Patent for “Wearable electronic device for tracking location and identifying changes to salient indicators of patient’s health”

Artificial Intelligence – Adam G. Sobol, Joseph T. Kreidler, Brian A. Donlin, Jon G. LEDWITH, Patrick J. McVey, Ross D. Moore, Peter Nanni, Dwayne D. Forsyth, Paul Sheldon, Todd Sobol, John D. Reed, Careband Inc

Search Patent for “Wearable electronic device for tracking location and identifying changes to salient indicators of patient’s health”

Abstract for “Wearable electronic device for tracking location and identifying changes to salient indicators of patient’s health”

“A wearable electronic gadget, a system and methods for monitoring with a wornable electronic device. The device contains a hybrid wireless communication module that can selectively acquire location data from both outdoor and indoor sources. It also includes a wireless communication submodule that can transmit an LPWAN signal to provide information about the location based on the data. One or more sensors may be included to collect environmental, activity and physiological data. Some or all of the acquired data may be transmitted to a larger system. This could include a cloud-based server. The data can also provide location-based information. The predictive health care protocol is based on a machine-learning model in one form.

Background for “Wearable electronic device for tracking location and identifying changes to salient indicators of patient’s health”

“Dementia-such as Alzheimer’s Disease, Parkinson’s Disease and related neurodegenerative conditions-corresponds to a decline in mental ability severe enough to interfere with one’s daily life, including the activities of daily living (ADL). In the United States alone, more than five million suffer from dementia. This number is expected to rise.

Care for dementia sufferers can be difficult because they might become lost or confused and wander off-road. These individuals can be injured if they are not found in a timely fashion. This problem is compounded by the fact that many dementia sufferers will not be able to recall their name, address, or any other identifying information even if they wander into someone seeking to help them.

“The other problem with caring for dementia patients is their declining mental and physical health. This includes elderly people as well as those who have just begun to develop the disease. Individuals with dementia could be at risk for infections, pneumonia, neuropsychiatric symptoms, and other comorbidities.

“Additionally, the declines might not appear until the underlying comorbidity has advanced. The person with the condition may not be capable of articulating symptoms that, if detected early enough, could lead to appropriate medical intervention. A urinary tract infection (UTI) is one of the most common infections that affects seniors and people with dementia. It is not easy to find information about the presence of a UTI in these patients. This is because it is expensive, time-consuming, and costly. A caregiver must monitor the patient’s activities to determine if a UTI may be imminent.

“Caring for someone with mental or physical disabilities can be difficult. If the individual is still at home, it’s possible for extended periods of time before symptoms are brought to the caregiver’s attention. It is also difficult to care for people who are experiencing or are showing early signs of physical or mental frailties in group settings like nursing homes, assisted living communities, or similar long-term care centers. This is due at least in part, in part, to the low number of caregivers relative to the number patients in these facilities.

The devices, systems, and methods described in the disclosure use a wireless, wearable application to improve the ability to locate and track the environment, activity, and physiological information of someone who is suffering from or is experiencing symptoms related to dementia, infections, neuropsychiatric issues, or other adverse health conditions. This data can be used to provide data-informed care insight for loved ones, nurses, doctors, and other caregivers. These devices, systems, and methods can be used to replace conventional data acquisition components. This addresses a problem that is especially acute in traditional data-acquiring device architectures, which require large amounts of electrical energy to receive, process, and transmit data. This is at least partially due to the seemingly incompatible goals to achieve long battery life and extended transmission distance. Devices capable of sending large amounts of data (such a cellular-based one) consume large amounts, while devices that can transmit large amounts of data (such a conventional Bluetooth or WiFi-based approach) have shorter detection and transmission ranges, making them ineligible for tracking the location of a user of the device, either indoors or outdoors. The present disclosure addresses the shortcomings of conventional computerized data acquisition methods by implementing the data acquisition, computer structure, and communication configuration as specified.

A first aspect of the disclosure describes a wearable electronic device that includes a platform for attaching to a person and a source and hybrid wireless communication module supporting the platform. The platform can also receive electric power from the source. The hybrid wireless communication module comprises a number of sub-modules. A first sub-module is used to selectively transmit location data using a beacon signal. A second sub-module is used to receive location information in the form a global navigation system (GNSS), signal, and a third submodule to transmit a low power wide area network signal (LPWAN). This signal provides location indicia for the wearable device based on location data acquired from at least one of two wireless communication submodules. In the current context, location data transmission and receipt are considered selective if an incoming signal (in case of received data) is detected by the wearable electronics device or if an outgoing LPWAN (in case of transmitted data) is detected by a remote receiver or gateway. Although hybrid wireless communication systems may involve continuous or periodic sending and receiving of data, the recipients or sources of the data might be out of reach. Therefore, the receipt and transmission of location data must?outside of necessity?be considered selective. One form of beacon signals that provide location data to the wearable electronic device are those from near-range private-network infrastructure. These signals do not require cellular, or other public-network features to transmit and receive wireless signals. For indoor operation, a Bluetooth Low Energy network (also known as Bluetooth low-energy technology) is used. Additionally, signals that provide location data to the first wireless communications sub-module could include signals from GNSS to meet outdoor and long-range location requirements.

“In one form, the embodiment of the first aspect can include many sensors, a nontransitory computer-readable medium, and a processor that is configured for performing a predefined set operations in response to receiving an instruction from a predefined Native Instruction Set. A set of machine codes from the Native Instruction Set are also selected and used by the processor to transmit LEAP data.

“In one form, the embodiment of the first aspect can include one or more previous forms. In which case, another machine code determines the distance between the wearable electronics device and the source of the beacon signal,

“In one form, an embodiment may include one or more previous forms. In which the machine code that transmits at most a portion the LEAP data through a third wireless communication module is used to transmit such data through the third wireless communication submodule, while the data remains substantially unchanged.

“In one form, an embodiment may include one or more previous forms. In which the machine code that transmits at most a portion the received LEAP data via the third wireless communications sub-module is used for such data transmission through the third wireless communication module while the data are in substantially processed form.”

“In one form, an embodiment may include one or more previous forms. In which the machine code that transmits at most a portion the received LEAP data via the third wireless communications sub-module is used for such data transmission through the third wireless communications sub-module, while the data is still in partially processed form.

“In one embodiment, the first aspect of the invention may include any of the preceding forms. At least one sensor that is configured to detect physiological information includes a heart rate sensor or breathing rate sensor, temperature sensor, pulse oximetry sensor and respiration sensor. A systematic pressure sensor. A systematic systolic pressure sensor. A systematic diastolic pressure sensor. A systematic mean arterial sensor. A central venous pressure sensors. A pulmonary pressure sensor.

“In one form, the embodiment of the first aspect can include one or more previous forms in which at minimum one of the sensors configured to detect activity data includes at least one sensor from the group consisting: an accelerometer; a gyroscope; a magnetometer; an altimeter and an inertial measuring unit.

“In one embodiment, the first aspect of the invention may include one or more previous forms. At least one sensor that is configured to detect environmental data includes at minimum one sensor from the following group: an ambient temperature sensor; an ambient pressure sensor; an ambient humidity sensor; an ambient light sensor; a motion sensor; a carbon monoxide detector; a carbon dioxide sensor; a smoke detector.

“In one embodiment, the first aspect of the invention may include any of the above forms. Further, the platform can support a nurse button and signally cooperate with the third wireless communications sub-module so that, upon activation, at least one signal is transmitted by the wearable electronic device to the third wireless communication module.”

“In one embodiment, the first aspect of the invention may include one or more previous forms. In which case, another machine code keeps the second wireless communication submodule in sleep mode until detection either of a waking event, or for a predetermined time, the second wireless communication submodule is maintained in the sleep mode.”

“In one embodiment, the first aspect of the invention may include one or more previous forms. In this case, the waking event includes detecting the wearable electronic device outside the range of detection for the first wireless communication module.

“In one form, an embodiment may include one or more previous forms. In which case, another machine code controls data transmission from at least two forms of received wearable electronic devices LEAP data through the third wireless communications sub-module,

“In one embodiment, an embodiment may include one or more previous forms. In which case, the hybrid wireless communication module doesn’t include a cell wireless communication sub-module.

“In one form, the embodiment of the first aspect can include one or more previous forms. The platform may be selected from the group consisting: a wrist-worn bracelet, an ankle-worn bracelet, an article or clothing (such as outerwear or underwear), a necklace, pendant, a clothing attachable pin, clothing-affixable patch, or a subcutaneous implants.

“In one embodiment, the first aspect of the invention may include any of the preceding forms. In this case, the first wireless communication submodule selectively receives location information in the form a BLE signal.

“A second aspect of the disclosure discloses a system that tracks the location of an individual. The system comprises a wearable electronic device, which includes a platform and one or more batteries, solar cells, capacitive devices or other sources of electric current. It also includes a hybrid wireless communication module that is composed of at least the first, second, and third wireless communication modules. A gateway for wireless signal communication is included in the system with the third wireless communication module. The platform can be worn or secured to an individual. However, the hybrid wireless communication module can receive electric power from the platform. The first wireless communication module receives location data as a beacon signal. The second wireless communication module receives location information in the form a GNSS signal. The third wireless communication module transmits an LPWAN signal which provides location indicia for the wearable electronic device based upon acquired location data from at most one of the wireless communication modules.

“In one embodiment, the second aspect could include the gateway and wearable electronic devices cooperating as part of a topology network that is star-rather than mesh.”

“In one form, the embodiment of the second aspect could include one or more previous forms and may also include a backhaul service in signal communication with gateway.”

“In one form, the embodiment of the second aspect can include one or more previous forms and may be configured so that the wearable electronic device or backhaul server includes a non-transitory medium, a processor, and a set machine codes chosen from a native instruction list and operated on by the processor. A minimum of a portion of the machine codes is stored on the non-transitory computer reader medium or mediums. Data structures correspond to different nodes in a machine learning model. For example, the input, intermediate, and output nodes in a neural network, or the input and output nodes in a K-means Clustering approach. One form of such data structures may be stored in the memory of the relevant computer readable medium. These data structures can be used by machine codes that correspond to the processor of the wearable electronic device or backhaul server processor.

“In one form, an embodiment may include one or more forms of the second aspect, and may also include at least one beacon for communication with the first wireless communication module.”

“A third aspect of the disclosure discloses a system that analyzes the health status of an individual. The system comprises a wearable electronic device that is designed to be worn on the body or secured to the person. It also includes a source and hybrid wireless communication module supported by the platform, and receiving electric power from a battery. The hybrid wireless communication system comprises a first wireless communication module that selectively receives position data in the form a beacon signal. A second wireless communication module that operates during its operation selectively receives location information in the form a GNSS signals. Finally, a third wireless communication module that transmits an LPWAN signal that provides location information for the wearable electronic device based upon acquired location data from at most one of the second and first wireless communication modules. The platform supports multiple sensors so that each sensor can detect a specific one of the following: environmental data, activity data, and physiological data. The system also includes a gateway, and a backhaul host. The gateway communicates wirelessly with the third wireless communication module, and the backhaul service is in signal communication. The backhaul server and the wearable electronic devices have at minimum a non-transitory computing medium, processor, and set of machine code selected from the native instruction sets. Each processor is capable of operating on the machine codes stored in the non-transitory computers readable mediums. The machine code that executes a machine learning model to classify an individual’s health condition based at minimum in part on the LEAP data is available for at least one backhaul server.

One embodiment of the third aspect could include having the machine-learning model be a neural model that has many input nodes, each of which contains a memory place for storing an input value that corresponds with a portion one of the acquired LEAP information, many hidden nodes that are connected to at most one of the plurality input nodes, and includes computational instructions that are implemented in machine codes by the respective processor for computing a plurality output values and many output nodes that each contain a location for storing output value from the machine learning class model

“In one form, the embodiment of third aspect may include one of these forms. At least a part of the set machine codes that is on at least one non-transitory medium of wearable electronic devices and the non?transitory medium of backhaul servers and that are operated on by the respective processor also includes a machine code that compares at most a portion the LEAP data with baseline data, which forms a data structure that is stored either on the non?transitory medium of wearable electronic devices or the backhaul computer readable

“In one form, the embodiment of the third aspect can include one or more previous forms. In which case, the baseline data are selected from the group consisting baseline data of an individual and baseline data representing a demographic group.

“In one embodiment, a third aspect may include one of the above forms. At least one portion of the set machine codes that is on the wearable electronic device or the backhaul computer readable media of the backhaul host and that are operated by the processor further comprises a code that provides clinical decision support using the machine learning classification model.”

“In one form, an embodiment may include one or more forms of the third aspect, further including a code to provide diagnosis through the machine learning classified model.”

“In one form, the embodiment of the third aspect could include one or more previous forms, as well as a machine code that executes an ADL analysis on the individual using at most a portion of the LEAP data.

“A third embodiment may contain one or more of these forms. It may also include a machine code that sends an alert through the third wireless communications sub-module if the transmitted location data indicates an individual is outside of a predetermined area.

“One form of the third aspect could include any of the above forms. The machine code used to train the machine-learning classification model may also include a code to clean at least some of the LEAP data and (b) a code to extract at most one feature from the cleansed data. c) A machine code that executes at least one of the algorithm based upon the one or multiple feature vectors. A machine code that executes at least one algorithm using the at minimum one feature vector so that the machine learning class model can provide a caregiver with a predictive analysis of the patient’s.

“In one form, the embodiment of the third aspect can include one or more previous forms. At least a part of the machine code to train a machine learning model includes a code to segment at minimum a portion from at least one LEAP data set into a training, validation, and testing data set. Also, the machine code that refines a machine learning model based upon the execution of at least one algorithm on each of the training, validation, and testing data sets.

“A third embodiment may include any of the above forms. It is possible for the machine code to train the machine-learning classification model to cooperate with it through (a) a code that analyses at least a portion at least of the location data or activity data after the machine learning model has been trained using at least one algorithm and (b) a code that causes at most one of the wearable electronics device and the backhaul host to output the analyzed information (such as to memory, an audio alert, or another use by a display or an audio alert, or other caregiver).

“Accordingly to a fourth aspect, the present disclosure discloses a method for monitoring an individual using a wearable electronics device. This method involves acquiring location data using the wearable device and wirelessly transmitting it to a wireless LPWAN receiver using a Star topology network.

“In one form, the embodiment of the fourth aspect could include acquiring, using many sensors that are part of the wearable electronics device, at minimum one of the following data: activity data, environmental data, and physiological data, then wirelessly transmitting these data from the wearable electric device to the wireless LPWAN reader.”

“In one form, an embodiment incorporating the fourth aspect can include one or more previous forms. In this case, wireless transmission of the LEAP data takes place using a hybrid wireless communications module that forms part of the wireless electronic devices.

“In one form, the embodiment of the fourth aspect can include one or more previous forms. Further, it may also include determining the health condition of an individual using a machine-learning model and providing an output. The machine learning model is at least partially based on at least some of the LEAP data.

“In one embodiment, the fourth aspect of the invention may include any of the preceding forms. The determining includes operating at minimum a non-transitory medium, a processor, and a set machine codes chosen from a native instruction list such that at most a portion are stored in the nontransitory medium. A machine code is used to cleanse at least some of the LEAP data. It also includes a code that extracts at most one feature vector from the cleansed data. The machine code then trains at minimum one machine learning algorithm using one or more feature vectors.

“In one form, the embodiment of fourth aspect may include one, or more, of the preceding forms. A machine code to train the machine-learning classification model includes a code to segment at most a portion (or all) of the LEAP datasets into a training set for the at minimum one machine-learning algorithm, a code to validate the data set by using the at the least one machine, a code that segments at best a portion (or all) of the LEAP datasets, and a code that refines the data sets by running the at the at the at the testing, validation, testing, training, validation, testing data sets.

“In one form, the embodiment of the fourth aspect can include one or more previous forms where the machine learning model of the machine is executed on at minimum one of the wearable electronic devices, backhaul servers, and the cloud.”

“In one form, the embodiment of the fourth aspect can include one or more previous forms. The health condition may be an adverse health condition chosen from the group consisting a neuropsychiatric disorder and an infection.

“In one embodiment, a fourth aspect may include one of the previously described forms. In this case, the infection includes a UTI. The set of machine codes on the non-transitory medium of wearable electronic device or the backhaul computer readable media of the backhaul host that is operated on by the respective processor also includes a machine that executes at most a portion a McGeer Criteria analysis that is based at least on a portion the LEAP data.

“In one form, the embodiment of the fourth aspect can include one or more previous forms. In this case, the machine code that executes at most a portion a McGeer Criteria analysis determines at minimum one of (a), new or significant increase in urgency to urination, (b), new or notable increase in frequency to urination, (c) new/marked increase in incontinence, and (d) change of functional status, based at the least in part on at the least a portion the LEAP data.”

“In one embodiment, a fourth aspect may include one or multiple of the preceding forms. The pneumonia is defined as a combination of at least one portion of the machine codes on the wearable electronic device and on the backhaul server’s non-transitory medium. Each processor also includes a machine program that performs a pneumonia analysis using at least some of the LEAP data.

“In one embodiment, the fourth aspect of the fourth aspect may contain one or more previous forms. The machine code to execute at most a portion a pneumonia analysis consists of machine code to execute at minimum one of a PSI score. CURB-65 score. SMART-COP score. An A-DROP score is based on at the least one location data. and activity data. This data is combined with physiological data which includes at least one respiratory data. These acronyms will be described in greater detail in this disclosure. The pneumonia analysis may also include one or more of the following factors.

“In one embodiment, a fourth aspect may include one or multiple of the preceding forms. In this case, the infection includes influenza and at least a part of the set machine codes that is on at minimum one of non-transitory computers readable media of the wearable electronic devices and the nontransitory computers readable mediums of backhaul servers and that are operated on by the respective processor further comprises the machine code to execute an analysis of influenza based at least on a portion at least one among the location data.

“In one embodiment, a fourth aspect may include one, or more, of the preceding forms. In this case, the machine code to execute at most a portion an influenza analysis includes machine code that executes at least a portion an influenza score based at least on one of the location and activity data together with the physiological data which comprises at minimum one of temperature, respiratory, and heat rate data.

“In one embodiment, a fourth aspect may include one of these forms. In this embodiment, the neuropsychiatric state includes agitation, such that at minimum a portion the set of machine code that is on at most one of non-transitory computers readable media of the wearable electronic devices and the nontransitory computers readable mediums of backhaul servers and that are operated on by the respective processor further comprises the machine code to execute an analysis of agitation based at least on at the least one of activity data, location data, physiological data, and environmental data.

“In one embodiment, the fourth aspect of the fourth aspect can include one or more previous forms. In this case, the machine code to execute an analysis of agitation includes machine code to determine if the individual is pacing.”

“In one embodiment, a fourth aspect may include one or multiple of the preceding forms. In this case, the neuropsychiatric disorder includes cognitive impairment. A machine code that executes a cognitive impairment analysis using at least a portion at least of the location, activity, and physiological data is included in the set of machine codes.

“In one embodiment, a fourth aspect of the fourth aspect can include one or more previous forms. In this case, the machine code to execute at most a portion of a cognitive impairment analysis includes machine code to determine at minimum one stage of dementia from the group consisting at least one (a) early stage dementia (b) moderate dementia (c) late dementia (d) terminal dementia.”

In one form, the embodiment of the fourth aspect can include any of the preceding forms. Indicia for the early stage dementia are selected from the following groups: indicia for the middle stage dementia are selected from those who have difficulty with fluids, pressure ulcers, and unawareness of external stimuli.

“In one form, the embodiment of the fourth aspect could include one or more previous forms. In which case, the neuropsychiatric condition can be analyzed using a regression-based machinelearning model.”

“Accordingly to a fifth aspect, the present disclosure discloses a method for using a machine-learning model to assess a person’s health condition. The method involves acquiring location data using one or both of GNSS and BLE data. It also includes acquiring with a plurality sensors, at least one of activity data, environmental data, and physiological data. Wirelessly transmitting at most a part of the LEAP data to a wireless low-power wide area network receiver using star topology networks is also included in the method. Also, the machine learning model is executed based at minimum in part on the LEAP data. Execution takes place using a nontransitory computer-readable medium, a processor, and a set machine codes from a predefined native instructions set. The processor executes a predetermined set of operations upon receiving a corresponding instruction from the set. This includes a machine that analyses at least one portion of the LEAP data after the machine learning model has been trained using at least one algorithm and a machine that causes the analyzed data be output to a caregiver.

“In one form, the fifth aspect of an embodiment may include one or more previous forms. The machine learning model is trained using at least 1 machine learning algorithm. This includes a machine that cleans at minimum a portion of the LEAP data, a code that extracts at most one feature vector from cleansed data, and a code that executes at the least 1 machine learning algorithm using at least the one feature vector.

“In one form, the fifth aspect of an embodiment may include one or more previous forms. In this case, the machine learning model includes an unsupervised approach that incorporates K-means clustering.

“In one form, the fifth aspect of an embodiment may include one or more previous forms. In this case, the machine learning model includes an unsupervised approach that contains a neural network.

“In one form, the fifth aspect of an embodiment may include one or more previous forms. In this case, the machine learning model includes a hybrid approach, which includes a supervised approach and an unsupervised approach.

“A fifth embodiment may be described in one form. The supervised approach includes a neural network, while the unsupervised approach involves K-means clustering.

“A sixth aspect of the present disclosure discloses a method for performing cognitive assessments of an individual. The method involves receiving data from a plurality sensors on a wearable electronics device that is secured to an individual, such data being converted into a labeled vector that describes at most one attribute of data, comparing that labeled feature matrix to baseline data using machine learning models, determining the cognitive status of the individual, and then communicating that information to a caregiver.

“In one form, the sixth aspect could include an ADL analysis that uses at most a portion the LEAP data as input.

“A non-transitory computer-readable medium is disclosed in accordance with a seventh aspect. Executable instructions are contained on the medium that, when executed by a machine, cause it to receive location information from at least one of a GNSS signal and a beacon signal through a hybrid radio communication module that forms at most a part of a wearable device and then transmit that location data through the wireless communication unit.

“In one form, the embodiment of the seventh element may also include the ability to cause the machine to sense activity, environmental, and physiological data from at minimum one sensor that forms at most a part the wearable electronic devices.”

“In one embodiment, an embodiment of a seventh aspect may include one of the preceding forms. The executable instructions further cause the machine to use at most a portion the LEAP data to determine if an individual wearing the wearable electronic device has a higher risk of developing an adverse medical condition.”

“In one embodiment, the seventh aspect of the invention may include one or more previous forms. The executable instructions further cause the execution of a machine-learning model that is (a) trained using at minimum one training algorithm and (b) analyzes at most a portion the LEAP dataset once the machine learning classification algorithm has been trained. This machine learning algorithm will output warnings of increased risk of developing an adverse condition.

“In one form, the embodiment of the seventh element may include one or more previous forms. The indicia that there is an increased risk of developing an adverse condition due to an increased risk of developing it is based at minimum in part on a comparison between at least a portion the LEAP data and baseline data.”

“Accordingly to the eighth aspect of this disclosure, a wearable electronic system for tracking a patient’s health is disclosed. The device comprises a processor, a battery, a power source, a first wireless communication module with a BLE chips communicatively connecting to the CPU and configured for receiving BLE location information. A second wireless communication module with a GNSSchip communicatively connecting to the process and configured to receive GNSS position information. Finally, a third wireless communication component with an LPWAN chip is connected to it. Based on the location information from at most one of the wireless communication submodules, the third wireless communication module provides location indica for the device.

“Accordingly to another aspect, the present disclosure discloses a computerized process for using a wearable device that includes determining if a patient is at high risk of developing an UTI. Another aspect of the disclosure discloses a computerized method to determine if a patient is at high risk for developing an adverse health condition using an ADL determination. Another aspect of the disclosure discloses a computerized method for determining if a patient is showing increased agitation. Another aspect of the disclosure is that wireless transmission of data from the wearable electronic devices to a wireless LPWAN receiver (such the gateway) via the star topology network (rather than mesh), may be possible. Another aspect of the disclosure states that a radio signal strength indicator (RSSI-based transmission protocol between one or more beacons and the wearable electronic devices may be replaced by a different direction-finding protocol, such as those based upon angle of arrival (AOA), or angle of departure (AOD), to provide real-time location functionality. Another aspect of the disclosure states that machine learning models, such as neural networks, Kmeans clustering, or similar approaches, may be used to analyze LEAP data collected by the wearable electronics device. You will see that there are many other aspects, as well as their respective uses of components and configurations. Other aspects will also be evident from the entirety of the disclosure.

“BRIEF DESCRIPTION ABOUT THE VIEWS FROM THE DRAWINGS”

“The following description of specific embodiments can be best understood when viewed in conjunction with these drawings. Like structure is indicated by like reference numerals, and in which:

“FIG. “FIG.

“FIG. 2A shows an upper perspective view showing the wearable electronic device in FIG. 1. according to one or more of the embodiments shown and described herein.

“FIG. “FIG. 2A with support tray in as-assembled condition, according to one or several embodiments described or shown herein.

“FIG. 2C shows an upper perspective view showing the main housing before attachment to the support tray. 2B as per one or more of the embodiments described or shown herein.

“FIGS. 2D and 2E show upper perspective views of FIG. 2C partially assembled with the antennas before (FIG. 2D) and (FIG. 2E) connection between them according to one or several embodiments shown or discussed herein;

“FIG. 2F is an exploded view from the upper perspective of FIG. 2A shows an exploded upper perspective view of FIG. 2, as well as a block diagrammatic representations of the logic device and various sensors, as well as the hybrid wireless communication module, according to one or several embodiments described herein.

“FIG. 2G shows a top view showing the main housing assembly for the wearable electronic device in FIG. 2A with the top covering removed in accordance to one or more embodiments described or shown herein.

“FIG. “FIG. 2A with an attachable belt according to one of the embodiments described or shown herein.

“FIG. “FIG.

“FIGS. 3A and 3B show notional cloud-based uplink/downlink messages between the wearable electronics device and system of FIG. 1;”

“FIG. 3C is a BLE and an eleven-byte beacon data format for some messages in FIGS. 3A and 3B, respectively.

“FIG. 3D shows a 11-byte GNSS data format that contains some messages from FIGS. 3A and 3B, respectively.

“FIG. “FIG. 3A and 3B, respectively.

“FIG. 3F is an eleven-byte format for data from the nurse call button for some messages in FIGS. 3A and 3B, respectively.

“FIG. “FIG. 3A and 3B

“FIG. “FIG. 3A and 3B, respectively.

“FIG. “FIG. 3A and 3B

“FIG. “FIG. 3A and 3B, respectively.

“FIG. “FIG. 1. according to one or more of the embodiments shown or discussed herein;

“FIG. FIG. 5 shows a simplified view showing a cloud-based connection between interested parties. This connectivity is based on information received from FIG. 1. according to one or more of the embodiments shown or discussed herein;

“FIG. “FIG. 1 can be used to create a machine-learning model according to one of the embodiments described or shown herein.

“FIG. “FIG.7” depicts a program structure as a neural network, according to one or more of the embodiments described herein.

“FIG. “FIG. 8. 8 shows a data structure that consists of a section of an ADL documentation chart for a patient. This data structure can be automated using data collected by the wearable electronic devices and systems of FIG. 1. according to one or more of the embodiments described or shown herein.

“FIG. “FIG. 1 and their wireless connectivity via the cloud to ascertain the position and activity of a patient in a multi-patient residence, as well as to display patient information to a remote computing devices according to one or several embodiments shown or discussed herein.

Summary for “Wearable electronic device for tracking location and identifying changes to salient indicators of patient’s health”