sensors 502 in certain embodiments to form an integrated system. This could include a computer, digital workstation or computer housed within a single housing component.
“Systems disclosed in the present disclosure include one or more processors that transmit control signals to intraoral appliances. In some embodiments processor 504 can be programmed to execute instructions to detect, forecast, or assess a pre or post-apnea condition based on sensor data from sensors 502, and to transmit instructions to intraoral device 506 to cause intraoral appliances 506 to move the lower jaw of the patient to an advanced position or protruded position in order to treat sleep apnea and/or suppress snoring. As described further herein, actuator 508 can move the patient’s lower jaw in response to the control signal. The processor 504 can control the position of the intraoral device 506 or actuator 508 by placing it in the mouth. In some embodiments, the processor 504 can adjust the distance or the direction in which the appliance is in the patient’s mouth. The processor 504 can be set up to send a control signal to the intraoral appliance 506 or actuator 508 via wired, wireless, or combination thereof. Actuator 508 could be an embedded motor or mechanism that allows for mandibular movement, e.g. Advancement can be in an anterior-posterior, vertical, or combination thereof.
In some embodiments, the processor 504 can send an intraoral signal to actuator 508 and/or intraoral appliance 506 to cause the device to retract the lower jaw from its normal position. This is done based on sensor data 502. A first control signal can be sent to intraoral device 506 or actuator 508, causing intraoral appliances 506 to move from one position to another when an onset of sleep apnea is detected. Then, processor 504 may send a second control signal, triggering intraoral apparatus 506 to retract from the second to first position, when the end of a sleeping apnea is detected. Alternately, processor 504 could be set up to send control signals and actuator 508 to intraoral appliance 506. This will cause intraoral appliance 508 to retract the mandible partially or completely after a predetermined period. The predetermined time can range between 1 minute and 10 minutes. The predetermined time period may be as short as 1 minute, 2 minutes or 5 minutes, 10 mins, 15 minutes or 20 minutes, depending on the embodiment.
“The systems of the present disclosure allow for the collection of data over time on patient’s sleep apnea patterns and the use of such data to improve treatment. Some embodiments of processor 504 allow for the collection of sensor data from sensors 502, which includes patient data regarding sleep apnea patterns. The patient data can be saved on a memory device, downloaded, or uploaded to the patient’s doctor, other treatment management personnel to system management personnel, as well as to a database like a cloud database for future retrieval. Other processors, including processor 504, can access the patient data. They may use algorithms (including machine learning algorithms) or other artificial intelligence-based methods that will improve patient treatment protocols. Processor 504 may execute instructions to analyze patient data and improve methods or algorithms for detection and prediction of physiological events. In some embodiments processor 504 is able to evaluate patient data in order to improve accuracy of machine learning algorithms for predicting the onset or termination of apnea events. This can be done based on past symptoms and/or any other relevant data.
“Physiological Sensors & Data”
“Systems, methods and devices, as well as apparatus, of the present disclosure, can include one or more sensors that are adapted to monitor patient parameters such physiological data. The physiological data may be linked to the patient’s sleep patterns and sleep apnea episodes, normal physiological events, or abnormal physiological events. The sensors can monitor the physiological data of a patient in real time and transmit it as one or several signals that can be received by one (e.g., a suitable system for sleep apnea monitoring or treatment). Sensor data can indicate events or patient symptoms. For example, symptoms that are associated with the onset and/or decrease in sleep apnea events. The sensor data may be indicative of patient sleep patterns and/or physiological information during sleep in some embodiments.
“Sensors used in the systems disclosed (e.g. sensor(s) 502 or 500) may monitor any of a number of patient symptoms or status indicators. This includes sounds such as breathing, cessation or snoring and heartbeat. The sensors may be used to monitor breathing patterns. This includes changes in breathing rate, inhalation length, inhalation length, and length between breaths. Temperature, temperature changes and other symptoms can also be detected. You can also measure saliva and other data, even if they are not directly related to sleep disorder. The sensors described herein can monitor physiological information, including breathing sounds, snoring, breathing rate and respiratory airflow, chest expansion, oxygen levels, and cardiac data (e.g. heart rate, EKG data), sleep position, sleeping movements, blood sugar, and brain activity (e.g. EEG data) or variants and/or combinations thereof.
You can use any combination of sensors, including one, two or three, four, five or more types. Examples of sensor types that can be used in accordance with the embodiment include, but are not limited, audio sensors (e.g. microphones), video sensors. oxygen sensors (e.g. pulse oximeters), motion sensors. temperature sensors. strain gauges. force sensors. pressure sensors. heart rate monitors. blood pressure monitors. EKG sensors. EEG sensors. Any other type of sensor suitable for obtaining physiological data relating to the patient’s sleeping status and/or sleep disorder.
The sensors described in this article can be placed on the patient’s skin, inside or outside of their bodies (internally positioned), as well as on the patient’s surface. The sensors can be external to the patient in some embodiments. For example, they may include an external microphone that detects breathing sounds, an external camera to detect sleeping position, or an EKG machine to determine the heart rate. Some embodiments incorporate externally-positioned sensors as part of an external process, such as a processor mounted on a table and positioned next to the patient while they sleep.
“In some embodiments, monitoring can be performed by a sensor on or inside the patient, such a sensor mounted on an intraoral device worn by the patient. The sensors can be mounted on an intraoral appliance. They can communicate wirelessly with other components of the system such as processors or wired. The sensor may be mounted or placed in the upper or lower shells of intraoral appliances. Monitoring intraoral breathing sounds, respiration rate, sleep position and/or variations thereof can all be included in intraoral monitoring. You can integrate sensors that are internally positioned into your oral appliance in a variety of ways and in a variety of places, depending on the embodiments.
“The sensors described in this document can communicate with and transmit data to a processor through a wired connection (such as a USB link), a wireless link, such as Bluetooth, and/or variants thereof or combinations thereof.”
“Machine Learning Based Control of Mandibular Advancement
“Some embodiments include one or more processors (e.g. the processor 504 in the system 500). These processors can automatically collect and analyze any or all patient parameters that have been sensed via one or more sensors. These parameters can be tracked and monitored over time to identify changes. This may allow certain symptoms and parameters of patients to be linked with sleep apnea or snoring. These patient parameters can be used to predict when an apnea event will occur, and to initiate treatment with mandibular advancement. The processor may be configured to use a machine-learning algorithm to identify patient-specific correlations between physiological parameters, symptoms, and sleep apnea events. These patient-specific correlations are used to predict when a sleep disorder will occur. Some symptoms that could be associated with the onset of sleep apnea events include, but are not limited, changes to blood oxygen levels, heart rate, breathing rate, rhythm changes, changes, body temperature, electrical resistance changes (e.g. skin), increased sweating or decreased sweating. Machine learning algorithms, which are computer-based, can be used to identify combinations of physiological parameters or symptoms that may help detect the onset sleep apnea.
“FIG. “FIG. 6A shows a method 600 to detect and treat sleep apnea events, according to embodiments. As with all the methods described herein. The method 600 can be performed using any of the apparatus, devices and systems. One or more processors can perform one or more of the steps in the method 600 (e.g. processor 504 from the system 500) to monitor and treat a patient with sleep apnea.
“In step 602, one or more sensors sends a set of sensor data. As described in this article, the sensors can be set up to monitor the patient for signs and symptoms that may indicate sleep apnea. The sensors can transmit their respective sensor data to the controlling processor at predetermined intervals or continuously throughout the monitoring period. To ensure accurate monitoring of the patient?s sleep and/or sleep apnea, you can adjust the rate at which sensor data are provided.
“In step 604, the onset or response of a sleep disorder is detected using the sensor data. The sensor data may indicate physiological parameters or symptoms that could be associated with the onset sleep apnea events. The sensor data could indicate, for example, that a sleep apnea episode has occurred or is currently occurring. The sensor data may also indicate, in combination with other information, that a sleep-apnea event is imminent or likely to occur. Step 604 may be performed with a computer-implemented algorithm. This algorithm may or may not include a machine learning algorithm. For example, a machine learning algorithm can be used to determine physiological parameters and/or the symptoms that are represented by the set sensor data and/or whether these parameters and/or the symptoms indicate the onset or continuation of a sleep disorder. The machine learning algorithm output can be used to detect the onset or recurrence of sleep apnea events. It can also be used with other patient-specific criteria (e.g. patient-specific changes such as heart rate and breathing rate). These are just a few examples of machine learning algorithms that can be used with the methods disclosed.
“In step 606, an intraoral device is sent a control signal to move the lower jaw of the patient’s from a first to a second position in order to treat sleep apnea. Any of the mandibular advance appliances described herein can be used as an intraoral appliance. The current position of the patient?s jaw can be used as the first position. The first position may be the current position of the patient’s jaw. In other embodiments, it can also be a normal position, such as a position that the patient assumes during sleep. A second position could be one in which the jaw is advanced relative to the maxilla.
“In some embodiments the second jaw position can be a patient-specific position, which is tailored for each patient. Optionally, the second position of the jaw can be determined by a machine learning algorithm. The machine learning algorithm can be used, for example, to determine the optimal amount of mandibular advance that will treat the patient’s sleep disorder. This is e.g. in terms of effectiveness and mitigating side effects such as discomfort. Patient-specific factors, such as anatomy, physiology or tolerance for discomfort, can affect the optimal amount of advancement. The optimal amount of advancement may also vary depending on the circumstances of the sleep apnea episode, such as its severity. The machine learning algorithm can therefore be used to determine the optimal amount of advancement based on the physiological parameters and/or symptoms, patient-specific factors, the circumstances surrounding the sleep apnea episode, or combinations thereof. The machine learning algorithm may be trained using data from the patient’s previous sleep apnea episodes to establish patient-specific correlations between treatment efficacy and mandibular advancement.
“In some embodiments the step 606 is causing the intraoral device to move the lower jaw anteriorly, until the reduction or cessation or occurrence of sleep apnea symptoms are detected (e.g. via one or more sensors). The control signal may cause the appliance’s mandible to move in an incremental fashion until sensor data indicates that sleep apnea symptoms are reduced or stopped. It is possible for changes in sleep apnea symptoms, such as slow advancement, to be detected. This can be used to reduce the jaw displacement that is applied to treat sleep apnea. It may also be helpful in mitigating side effects like patient discomfort, muscle strain and TMJ dysfunction.
The length of time that the jaw remains in an advanced position can vary depending on the patient. It can take from a few seconds up to several hours. Some patients only need a few jaw movements to cause muscles in the upper airway and prevent snoring and sleep apnea. The processors described herein can be configured to retract the patient?s mandible back to its original position after the sleep apnea event subsides and/or after a predetermined interval. The processor can be programmed to keep the jaw in an elevated position for less that 75%, less then 50%, less over 40%, less about 30%, less under 20%, less below 10%, and less than 5% of total sleep time. The processor can also be set up to keep the jaw in an advanced position for a maximum of 5 hours, not more than 2 hours or more than 30 mins, and no longer than 20 minutes. It should also stop the processor from storing more than 10 minutes or more information at once. The processor may be able to analyze the sensor data and determine whether sleep apnea symptoms are decreasing or stopping (e.g. with the aid of a machine-learning algorithm), and then retract the patient’s jaw accordingly. This can be helpful in mitigating side effects like patient discomfort, muscle strain and TMJ dysfunction.
Alternative embodiments of the method 600 do not require the jaw to be advanced to a static position. Instead, the intraoral appliance can cause the mandible to move through a sequence of movements. Patients may have different preferences regarding the types of movements that they use to treat sleep apnea. The machine learning algorithms described in this article can be used to identify patient-specific movements for treating sleep apnea.
“FIG. “FIG. 6B shows a method 610 to terminate treatment for a sleep apnea episode, according to embodiments. One or more of the steps in the method 610 may be executed by processors within a system that monitors and treats a patient with sleep apnea (e.g. processor 504 in the system 500). The method 610 can be performed following the method 600 in some embodiments to allow automatic advancement or retraction of mandibles based on the patient’s status with sleep apnea.
“In step 612, one or more sensors provide a set of sensor information. Each sensor can either provide data at predetermined times or continuously, similar to step 602 in the method 600. You can adjust the rate at which data is sent to monitor patient’s sleep and/or sleep apnea.
“In step 614 the termination of sleep-apnea events is detected based or in response to the collection of sensor data. Sensor data may indicate physiological parameters or symptoms that can be associated with the end of a sleep apnea episode. The sensor data could indicate that the sleep disorder has ended or is about to end, for example, due to the appearance of less severe symptoms. The sensor data may also indicate, in combination with other information, that a sleep-apnea event is nearing or is likely to end. Step 614 may be performed with a computer-implemented algorithm. This algorithm may or may not include a machine learning algorithm. For example, a machine learning algorithm can be used to determine physiological parameters and/or the symptoms that are represented by the set sensor data and/or whether these parameters and/or the symptoms indicate the termination of a sleeping apnea episode. The machine learning algorithm output can be used to detect the end of a sleep-apnea episode. The machine learning algorithm could be the same as the one used in method 600 or a different algorithm.
“In step 616, an intraoral device is sent a control signal to move the lower jaw of the patient’s from the second to the first position. The first position may be the current or usual position of the patient’s lower jaw. The second position may be a mandible advanced jaw position. Some embodiments allow the patient to have their jaw moved to the second position prior to treating sleep apnea (e.g. according to the method 600). The step 616 retracts mandible back to the original position to end the mandibular advancement treatment.
“In addition to detecting the onset and/or end of sleep apnea events in real time, the processors can be set up to receive feedback about the efficacy of the mandibular enhancement treatment. The processor can, for example, receive feedback data from one or more sensors and then analyze it to determine if the patient’s symptoms and physiological parameters have improved. The processor can make adjustments to the mandible position if the current treatment is not effective. This can be done in real-time to allow for dynamic adjustments in order to improve the treatment of sleep apnea.
“FIG. “FIG. 6C shows a method 620 to improve the effectiveness of a sleep-apnea treatment. It is in accordance with embodiments. One or more of the steps in the method 620 may be performed by processors within a system that monitors and treats a patient with sleep apnea (e.g. processor 504 of system 500). Some embodiments of the method 620 are performed after the method 600 or before the method 610 to allow dynamic changes to the treatment plan.
“In step 622, one or more sensors provide a set data while the lower jaw remains in the second position (e.g. the advanced position). Sensor data can be provided at predetermined times or continuously. The rate at which the sensor data is delivered can also be adjusted to ensure that the patient has accurate monitoring of their sleep and/or sleep apnea.
“Based on the sensor data, step 624 determines the effectiveness of the second position for treating the sleep apnea episode. Sensor data may indicate physiological parameters or symptoms associated with sleep apnea events. It is possible to determine the effectiveness of the treatment by checking whether patient’s physiological parameters have improved or fallen back to normal, and whether symptoms are less severe or more severe. A treatment that is effective may be associated to normal physiological parameters, or the absence of/reduction in sleep apneasymptoms. An ineffective treatment could be associated with abnormal physiological conditions and/or the existence of sleep apnea signs. Step 624 may be performed by a computer-implemented algorithm. This algorithm may or may not include a machine learning algorithm. For example, a machine learning algorithm can be used to determine physiological parameters and/or the symptoms that are represented by the set sensor data and/or whether these parameters and/or the symptoms indicate an effective treatment. The machine learning algorithm could be the same as the one used in other methods, or it may be a completely different algorithm.
The determined effectiveness can be used to improve the machine learning algorithm. To improve the algorithm’s performance, input data can include the determined effectiveness, jaw position that is associated with it, and/or sensor data. This data could include information about the patient’s current physiological parameters, symptoms, and/or other relevant data. Feedback data can be used to improve the algorithm’s accuracy in determining the most effective treatment plan for the patient with sleep apnea.
“In step 626, the modified position of the lower jaw is determined to increase the effectiveness of treating the sleep disorder. A machine learning algorithm, or another computer-implemented algorithm, can be used to determine the best position for the mandible. A machine learning algorithm can also be used to determine whether there is a change in mandibular progress. The algorithm can also determine changes in jaw configurations, such as the amount of mouth opening. This is an option that could improve efficiency. The patient’s physiological parameters, symptoms, and circumstances, as well as combinations thereof, can determine the change. Some embodiments allow the machine learning algorithm to be trained using patient-specific data, such as previous sleep apnea event data, in order to identify patient-specific correlations between treatment effectiveness and jaw position.
“In step 628, an intraoral appliance is sent a control signal to move the lower jaw to the new position. The method 620 can then be repeated as many times as necessary to provide continuous feedback on treatment effectiveness and allow for the system to adjust the appliance to ensure that it is performing at its best.
The various data collected during the mandibular advance treatment can be stored (e.g. on one or more memory devices associated to the treatment system) for further processing and analysis. These data could include information about the patient’s past sleep patterns (e.g. duration and physiological parameters during sleep), prior sleep apnea (e.g. number, duration and/or severity sleep apnea episodes, symptoms during sleep events, physiological parameters during these events), and any previous mandibular advances treatments (e.g. amount and/or length of advancement, number and effectiveness of advancement in treating sleeping apnea). The data collected can also include data about patient preferences, such as patient preferences regarding pain, treatment effectiveness, satisfaction, and so forth. The processor could be programmed to determine if the mandibular advancement time and length is related to success in treating snoring and apnea. As data is collected over time, it may be possible to optimize treatment parameters and use them moving forward. This data collection and analysis may be done within the system (e.g. a microprocessor) or externally via communication over the internet or other suitable remote access methods. A system can also be used to contact a doctor periodically and/or automatically in order for him to give data or alerts about serious conditions.
“In some embodiments the data collected (e.g. previous sleep patterns, past sleep apnea events patterns, patient preferences) can be used to update machine learning algorithms. The stored data can be used as training data to update the machine learning algorithm. The update of the machine-learning algorithm may include updating the models, classifications, correlations or other data structures that are used by the algorithm to generate the predictions and determinations described. This allows the system to adapt to patient’s sleeping patterns and sleep apnea, and to improve the efficacy of the mandibular advance treatment regimen for treating sleep apnea. As the system is used more often, it can be made more customized for each patient.
“Optionally, patient-specific data can also be added to a sleep apnea database for multiple patients. This database can then be processed and analyzed in order to identify information that could be useful in improving sleep apnea understanding and designing effective treatments. These analysis results can be used for patient-specific treatments such as those based on the selective and permanent mandibular advancement methods, methods, or devices described herein.
Other features that may be optionally provided by the system include activating other functions or devices which could contribute to cessation or cessation of snoring or apnea, and providing alerts locally or remotely under certain circumstances. The processor may be programmed to execute instructions to detect physiological discrepancies in patients, such as those identified by sensor data. These discrepancies may include discrepancies between the patient’s normal or expected physiological parameters and the patient’s current physiological parameters. The discrepancy could be between the expected or normal sleeping patterns of the patient and the current sleeping patterns of the patient in some embodiments. The processor can use a machine-learning algorithm in various embodiments to detect discrepancies. This could be done by comparing historical or predicted data with patient’s current state. The processor can create an alert if a discrepancy in data is detected. This could be on a user device, such as a digital processing gadget. To inform the patient or their care provider of potential medical issues, the alert can be sent to them. If the discrepancy is indicative that there is a medical emergency, you can take immediate action. The alert can be used to call the emergency department, wake the patient and/or contact their care provider.
The systems described herein can implement many different types of machine-learning algorithms to provide patient-specific monitoring and treatment. The machine learning algorithms described in this document can include supervised learning methods such as classification and regression. The machine learning algorithms described in this document can also include unsupervised learning methods such as clustering. These examples of machine learning are not intended to be exhaustive. Other methods and approaches are available to those skilled in the art to generate and apply predictive models, make physiological assessments, and are included within the scope and capabilities of the systems, methods devices, and apparatus described herein.
“Machine Learning Algorithms” can include reinforcement learning algorithms and representation learning algorithm, similarity learning algorithm, similarity learning algorithm, recommendation systems, metric learning methods, metric learning programs, recommendation systems and sparse dictionary learning algoritms, genetic algorithms, genetic algorithms, inductive programming and/or variations thereof, or combinations thereof.
“Machine Learning Algorithms” can include supervised learning methods such as regression, classification, regression methods and/or variations thereof.
“Machine-learning algorithms described herein may include decision tree learning. This can be used to map observations regarding physiological data from patients in order to make predictions. Regression tree learning and classification tree learning are two examples of decision tree learning.
“Machine learning algorithms described in this article can include association rule learning. This can be used to determine relationships between variables obtained via physiological data to make predictions. Associative rule learning may include, but not be limited to: a priori algorithms; equivalence-class transformation algorithms; frequent pattern growth algorithms; context-based association rule mining algorithms; node set based algorithms; general unary hypothesis automata, including ASSOC procedures, OPUS and/or variants thereof or combinations thereof.
Click here to view the patent on Google Patents.How to Search for Patents
A patent search is the first step to getting your patent. You can do a google patent search or do a USPTO search. Patent-pending is the term for the product that has been covered by the patent application. You can search the public pair to find the patent application. After the patent office approves your application, you will be able to do a patent number look to locate the patent issued. Your product is now patentable. You can also use the USPTO search engine. See below for details. You can get help from a patent lawyer. Patents in the United States are granted by the US trademark and patent office or the United States Patent and Trademark office. This office also reviews trademark applications.
Are you interested in similar patents? These are the steps to follow:
1. Brainstorm terms to describe your invention, based on its purpose, composition, or use.
Write down a brief, but precise description of the invention. Don’t use generic terms such as “device”, “process,” or “system”. Consider synonyms for the terms you chose initially. Next, take note of important technical terms as well as keywords.
Use the questions below to help you identify keywords or concepts.
- What is the purpose of the invention Is it a utilitarian device or an ornamental design?
- Is invention a way to create something or perform a function? Is it a product?
- What is the composition and function of the invention? What is the physical composition of the invention?
- What’s the purpose of the invention
- What are the technical terms and keywords used to describe an invention’s nature? A technical dictionary can help you locate the right terms.
2. These terms will allow you to search for relevant Cooperative Patent Classifications at Classification Search Tool. If you are unable to find the right classification for your invention, scan through the classification’s class Schemas (class schedules) and try again. If you don’t get any results from the Classification Text Search, you might consider substituting your words to describe your invention with synonyms.
3. Check the CPC Classification Definition for confirmation of the CPC classification you found. If the selected classification title has a blue box with a “D” at its left, the hyperlink will take you to a CPC classification description. CPC classification definitions will help you determine the applicable classification’s scope so that you can choose the most relevant. These definitions may also include search tips or other suggestions that could be helpful for further research.
4. The Patents Full-Text Database and the Image Database allow you to retrieve patent documents that include the CPC classification. By focusing on the abstracts and representative drawings, you can narrow down your search for the most relevant patent publications.
5. This selection of patent publications is the best to look at for any similarities to your invention. Pay attention to the claims and specification. Refer to the applicant and patent examiner for additional patents.
6. You can retrieve published patent applications that match the CPC classification you chose in Step 3. You can also use the same search strategy that you used in Step 4 to narrow your search results to only the most relevant patent applications by reviewing the abstracts and representative drawings for each page. Next, examine all published patent applications carefully, paying special attention to the claims, and other drawings.
7. You can search for additional US patent publications by keyword searching in AppFT or PatFT databases, as well as classification searching of patents not from the United States per below. Also, you can use web search engines to search non-patent literature disclosures about inventions. Here are some examples:
- Add keywords to your search. Keyword searches may turn up documents that are not well-categorized or have missed classifications during Step 2. For example, US patent examiners often supplement their classification searches with keyword searches. Think about the use of technical engineering terminology rather than everyday words.
- Search for foreign patents using the CPC classification. Then, re-run the search using international patent office search engines such as Espacenet, the European Patent Office’s worldwide patent publication database of over 130 million patent publications. Other national databases include:
- European Patent Office (EPO) provides esp@cenet to access a network of Europe’s patent databases with access to machine translation of European patents.
- Japan Patent Office (JPO) – with access to machine translations of Japanese patents.
- World Intellectual Property Organization (WIPO) offers PATENTSCOPE with a full-text search of published international patent applications and machine translations for some documents, as well as a list of international patent databases.
- Korean Intellectual Property Rights Information Service (KIPRIS)
- State Intellectual Property Office (SIPO) with machine translation of Chinese patents.
- Other International Intellectual Property Offices with online patent databases include Australia, Canada, Denmark, Finland, France, Germany, Great Britain, India, Israel, Netherlands, Norway, Sweden, Switzerland, and Taiwan.
- Search non-patent literature. Inventions can be made public in many non-patent publications. It is recommended that you search journals, books, websites, technical catalogs, conference proceedings, and other print and electronic publications.
To review your search, you can hire a registered patent attorney to assist. A preliminary search will help one better prepare to talk about their invention and other related inventions with a professional patent attorney. In addition, the attorney will not spend too much time or money on patenting basics.
Download patent guide file – Click here