Wearable multi-sensor system and method for monitoring physiological metrics and providing feedback

Abstract

There is provided a modular and portable system for monitoring biomechanical and physiological metrics of a user or patient and for managing treatment and exercises with real-time feedback. Wearable sensors provide detailed movement, position and physiological data during everyday activities and during exercise or therapy outside of clinical environments. The system provides real-time feedback to guide and correct movements and to mitigate motor symptoms of various disorders and conditions. The user's data is processed to provide real-time symptom monitoring and intelligent insights to improve treatment management and efficacy of exercise and rehabilitation.

Description

Wearable multi-sensor system and method for monitoring physiological metrics and providing feedbackCross-reference

[0001] The present disclosure claims priority to, or a domestic benefit of, US 63 / 764,215, filed 27 February 2025, the entire contents of which are incorporated herein by reference where permissible.Field of Invention

[0002] The present disclosure generally relates to systems and methods for monitoring physiologically relevant motions, managing treatment, providing real-time feedback to mitigate motor symptoms, and remotely guiding exercise and therapy using sensors, actuators and computer programs. More particularly, the disclosure relates to a wearable multi-sensor system and method for monitoring movement and health metrics and providing feedback.Background

[0003] As medical technology advances, devices involving wearable sensors for monitoring physiological and vital signs have been increasingly relied upon for symptom monitoring and effective patient care and treatment. Clinical symptom monitoring for movement disorders such as Parkinson’s disease generally involve infrequent and subjective clinical judgments, which are complicated by symptoms that often vary throughout the day and are often difficult to detect in standard examinations, resulting in frequent misdiagnosis and inaccurate assessments.

[0004] Many wearable devices include sensors that provide some level of continuous objective monitoring related to an individual’s physical motions. They generally involve motion tracking systems based on motion sensors, such as accelerometers that are fixed to the body and generate movement data, or motion capture systems based on one or more carefully positioned cameras that rely on streams of images to obtain movement information.

[0005] It is desired to provide improved wearable multi-sensor systems and methods for monitoring movement and health metrics and providing feedback.Summary

[0006] The present invention addresses the aforementioned need by providing a method and system for monitoring movement and health characteristics of a user or patient and for managing treatment and exercises by providing real-time feedback. The system includes a computing device with communicationcapabilities, multiple sensor modules that provide both motion data and position data, and accessory modules that allow for a variety of physiological indicators to be measured using a variety of sensor types. The computing device processes data from these modules to generate refined metrics that are more accurate than existing motion sensor systems and provides real-time feedback to the user to mitigate symptoms and improve the efficacy of exercise and rehabilitation.

[0007] The system integrates a cloud platform that further analyzes the user’s movement and health metrics to provide detailed and real-time health insights for managing treatment and exercises. This invention aims to improve the accuracy of sensor data and timeliness of feedback, thereby enhancing the user's ability to monitor and improve health and exercise outcomes.

[0008] In one aspect of the present invention, the system improves the accuracy and utility of biomechanical metrics from motion sensor data by synchronizing the motion sensor data and metrics with position data.

[0009] In another aspect of the present invention, the system enhances the utility of motion sensor data by synchronizing the motion sensor data and biomechanical metrics with physiological metrics to produce unique insights for patient care and exercise.Brief Description of Drawings

[0010] Fig. 1 is a conceptual overview of a system for monitoring a user’s physiological metrics, for providing custom exercises, therapy and feedback, and for facilitating metrics sharing and interactions between users and third parties according to an embodiment.

[0011] Fig. 2 is a block diagram of a sensor module, accessory module, base station (computing device), and user device according to an embodiment.

[0012] Fig. 3A is a front view of a base station with a “pill” (i.e. a sensor module) received by a base / sensor adapter of the base station according to an embodiment.

[0013] Fig. 3B is a side view of a base station illustrating the determination of a y-coordinate of a sensor module in 3D space according to an embodiment.

[0014] Fig. 3C is a top view of a base station illustrating the determination of an x-coordinate and a z-coordinate of a sensor module in 3D space according to an embodiment.

[0015] Fig. 4 is a diagram of a system 100C in accordance with an embodiment.Detailed Description

[0016] Motion tracking systems often lack the accuracy and reliability required for clinical-grade monitoring. Many of these systems also fail to provide position data in three-dimensional space and are limited to wrist-worn or ankle-worn devices that are unable to account for symptoms such as voice changes, stooped posture and dysphagia.

[0017] Many motion capture systems similarly struggle to accurately identify symptoms due to inability to monitor subtle movement variations and the potential for altered patient movements due to the awareness of being observed. These systems often involve bulky or expensive equipment and complex setups requiring dedicated spaces and lighting, leading to inconsistent measurements and user experiences, reducing compliance and effectiveness.

[0018] Motion tracking and motion capture systems also fail to provide other relevant health and activity information that are implicated in several motor disorders and are affected by medications, such as blood pressure, heart rate and respiration. In Parkinson’s disease, the complex interplay between different symptoms, whereby motor symptoms can exacerbate non-motor symptoms and vice versa, underscores the necessary of a comprehensive data collection approach that extends beyond motion data.

[0019] Current systems are also not well suited to patients receiving physical therapy or rehabilitation, especially where therapy exercises require guidance to perform exercises correctly and are completed outside of clinical environments such as patient’s home. Current systems are not tailored to the specific needs of patients and often lack the ability to monitor therapeutic activities outside of clinical environments. They also fail to provide real-time feedback to patients engaging in physical therapy, which leads to reduced adherence and effectiveness of therapy plans.

[0020] Current systems therefore fail to meet the needs of individuals requiring chronic health monitoring, remote therapy, and physical rehabilitation. Therefore, there is a need for an improved system that can integrate multiple types of sensors to detect various biomechanical and physiological signals, process data efficiently, and deliver real-time feedback to users to enhance their performance and health outcomes.

[0021] Embodiments of the present invention provide a modular and portable system for monitoring biomechanical and physiological metrics of a user or patient and for managing treatment and exercises with real-time feedback. Wearable sensors provide detailed movement, position and physiological data during everyday activities and during exercise or therapy outside of clinical environments. The systemprovides real-time feedback to guide and correct movements and to mitigate motor symptoms of various disorders and conditions. The user’s data is processed to provide real-time symptom monitoring and intelligent insights to improve treatment management and efficacy of exercise and rehabilitation. The system therefore addresses an unmet need for personalized remote care and exercise guidance that produces greater compliance and outcomes than existing methods and provides objective information for assessing and managing treatment and exercise.

[0022] Embodiments of the apparatus will be understood with reference to Figs.1, 2, and 3A-3C, together with the following description. Fig. 1 is a conceptual overview, in accordance with an embodiment, of a system 100A for monitoring physiological metrics of a user (e.g. 102), for providing custom exercises, therapy and feedback, and for facilitating metrics sharing and interactions between users and third parties (e.g. 104), such as instructors, researcher and clinicians and / or fellow users, caregivers or other members 106A of a virtual community 106. System 100 comprises a plurality sensor modules 108 (e.g. a representative one of which is sensor module 108A) that are user coupled and / or body worn such as shown. Sensor modules 108 communicate with a base station 110, such as wirelessly, as further described. Sensor modules 108 communicate with one or more user devices 112 (e.g. a representative one of which is sensor module 112A), such as wirelessly, as further described. User devices 112 may include a computing device such as a laptop, desktop, tablet, smartphone, etc.

[0023] User devices 112 are coupled (e.g. via one or more networks, for example, the Internet) to a cloud-based (in an embodiment) platform such as cloud health platform 114. Cloud health platform 114 comprises one or more computing devices 114A (not individually shown). The computing devices 114A of cloud health platform 114 are configured (e.g. via software) for one or more of systems monitoring, treatment management, exercise and rehabilitation (management), or virtual community facilitation. In an embodiment, the platform 114 is configured to communicate with user devices for a plurality of respective users (not show) to provide services to each respectively.

[0024] In an embodiment, third parties 104 have respective computing devices (e.g. 104A) coupled (e.g. via one or more networks, for example, the Internet) to cloud health platform 114. Similarly, in an embodiment, virtual community members 106A have respective computing devices (e.g. 106B) coupled (e.g. via one or more networks, for example, the Internet) to cloud health platform 114. For simplification, network components are not shown.

[0025] Fig. 2 is a block diagram of a system 100B including a sensor module (e.g. 108A), accessory module 200, base station 110 (a form of computing device), and user device 112A each according to an embodiment. Representative sensor module 108A comprises a microcontroller 202A incommunication with a plurality of components (e.g. via a bus or other structure (not illustrated), the components comprising indication LEDs 202B, external flash memory 202C, haptic actuator 202D, Bluetooth transceiver / wireless comm, unit 202E, inertial measurement unit (IMU) 202F, ultra-wide band tag 202G, rechargeable battery and battery management unit 202H, adapters 2021 (e.g. a plug-in coupler and an accessory adapter). The rechargeable battery and battery management unit 202H and one of the adapters 2021 are coupled, for example, for recharging purposes. Sensor module, in an embodiment, couples with an accessory module (e.g. via an extension interface).

[0026] Accessory module 200 comprises a microcontroller 200A in communication with a plurality of components (e.g. via a bus or other structure (not illustrated), the components comprising one or more sensors 200B, and optional components, comprising external flash memory 200C and rechargeable battery and battery management unit 200D and a further component, namely, adapter 200E (e.g. a plugin coupler). The rechargeable battery and battery management unit 200D and adapter 200E are coupled, for example for recharging purposes.

[0027] Base station 110 comprises a microcontroller 204A in communication with a plurality of components (e.g. via a bus or other structure (not illustrated), the components comprising indication LEDs 204B, inertial measurement unit (IMU) 204C, external flash memory 204D, rechargeable battery and battery management unit 204E, adapters 204F (e.g. a plug-in coupler and a plurality of base / sensor adapters 300 (see Fig. 3F)), first and second dual ultra wideband anchors (antenna) 204G and Bluetooth transceiver / wireless comm, unit 204I. The rechargeable battery and battery management unit 204E and one of the adapters 204F are coupled, for example for recharging purposes. As shown in Fig. 3A, base / sensor adapters 300 are configured to receive a pill, i.e. a sensor module, coupling to one of its respective adapters 202I.

[0028] Representative user device 112A comprises one or more processors 206A, one or more storage devices 206B (e.g. storing instructions, such as software, providing one or more applications such as a mobile or web application 206C), a display 206C (which is a touch screen device in an embodiment), a Bluetooth transceiver / wireless comm, unit 206E and external flash memory 206F. User device 112A further comprises a communication subsystem 206G for network communication (whether wired and / or wireless to one or more LAN, WAN or other networks, for example, the network such as for communication with cloud platform 114, WIFI, cellular, GPS, etc. Though not shown, user device 112A comprises or is coupled to one or more input devices (e.g. buttons, microphone, camera, gesture I pointing device, such as a mouse, etc.) one or more output devices (e.g. speaker, bell, lights, etc.). Inan embodiment, user device 112A comprises a rechargeable battery and battery management unit (not shown).

[0029] The various devices shown are examples of computing devices chiefly characterized by a processor (e.g. a microcontroller or a CPU, GPU, etc.) a storge device(s) storing instructions which when executed by the processor cause the computing device to perform steps of a computer implemented method. The computing device typically has one or more input and output devices. In an embodiment, the computing device executes an operating system as well as one or more applications to provide features, functions and services to users thereof. Alternative arrangements and configurations are apparent to a person of ordinary skill in the art.

[0030] Fig. 3A is a front view of a base station 110 in accordance with an embodiment, showing a representative form factor for the device. Fig. 3A shows station 110 coupled with a “pill” 108N (i.e. one of the plurality of sensor modules 108) as received by a base / sensor adapter 300A, one of a plurality of such base / sensor adapters 300. Fig. 3A further shows the first and second dual antenna ultra-wideband anchors (each UWB Antenna), 204G and 204H. First UWB Antenna 204G is vertically aligned in base station 110, second UWB Antenna 204H is horizontally aligned in base station 110. As described further, an extra pill 108N (i.e. one of the sensors that is not being body worn to collect user data via motion etc.) can be used in base station 110 for improved accuracy of measurements. Note that renderings of various components shown in Figs. 3A-3C may be in different scales for convenience.

[0031] Fig. 3B is a side view of a base station 110 illustrating the determination of a y-coordinate of a sensor module (e.g. 108A) in 3D space. Fig. 3C is a top view of a base station 110 illustrating the determination of an x-coordinate and a z-coordinate of a sensor module 108A in 3D space. The y coordinate is solved using the Phase Difference of Arrival of the UWB transceiver (204G) that has vertically aligned dual antennas. In an embodiment, for distance d1 between sensor module 108A and the first dual UWB antenna (e.g. 204G):

[0032] dx = dz = d1*cos 0; and

[0033] dy = d1*sin 0.

[0034] It will be understood that dx = dz since the solution set for the position of the pill lies in a circle (not shown) around the UWB receiver at distance d1*cos 0. Similar considerations apply for the x and z-coordinates as shown if Fig. 3C, where d2, the distance between sensor module 108A and dual UWB antenna is noted as d2. The x coordinate is solved using the Phase Difference of Arrival of the UWB transceiver (204h) that has horizontally aligned dual antennas. The z-coordinate is solved using thecosine portion of the measurement from both transceivers, along with an extra pill(s) on the dock (base station 110). Thus, in an embodiment:

[0035] dz = dy = d2*cos <|); and

[0036] dx = d2*sin <|).

[0037] It will be understood that dz = dy since the solution set for the position of the pill lies in a circle (not shown) around the UWB receiver at distance d2*cos <|).

[0038] Operations performed by the apparatus, including a cloud platform, will be understood with reference to the system 100C in block diagram of Fig. 4. System 100C is similar to systems 100A and 100B, showing additional functions and features and user connections. Fig. 4 shows end users 102 and 104 receiving functions or services from components of a med. system 400. Med. system 400 comprises hardware components 402, user device 112A, and cloud platform 114. In an embodiment, hardware component 402 comprises no or one or more sensorized accessories (e.g. 200), sensor modules (e.g. one or more of sensors 108) and the dock (base station 110). These hardware components are variously coupled such as previously described. And at least some are coupled to user device 112A as previously described. User device 112A is configured such as by instructions stored and executed to provide one or more applications, functions, etc. Examples include symptom monitoring 404A, treatment management 404B, rehabilitation gaming exercise platform 404C and e-community services 404D. Rehabilitation gaming exercise platform 404C and treatment management are linked via a feedback connection. User device 112A is coupled with platform 114 sch as to provide sensor or other data and receive data such as for one or more of the applications or functions 404A-404D.

[0039] Cloud platform 114 provides cloud health services such as Al-based disease evaluation (114B) and digital clinic 114C. Thus, in an embodiment, the features of the digital platforms are accessible via a mobile application of a user: symptom monitoring platform, exercise and rehabilitation platform (labeled as “Rehab Gaming I Exercises Platform”), and virtual community platform (labeled as “E-Community”) according to an embodiment.

[0040] Cloud platform 114 provides cloud health services (e.g. features of a digital treatment management platform) accessible via a mobile application of a user according to an embodiment. The user may include some of the users 104 as noted.

[0041] In an embodiment, the system comprises three main physical components: a computing device, sensor modules, and accessory modules. In an embodiment, the computing device is configured as adocking station, as further described. In an embodiment, the system integrates with a cloud platform for additional processing and analysis to provide enhanced insights into a user’s health status, disease progression and treatment efficacy. The cloud platform also enables data sharing and interactions between the user, clinicians, therapists, caregivers and other users, facilitating more accurate and remote treatment management and the creation of a virtual community to provide users with additional support and connections with other patients.

[0042] Thus, in an embodiment, the computing device includes a communication unit, at least one processor, two or more dual antenna ultra-wideband (“UWB”) anchors for radio communication over a wide band of spectrum, an inertial measurement unit (“IMU”), and at least one storage device. The IMU is useful with the UWB to provide accurate orientation of the sensor modules. In an embodiment, the computing device further includes physical adapters for receiving sensor modules, contact pins for charging and communicating with sensor modules, indication lights (e.g., to indicate power status or pairing status with sensor modules or accessory modules), at least one rechargeable power source and one or more sensors.

[0043] The communication unit of the computing device is configured to wirelessly communicate with sensor modules and accessory modules via a suitable wireless communication protocol, such as Bluetooth® (BLUETOOTH SIG, INC.). The communication unit may therefore enable the computing unit to receive sensor data and metrics from the sensor modules and accessory modules and provide instructions to the sensor modules and accessory modules. The at least one processor may be included within a microcontroller and executes instructions stored in the storage device to perform various functions of the system.

[0044] The UWB anchors facilitate the generation of timestamped three-dimensional (“3D”) position data of the sensor modules. Each UWB anchor is equipped with dual antennas positioned such that at least two antennas lie on each of three perpendicular axes (i.e., at least two antennas on each of an x-axis, y-axis and z-axis) to enable accurate acquisition of UWB tags in 3D space with a resolution of ~1 cm. The UWB anchors communicate with UWB tags in the sensor modules to determine their precise location in real-time.

[0045] The computing device acts as a base station for the sensor modules and be referred to as a “base station”, “base” or “dock”. In an embodiment, it provides a central hub for coordinating data transfer, position calibration for he sensor notes and sensor node management. The computing device comprises one or more base / sensor adapters to receive and charge the sensor modules, and to facilitate data transfer between the base station and the sensor modules when the sensor modules are not inuse (i.e., not coupled to a body part of a user). In an embodiment, the base station comprises 8 base / sensor adapters configured to simultaneously receive and communicate with up to 8 sensor modules through contact pins. In other embodiments, the base station charges and communicates with the sensor modules exclusively through wireless means, such as via Bluetooth and wireless / inductive charging coils.

[0046] The sensor modules are small, lightweight and are designed to be attached to different body parts of the user, such as a finger, hand, wrist, forearm, upper arm, shoulder, head, neck, chest, back, abdomen, waist, upper leg, lower leg, ankle or foot. This broad range of attachment sites allows for detailed measurements of individual joint activity, as well as holistic whole body measurements. The sensor modules each comprise an IMU, a UWB tag, a feedback actuator, a communication unit, one or more rechargeable power sources, one or more external flash memories, and one or more processors which may be included in a microcontroller. The sensor modules further comprise adapters for connecting to the computing device for charging the sensor modules and as an additional means for pairing or data transfer between sensor modules and the computing device. The adapters may also be configured to receive accessory modules for communicating with and charging the accessory modules.

[0047] In an embodiment, the IMU is a 6-axis IMU comprising a 3-axis accelerometer and a 3-axis gyroscope. In another embodiment, the IMU is a 9-axis IMU comprising a 3-axis accelerometer, a 3-axis gyroscope and a 3-axis magnetometer. The IMUs generate IMU sensor data responsive to body movement (motion sensing, positioning sensing), which is used to generate biomechanical time series metrics comprising one or more of acceleration, velocity, angular velocity, displacement, angular displacement, or orientation.

[0048] The UWB tag in each sensor module communicates with the UWB anchors of the computing device to provide 3D position data. This communication occurs at high frequencies, ensuring low latency and high accuracy in position tracking, which is used to refine the biomechanical time series metrics and provide additional insights related to motor function and motor symptoms.

[0049] The feedback actuator in each sensor module provides real-time feedback to the user based on (e.g. the computing device’s) analysis of biomechanical and physiological metrics, which can mitigate motor symptoms and provide guidance when performing exercises or therapy. In an embodiment, the computing device coordinates the feedback among sensor modules worn on different parts of the body, allowing for intricate feedback schemes and enhanced guidance in performing exercises and therapy. In an embodiment, the feedback actuators delivers haptic feedback in the form of vibrations, which may also be used to provide alerts to the user.

[0050] The accessory modules may include various accessory sensors for monitoring physiological metrics such as heart rate variability, blood pressure, neural activity, stress, muscle activity, speech, temperature and blood oxygen saturation, among others. Examples of accessory sensors include electrocardiograms (“ECG” / “EKG”), electromyography (“EMG”) sensors, electrodermal activity (“EDA”) sensors, electroencephalographs (“EEG”) pulse oximeters, thermometers and microphones. Each accessory module generates accessory sensor data, which is used to generate physiological time series metrics. In an embodiment, the accessory modules communicate with the sensor modules and computing device to transmit the collected data for further processing.

[0051] In an embodiment, the cloud platform receives the sensor data and metrics from the computing device, as well as other health-related user data via a digital health diary in a mobile or web-based application. In an embodiment, the cloud platform is configured to use machine learning I artificial intelligence (“Al”) algorithms to facilitate intelligent analysis of the extensive data and metrics generated by the sensor modules and accessory modules, as well as the user’s other health-related data, enabling the extraction of specific symptom metrics in real-time to provide invaluable insights for patients, clinicians, caregivers and researchers. The cloud platform can serve as a secure digital health platform for advanced health data analysis, providing safe and confidential handling and sharing of sensitive health information.

[0052] In some embodiments, the mobile application and / or cloud platform may interface with one or more third-party health data platforms via application programming interfaces (APIs) or software development kits (SDKs). Such platforms may include, without limitation, smartwatch or wearable ecosystems and health data aggregation frameworks. The system may ingest, synchronize, or aggregate health-related data obtained from external devices, including but not limited to activity metrics, heart rate, oxygen saturation, electrocardiogram data, blood pressure data, caloric expenditure, or other physiological measurements. The ingested data may be fused with sensor data collected by the disclosed sensor modules to generate unified time series metrics or predefined physiological events.

[0053] In an embodiment, the cloud platform provides access to one or more digital platforms (e.g. as described herein) through one or more feature-rich mobile or web-based applications. In an embodiment, the digital platforms include a symptom monitoring platform configured for real-time symptom tracking and historical disease progression tracking. User interfaces are configured to present tracking information through graphical visualizations. In an embodiment, the symptom monitoring platform also enables the sharing of disease progression data (e.g. historical record) and other relevant biomechanical and physiological metrics with clinicians and caregivers. In an embodiment, the digital platforms include a treatment management platform configured for medication tracking and reminders,side effect identification, disease progression predictions and for interacting with and scheduling appointments with clinicians.

[0054] In an embodiment, there is provided an exercise and rehabilitation platform that enables clinicians, therapists, instructors (e.g., coaches, yoga, etc.) and third party developers to provide custom exercises, therapy programs and rehabilitation games to users. The exercise and rehabilitation platform leverages the wearable sensor system to provided guided exercises and real-time feedback and performance tracking to improve therapy efficacy and adherence. A user’s performance with such exercises, as measured by the sensor modules and accessory modules, contributes to the data analyzed with machine learning, thereby refining the recommendations and predictions made through the treatment management platform. The exercises and rehabilitation games from third party developers may be provided in the form of separate applications, for example, through a mobile app store.

[0055] In an embodiment, there is provided a virtual community (or e-community) platform that facilitates virtual support groups and connections among patients and caregivers, reducing social isolation and the stigmas related to various diseases, disorders and condition. The virtual community platform also facilitates the sharing of patient experiences and advice, which is particularly beneficial for individuals that have been newly diagnosed with a disease, disorder or condition. The virtual community further supports a digital marketplace, providing users with Al-driven recommendations for health products and services that are tailored to their circumstances.

[0056] In some embodiments, the digital marketplace further comprises an event discovery and promotion module configured to present users with information regarding conferences, therapeutic classes, rehabilitation programs, clinical studies, educational webinars, or community events. The event discovery module may use one or more of the user’s biomechanical metrics, physiological metrics, symptom metrics, treatment history, engagement-related metrics, geographic location, or clinician recommendations to personalize event suggestions. The platform may enable third-party providers to advertise, promote, or host such events within the digital marketplace.

[0057] The system therefore facilitates a robust data-driven approach to enhance patient engagement and symptom management, providing a comprehensive tool for all stakeholders in the management and study of various diseases and disorders. Potential uses cases include the management of treatment, therapy and rehabilitation for individuals undergoing care for Parkinson’s disease, dementia, stroke, attention deficit hyperactivity disorder, chronic respiratory conditions and post-injury rehabilitation or post-surgery recovery. In certain embodiments, the system may further quantify and analyze social engagement metrics as a health-related metric type, derived from sensor data, activity patterns, vocalinteraction signals, communication frequency, or aggregated community-level data, to assess behavioral participation, isolation risk, therapy adherence, or quality-of-life indicators.

[0058] In an embodiment, the system may be applied to the monitoring and management of attention deficit hyperactivity disorder (ADHD). The one or more first or refined biomechanical time series metrics and / or physiological time series metrics may be analyzed to detect patterns associated with hyperactivity, impulsivity, motor restlessness, vocal activity, or stress-related physiological responses. The computing device and / or cloud platform may determine the occurrence or quality of predefined physiological events related to dysregulated movement or behavioural patterns and may provide realtime feedback via one or more sensor modules to support behavioural regulation, structured activity engagement, or therapy adherence.

[0059] In some embodiments, the one or more time series metrics may further comprise engagement-related metrics derived from one or more of activity levels, mobility patterns, vocal activity indicators, interaction frequency, exercise participation signals, or environmental interaction patterns detected by the one or more sensor modules, accessory modules, computing device, and / or cloud platform. The engagement-related metrics may be used to assess participation levels, adherence to prescribed exercises or activities, therapy compliance, environmental interaction patterns, behavioral trends, or quality-of-life indicators relevant to treatment monitoring, rehabilitation management, or disease progression analysis.

[0060] In some embodiments, the subject may comprise a non-human animal. The disclosed sensor modules, synchronization framework, refined biomechanical time series metrics, and / or physiological time series metrics may be adapted for monitoring movement, posture, activity patterns, stress responses, or physiological states of companion animals, livestock, or research animals. The computing device and / or cloud platform may analyze one or more first or refined time series metrics to determine predefined physiological events associated with veterinary health, behavioural conditions, recovery monitoring, or performance tracking.

[0061] METHOD OVERVIEW

[0062] One or more methods of the present disclosure for monitoring biomechanical and physiological metrics of a user and providing real-time feedback, according to various embodiments, is disclosed herein.

[0063] In an embodiment, a method comprises receiving in real-time, by a computing device, sensor data or metrics from one or more sensor modules and one or more accessory modules. In anembodiment, the sensor data or metrics are transmitted by a communication unit of each of the one or more sensor modules or accessory modules and are received by a communication unit of the computing device. The communication unit may be a wireless communication unit, such as a Bluetooth transceiver.

[0064] In another embodiment, the computing device receives the sensor data and metrics through physical base / sensor adapters comprising contact pins in contact with contact pins of one or more sensor modules or accessory modules. The contact pins may also be used to pair the one or more sensor modules or accessory modules with the computing device, or to charge a rechargeable power source of a respective sensor module or accessory module. In another embodiment, the contact pins of the sensor modules and accessory modules may be used for wired charging.

[0065] In an embodiment, the sensor modules and accessory modules comprise one or more LED indicators that provide different indications based on different states or functions of a given sensor module or accessory module. For example, different numbers, colours or activation patterns of LED indicators may be used to indicate various states, such as a charging state, a pairing state, a paired state and a data transfer state, as well as to indicate various errors.

[0066] In an embodiment, each sensor module and accessory module are coupled to a body part of user, such as a finger, hand, wrist, forearm, upper arm, shoulder, head, neck, chest, back, abdomen, waist, upper leg, lower leg, ankle or foot. Multiple sensor modules and accessory modules may be coupled to the same body part. In an embodiment, one sensor module is coupled to a body part of the user. In another embodiment, up to eight sensor modules are coupled to one or more body parts of the user. The location of a sensor module or accessory module on the body of a user may determine the type of sensor data or metrics produced by the respective sensor module or accessory module.

[0067] The sensor data or metrics from any given sensor module or accessory module may relate to the body part to which the sensor module or accessory module is coupled, or to a different body part. For example, In an embodiment, the sensor data or metrics from a waist-coupled sensor module may relate to movement of the legs.

[0068] The sensor data or metrics are time series data or time series metrics. Any reference herein to sensor data and metrics should be understood to mean time series sensor data and time series metrics.

[0069] The sensor data or metrics received from a sensor module comprise sensor module-originated IMU sensor data or one or more first biomechanical metrics. The sensor module-originated IMU sensor data for each respective sensor module are generated by an IMU and comprise time series measurements of one or more of vibration, acceleration, velocity, angular velocity, or orientation for therespective sensor module. The one or more first biomechanical metrics comprise one or more biomechanical characteristics of the one or more body parts, including heart rate, swallowing activity, vocal activity, gait, movement or orientation. In an embodiment, the IMU sensor data comprises time series measurements of subtle vibrations in the throat to generate biomechanical metrics related to vocal activity.

[0070] In an embodiment, the IMU sensor data from a sensor module is processed by a processor of the sensor module to generate first biomechanical metrics related to one or more body parts. The processor of the sensor module may be a component of a microcontroller. In another embodiment, the IMU sensor data is processed by a processor of the computing device to generate first biomechanical metrics. The at least one processor of the computing device may be a component of a microcontroller. The IMU sensor data or first biomechanical metrics from each sensor module may be stored in an external flash memory of the respective sensor module or in an external flash memory of the computing device.

[0071] The sensor data or metrics received from an accessory module comprise accessory sensor data or one or more physiological metrics. The accessory sensor data for each respective accessory sensor module are generated by one or more accessory sensors, which may comprise any sensor capable of detecting physiologically relevant signals, such as biological, chemical, electrical, electromagnetic, acoustic, optical or heat. In various embodiments, an accessory sensor may comprise electrocardiograms (“ECG” / “EKG”), electromyography (“EMG”) sensors, electrodermal activity (“EDA”) sensors, electroencephalographs (“EEG”) pulse oximeters, thermometers or microphones. The one or more physiological metrics comprise physiological characteristics of muscle activity, fatigue, neural activity, blood oxygen saturation, pulse, blood pressure, respiration, stress, sleep, speech, temperature or other characteristics determined by biological, chemical, electrical, electromagnetic, acoustic, optical or heat indicators. Sensorized accessorise may be voice action capable and perform voice activity detection.

[0072] In an embodiment, the accessory sensor data is processed by an accessory module processor to generate physiological metrics related to one or more body parts. The accessory module processor may be a component of a microcontroller. In other embodiments, the accessory sensor data is processed by a processor of a sensor module or the computing device to generate physiological metrics. The accessory sensor data or physiological metrics from each accessory module may be stored in an external flash memory of the respective accessory module or in an external flash memory of a sensor module or of the computing device.

[0073] In an embodiment, the accessory sensor data or physiological metrics are first received by a sensor module through a physical connection comprising contact pins. The contact pins may also be used to charge a rechargeable power source of a respective accessory module or provide instructions to the respective accessory module by a sensor module. In an embodiment, an accessory module and a sensor module are continuously coupled to one another through the physical connection when coupled to a body part of a user.

[0074] The method further comprises generating, by the computing device, timestamped 3D position data of each of the one or more sensor modules based on communication between the UWB tags of the sensor modules and the UWB anchors of the computing device. In an embodiment, the UWB tag of each sensor module received by a base / sensor adapter of the computing device is configured to be used by the base station as an additional UWB anchor antenna in addition to the two or more dual antenna UWB anchors of the base station. By increasing the number of sensor modules received by the base / sensor adapters of the computing device, the accuracy of the 3D position data may be improved.

[0075] The computing device synchronizes and processes the one or more first biomechanical metrics with the 3D position data for each of the one or more sensor modules to generate one or more refined biomechanical metrics. The one or more refined biomechanical metrics comprise the one or more first biomechanical metrics having improved accuracy and one or more position characteristics of the one or more body parts, including position, pose, posture, pathlength, trajectory, or range of motion.

[0076] In an embodiment, the computing device is coupled to a body part of the user and further comprises a local IMU configured to generate computing device-originated IMU sensor data responsive to body movement of the one or more body parts for generating the one or more first biomechanical metrics. In an embodiment, the one or more first biomechanical metrics generated from the computing device-originated IMU sensor data is combined and / or processed with sensor module-originated IMU sensor data or the one or more first biomechanical metrics generated from the sensor module-originated IMU sensor data to enhance the accuracy of the one or more refined biomechanical metrics.

[0077] The method further comprises determining, by the computing device, whether to provide realtime feedback to the user in response to analysis of one or more of the one or more first or refined biomechanical metrics or physiological metrics. The analysis determines an occurrence of or quality of one or more predefined physiological events and one or more relevant sensor modules associated with the one or more predefined physiological events for providing corrective feedback.

[0078] The occurrence of a predefined physiological event comprises (i) an onset or a cessation of a clinical symptom or (ii) an indication that a first or refined biomechanical metric or physiological metric complies with or deviates from one or more reference metrics. The quality of a predefined physiological event comprises (i) a severity of a clinical symptom or (ii) an extent to which a first or refined biomechanical metric or physiological metric complies with or deviates from one or more reference metrics. If real-time feedback is required, the computing device communicates with the relevant sensor module to provide feedback via the feedback actuator of the relevant sensor module.

[0079] In an embodiment, real-time corrective feedback is provided to correct a user’s movements in response to the onset of a symptom or a deviation from a reference metric. In other embodiments, realtime confirmatory feedback is provided to indicate to a user that a symptom has ceased or that a movement complies with a reference metric. Feedback may be provided in different patterns or intensities to indicate the occurrence of different predefined physiological events.

[0080] For example, if an analysis of the first or refined biomechanical metrics reveals the onset of a freezing of gait episode, the computing device may determine that real-time feedback is required and may communication with the one or more relevant sensor modules to provide real-time feedback via the respective feedback actuators of the one or more relevant sensor modules. In an embodiment, the first or refined biomechanical metrics of a particular sensor module (e.g., waist-coupled) may indicate the need to provide real-time feedback via a different sensor module (e.g., ankle-coupled). In an embodiment, the real-time feedback comprises haptic feedback provided by a haptic actuator of a sensor module. In other embodiments the real-time feedback comprises optical or auditory feedback provided by an indicator light or speaker of a sensor module.

[0081] In an embodiment, analysis uses one or more predefined thresholds determined using one or more biomechanical or physiological reference metrics generated from historical metrics of the user or a plurality of other users, model biomechanical or physiological metrics recorded by one or more clinicians, therapists, researchers or instructors using the one or more sensor modules, or other model metrics derived from suitable data sources. The reference metrics may be obtained from one or more individuals having no symptoms, individuals having a known type, severity or frequency of one or more symptoms or individuals recording model metrics comprising one or more target positions, orientations, poses, postures, pathlengths, trajectories, ranges of motion, movements or exercises involving one or more body parts.

[0082] For example, a therapist may develop model refined biomechanical metrics for a particular exercise through the creation of a virtual zone comprising a defined virtual 3D space in which a user’s body part must remain during an exercise.

[0083] In an embodiment, zones comprise model biomechanical metrics created by one or more clinicians, therapists or instructors by performing one or more predefined exercises comprising predefined positions, orientations, poses, postures, pathlengths, trajectories or ranges of motion of one or more relevant body parts using one or more sensor modules worn on the one or more relevant body parts and the computing device. The performance of the predefined exercise is recorded by the I MU sensors (e.g. of the modules and computing device) and by the communication between the UWB anchors of the computing device and the UWB tags of each of the one or more sensor modules worn during the performance of the exercise to generate model IMU sensor data and model 3D position data comprising a plurality of points in 3D space. A virtual circle, sphere or other 2D or 3D shape with a predefined radius, area or volume may be established around each point to define the zone. If a user attempts to perform the predefined exercise and one or more relevant body parts deviates from the zone, real-time feedback may be triggered at the one or more relevant sensor modules to notify the user of the deviation or guide the user’s movements to correct the deviation.

[0084] In some embodiments, the defined virtual zones extend beyond exercise guidance and are configured as safety boundary zones within clinical, institutional, residential, or community environments. The computing device and / or cloud platform may determine whether a user’s one or more body parts, or the user as a whole, deviates from a predefined safety boundary zone. Upon detecting a boundary deviation, in an embodiment, the system generates one or more alerts comprising haptic, auditory, visual, or remote notifications transmitted to caregivers, clinicians, or institutional monitoring systems. Such virtual safety zones may be used for wandering prevention, fall-risk mitigation, restricted-area monitoring, or supervised mobility training in hospitals, rehabilitation centers, assisted living facilities, schools, or home-care environments.

[0085] In an embodiment, a single sensor module may determine to provide real-time feedback via the respective feedback actuator in response to an analysis, by a processor of the sensor module, of one or more first biomechanical metrics. Based on the sensor processor’s determination to provide the feedback, the sensor processor may communicate with the feedback actuator of the respective sensor module to provide the feedback for a predefined duration or responsive to further analysis of additional one or more of the first biomechanical metrics associated with the occurrence of or quality of one or more predefined physiological events. For example, if a sensor module identifies the onset of a freezing of gait using only the IMU sensor data and first biomechanical metrics of the respective sensor module,that sensor module may cause its respective feedback actuator to provide feedback without further processing or analysis by the computing device. In an embodiment, the feedback actuator is actuated to provide cueing to the user, guiding the user to gait improvement.

[0086] Similarly, a sensor module may also identify a respective body part to which the respective sensor modules is coupled from an analysis of the I MU sensor data of the respective sensor module and reference IMU sensor data comprising signatures indicative of predefined body parts. Data identifying the respective body part to which a sensor module is coupled may be transmitted to the computing device by the respective sensor module to facilitate the analysis determining the one or more relevant sensor modules associated with an occurrence of or quality of one or more predefined physiological events for providing corrective feedback.

[0087] In some embodiments, health-related data, as referenced herein, may further include data obtained from one or more external wearable devices, mobile devices, or third-party health data repositories. For example, data is obtained via secure application programming interfaces (APIs) or software development kits (SDKs). Such externally sourced data may comprise physiological metrics, activity measurements, cardiovascular data, respiratory data, metabolic indicators, or other health-related measurements. The externally obtained data may be synchronized with, aggregated with, or fused with sensor-derived time series metrics to generate unified datasets for determining predefined physiological events and / or generating corrective feedback.

[0088] CLOUD PLATFORM

[0089] In an embodiment, the wearable sensor system integrates with a cloud platform for further processing and analysis of sensor data and metrics. The cloud platform is configured to provide cloud services and includes one or more cloud processors using machine learning algorithms, a data encryption module and one or more databases. The cloud services may be used by one or more of sensor module users, clinicians (e.g., physicians, surgeons, movement specialists, physiotherapists, occupational therapists, mental health professionals, etc.), instructors (e.g., coach, athletic trainer, yoga instructor, etc.), caregivers (e.g., family members, friends, personal support workers, etc.), or researchers (e.g., involved in clinical studies).

[0090] In an embodiment, the cloud platform receives sensor data and metrics from the computing device or user device. In an embodiment, the cloud platform (e.g. further) receives health-related data of the user via mobile or web-based applications, which may be provided by the user or by a third party, such as a clinician, instructor, caregiver, or researcher. The health-related data may comprise healthrecords and timestamped health diary data related to tracking medication, side effects, exercise, diet, sleep, energy levels and mood, as well as other information relevant to the health or activity of the user.

[0091] In an embodiment, the sensor data and metrics received by the cloud platform include I MU sensor data, accessory sensor data, 3D position data, one or more first biomechanical metrics, one or more refined biomechanical metrics and one or more physiological metrics related to one or more body parts of the user. The sensor data and metrics may be generated and pre-processed by the sensor modules, accessory modules and the computing device of a user before being received by the cloud platform as follows:a. the one or more first biomechanical time series metrics comprise one or more biomechanical characteristics of the one or more body parts, including heart rate, swallowing activity, vocal activity, gait, movement and orientation;b. the one or more first biomechanical time series metrics are generated by one or more sensor modules, each sensor module coupled to the sensor module user and comprising a UWB tag and an IMU, the IMU configured to generate IMU sensor data responsive to body movement of the one or more body parts for generating the one or more first biomechanical time series metrics;c. the IMU sensor data for each respective sensor module and / or computing device IMU comprises (or is processed to comprise) time series measurements of vibration, acceleration, velocity, angular velocity, displacement, angular displacement, and orientation for the respective sensor module;d. the 3D position data comprises timestamped information about a position of each of the one or more sensor modules in 3D space based on communication between the UWB tag of each sensor module and two or more dual antenna UWB anchors of the computing device, wherein the computing device synchronizes and processes the one or more first biomechanical time series metrics with the 3D position data of each of the one or more sensor modules to generate the one or more refined biomechanical metrics;e. the one or more refined biomechanical metrics comprise the one or more first biomechanical metrics having improved accuracy and one or more position characteristics of the one or more body parts, including position, pose, posture, pathlength, trajectory and range of motion;f. the one or more physiological time series metrics comprise physiological characteristics of muscle activity, fatigue, neural activity, blood oxygen saturation, pulse, blood pressure, respiration, stress, sleep, speech, temperature or other characteristics determined by biological, chemical, electrical or optical indicators; andg. the one or more physiological time series metrics are generated by one or more accessory modules, each accessory module comprising one or more accessory sensors configured to generate accessory sensor data used to generate the one or more physiological time series metrics.

[0092] In an embodiment, the cloud processor processes and analyzes the received data and metrics using machine learning I Al algorithms, which may include neural networks, decision trees, or support vector machines, among others. In an embodiment, the machine learning models are trained on disease- or disorder-specific reference data. Training data is synchronized and consistent across different sensor types and devices, ensuring that the machine learning-generated insights and inferences are accurate and reliable. Transfer learning may be used to fine-tune pre-trained models for specific symptoms or conditions, to enhance model performance across different patient populations, and to adapt models for individual treatment needs.

[0093] The analyses may be based on users’ sensor data, biomechanical and physiological metrics, and / or health-related data provided by users, clinicians, instructors, or caregivers. The analyses may include extracting symptom metrics in real-time, predicting disease progression, and making personalized recommendations.

[0094] Real-time symptom metric extraction may be used to assess symptoms related to specific diseases, disorders or conditions. In an embodiment, one or more cloud processors are configured to extract and assess symptom metrics related to Parkinson’s disease, such as tremor severity, gait abnormalities, bradykinesia, muscle stiffness / rigidity, balance impairments, sleep disturbances, stooping, vocal abnormalities, dysphagia or stress. Anomaly detection algorithms may be applied to identify abnormal symptoms or behaviours recorded by sensor modules and accessory modules to facilitate early interventions and alert clinicians to potential issues requiring urgent attention.

[0095] Disease progression predictions may be generated using machine learning models to analyze sensor data over time and generate inferences to provide clinicians with actional insights related to enable early interventions and create customized treatment plans. Cloud-based data sharing enables secure, real-time sharing of symptom metrics and disease progression data with caregivers or clinicians to facilitate continuous monitoring and up-to-date treatment optimization.

[0096] In an embodiment, recommendations are personalized based on machine learning analyses of a user’s sensor data and metrics and the user’s other health-related data (e.g., health records) received by the cloud platform. The personalized recommendations may include physical therapy exercises or games, cognitive exercises that may complement physical therapy, medication adjustments, and health products and services. The system also provides clinicians with data-driven insights related to treatment efficacy and recommended treatment parameters, enabling clinicians to optimize treatment parameters over time according to each user’s symptoms and disease progression.

[0097] In an embodiment, the one or more databases store the received data and metrics, as well as the outputs generated by the one or more cloud processors. The one or more databases may also comprise one or more data centres storing disease-specific, sport-specific or other relevant reference data. Cloud services such as Amazon Web Services® (Amazon Technologies, LLC.), Google Cloud™ (Google LLC.) or Microsoft Azure® (Microsoft Corp.) may be used to establish the one or more databases.

[0098] In an embodiment, the data encryption module provides end-to-end encryption, secure access controls, and multi-factor authentication to ensure data security. End-to-end encryption and access controls may comprise the implementation of key-and-lock mechanisms to ensure that stored data is accessed only by authorized users, clinicians, instructors, researchers or caregivers. Tiered levels of access may be configured to grant varying levels of permission based on user type or other conditions. Data access logs may also be maintained to record access or modifications to data.

[0099] In an embodiment, the cloud platform provides digital platforms accessible via mobile or webbased applications. These platforms enable users, clinicians, instructors, researchers, and caregivers to view and share data, access real-time and historical metrics, and receive virtual health support services.

[0100] In an embodiment, the digital platforms include a symptom monitoring platform, a treatment management platform, an exercise and rehabilitation platform, and a virtual community platform. The cloud platform may comprise a digital health clinic for providing the virtual health support services that integrates with one or more of the digital platforms. In an embodiment, the digital health clinic comprises self-assessments tests for users / patients, Al-based digital clinicians, one or more disease progression features for evaluating and sharing symptom metrics and treatment parameters with clinicians, or services for scheduling virtual or in-person appointments with clinicians and for enabling communication between users and clinicians. In an embodiment, the digital health platform is configured to provide ethical recommendations and warnings. For example, suggestions and recommendations are alignedwith medical regulations to ensure accuracy and avoid misleading users, users are proactively warned to consult professionals (e.g. their doctor) for concerns flagged by Al analysis, reducing stress and ensuring professional evaluation, and users are encouraged to share historical health data compiled via system 100A-100C for comprehensive understanding of the symptoms and monitoring results to enable the making of informed patient decisions.

[0101] In an embodiment, the digital platforms are accessible by platform users comprising one or more of sensor module users, clinicians, therapists, instructors, coaches, caregivers, researchers and product and service providers. The digital platforms may be accessible in mobile and web-based applications that are tailored to the particular type of platform user. For example, in an embodiment, the symptom monitoring platform and treatment management platform are accessible by platform users comprising any of sensor module users, clinicians, therapists or caregivers, though user interfaces or applications that are customized for each type of platform user.

[0102] In an embodiment, the symptom monitoring platform provides real-time symptom tracking and historical disease progression tracking through graphical visualizations and by generating related reports. The symptom monitoring platform further includes a digital diary (e.g. an interface) to log personal observations, triggers and / or medications.

[0103] The symptom monitoring platform also enables the sharing of disease progression data and other relevant biomechanical and physiological metrics with clinicians, caregivers or researchers. The symptom monitoring platform includes features for automatic detection and alerting of anomalies or new or worsening symptoms.

[0104] In an embodiment, the treatment management platform is configured to provide personalized medication management, medication tracking and alerts or reminders, side effect identification, disease progression predictions and / or a means for interacting with and scheduling appointments with clinicians.

[0105] The treatment management platform may facilitate medication and event tracking to monitor adherence and provide shareable records for caregivers and clinicians. Alerts and reminders may be provided through light and haptic alarms to remind users of medication schedules or critical events.

[0106] Personalized medication management may be facilitated through Al-driven dose optimization to provide dosage suggestions tailored to the patient’s symptoms, medication history and symptom progression trends. The treatment management platform may be integrated with a drug interaction database to alert users, clinicians or caregivers of potential issues when medications are added or adjusted, providing alerts for adverse interactions. The treatment management platform may monitorand cross-reference users’ recorded symptoms with a database of potential side effects to provide personalized alerts to users of possible and actual medication side effects based on users’ medication history and individual responses as determined by users’ biomechanical and physiological metrics. The personalized alerts may include severity-based recommendations, such as recommending hydration for mild symptoms or recommending clinician consultations for more severe symptoms.

[0107] Personalized medication management may include recommendations for specific medications, doses and frequencies with safeguards to ensure strict clinical oversight. Safeguarding may include a clinician validation step and the provision of disclaimers to characterize recommendations as informational data-driven insights rather than prescriptive medical advice.

[0108] In an embodiment, the treatment management platform provides disease progression predictions determined by machine learning-based analysis of extracted symptom metrics and associated trends. Predictions are presented to users and may be shared with clinicians to assist clinicians in developing optimized treatment plans. In an embodiment, the treatment management platform also provides an Al-based scheduler for appointments or visits with clinicians based on a user’s recorded disease progression and symptom metrics to prioritize critical needs and optimizing long-term care planning.

[0109] In an embodiment, the treatment management platform further provides users with customizable activity reminders to encourage health-promoting habits through personalized positive reinforcement.

[0110] In an embodiment, the activity reminders are integrated with guided physical exercises and cognitive exercises, including cognition games, provided through the exercise and rehabilitation platform. The exercise and rehabilitation platform may integrate with the treatment management platform to track users’ exercise progress and performance, and to improve adherence and engagement through the activity reminders. In an embodiment, activity reminders include: “Time to stand up and stretch”; “It’s time for your daily exercise routine”; and “Engage your mind with a quick game!”.

[0111] In an embodiment, the exercise and rehabilitation platform provides users with access to predefined exercises or games. The exercises or games may relate to therapy or rehabilitation programs, functional assessments, strength training, yoga, athletic activities, or recreational activities. The exercises and games may be developed by clinicians, therapists, instructors, coaches or third party developers using one or more sensor modules and a computing device I base station to create reference metrics for guiding user movements in the exercises or games. In some embodiments, the exercises and games use virtual zones created by clinicians, therapists, or instructors as reference metrics.

[0112] In an embodiment, a user’s real-time sensor data and metrics are monitored as the user engages with an exercise or game. In response to monitoring the user’s sensor data and metrics, the exercise and rehabilitation platform may provide instructions to the user’s sensor modules to provide real-time feedback to the user to correct or augment the user’s movements. In various embodiments, the feedback is haptic, auditory, visual, or a combination thereof.

[0113] In an embodiment, the exercise and rehabilitation platform integrates with the symptom monitoring platform to receive a user’s historical and real-time symptom metrics such as before, during and / or after the user engages an exercise or game. The cloud platform may apply machine learning algorithms to analyze the relationships between the user’s symptom metrics and the user’s performance or progress related to one or more exercises or games.

[0114] In an embodiment, the exercise and rehabilitation platform further integrates with the treatment management platform to refine or augment the personalized medication management outputs of the treatment management platform. The exercise and rehabilitation platform may provide one or more of the following inputs: a user’s symptom metrics, information about the user’s performance or progress related to one or more exercises or games, and machine learning-based analyses of the relationships between the user’s symptom metrics and the user’s performance or progress related to one or more exercises or games.

[0115] The exercise and rehabilitation platform may enable users to rate and review exercises and games via a ranking system to generate recommendations for other users of the exercise and rehabilitation platform or to generate insights related to user experience and therapeutic efficacy of one or more exercises or games.

[0116] In an embodiment, one user engages an exercise or game of the exercise and rehabilitation platform. In other embodiments, multiple users simultaneously engage an exercise or game in a multiuser or multi-player mode. In an embodiment of the multi-player mode, each user interfaces with a single shared device to engage the exercise or game. In another embodiment of the multi-player mode, each user interfaces with a separate device, each device connected by a network (e.g., internet) to a cloud server configured to host the exercise and rehabilitation platform.

[0117] In an embodiment, the exercise and rehabilitation platform hosts a marketplace for mobile or web-based applications developed by third parties, wherein the applications include exercises and games configured to integrate with the exercise and rehabilitation platform and further configured to monitor a user’s sensor data and metrics to provide real-time feedback to the user.

[0118] In an embodiment, the virtual community platform facilitates virtual support groups and connections among patients and caregivers, reducing social isolation and the stigmas related to various diseases, disorders or conditions. In an embodiment, the virtual community platform facilitates the creation of subgroups of users related to specific diseases, disorders or conditions. In another embodiment, the virtual community platform facilitates the creation of groups of users engaged in a particular therapy or rehabilitation program. In other embodiments, groups may be created in relation to athletics or recreation, such as a virtual yoga class a team of athletes of a team sport.

[0119] The virtual community platform may be configured to provide users with access to forums, online virtual meetings or videoconferencing means, or chat rooms. In an embodiment, one or more forums facilitate the sharing of experiences and advice related to one or more diseases, disorders, or conditions among users and caregivers. The virtual community platform may also comprise a recommendation system to provide users with personalized suggestions for exercises, games, educational resources or relevant social communities hosted by the virtual community platform.

[0120] The virtual platform may be further configured to host one or more digital marketplaces, providing users with Al-driven recommendations for health-related products and services that are tailored to their circumstances.

[0121] MOBILE / WEB-BASED APPLICATIONS AND USER INTERFACES

[0122] The methods and systems of the present disclosure comprise one or more mobile, desktop or web-based applications and user interfaces for different individuals. These applications and user interfaces may provide access to the digital platforms hosted by the cloud platform. In an embodiment, the methods and systems comprise a mobile application and user interface for sensor module users or patients, a mobile application and user interface for caregivers, a web-based application for clinicians, and a desktop or web-based application and user interface for researchers. These applications and user interfaces are further described herein.

[0123] In an embodiment, the mobile application and user interface for users comprises a settings page, a home page, a reminder page, a game page, and / or a virtual community page. A step-by-step guide may be provided for first-time users to instruct users on how to use the mobile application effectively, how to connect or pair sensor modules with the computing device, how to establish notifications, and how to navigate the mobile application’s features. The mobile application for users may further comprise an emergency alert feature to enable users to easily contact caregivers or clinicians and automatically transmit recent recorded sensor data to clinicians in emergencies. The user interface for users mayfurther comprise accessibility features such as voice commands for hands-free operation, high-contrast modes and colour blindness options, and text-to-speech support.

[0124] The user settings page enables the management of personal information such as weight, height, age, sex, and other related characteristics. Users may also view, add, delete or edit historical records of symptoms, including the dates, times and severities of symptoms. Symptom records may be related to specific diseases, disorders and conditions. In an embodiment, the records relate to Parkinson’s disease. Symptom records are presented as graphical visualizations, such as line charts or bar graphs, to depict longitudinal trends and enable users to monitor symptom progression.

[0125] The user settings page further enables users to view and edit medication history, wherein users may view one or more lists of medications that have been prescribed, including the dosage, frequency, and start and stop dates. Users may edit or remove medications in accordance with clinician advice. Medication history may further comprise information related to side effects, changes in dosages and clinician notes. Users may also link symptoms to specific medications to identify how one or more medications may affect the user’s symptoms.

[0126] The user settings page enables users to (e.g. selectively) export and share historical symptom records and medication data with clinicians or caregivers. Records and data may be exported in different formats, including for example, CSV or PDF formats. In an embodiment, user may selectively indicate which data / data types are to be sent.

[0127] The user settings page further enables users to monitor and control various features related to the sensor modules, the accessory modules or the computing device. The user settings page displays the Bluetooth connectivity status, Bluetooth address, universal unique identifier (UUID), power status and memory storage of a user’s one or more sensor modules, accessory modules or computing device. The user settings page enables the connection of the computing device and multiple sensor modules, with support for simultaneously connecting multiple sensor modules. In an embodiment, up to eight sensor modules may be connected, with support for simultaneously connecting two sensor modules. The user settings page enables users to search for, pair, and store information for newly connected sensor modules and the computing device. The settings page further enables users to test the one or more feedback features of the one or more sensor modules.

[0128] In an embodiment, the user home page enables users to monitor each of the one or more sensor modules. In an embodiment, each sensor module may be selected using a dropdown feature. The user home page displays real-time sensor data for the IMU of each sensor module. In an embodiment, the sensor data is displayed as line plots for each of the components (accelerometer, gyroscope ormagnetometer) of each IMU. The user home page may further display historical sensor data from each of the one or more sensor modules’ storage using one or more suitable plot types, such as a bar plot.

[0129] In an embodiment, the user reminder page enables users to view, add, modify or delete medication reminders, with customizable options for time of day reminders, frequency of reminders (e.g., daily or weekly), and the method of receiving medication alerts (e.g., haptic, visual or auditory). The user reminder page also provides an appointment calendar that synchronizes with one or more appointment schedules of one or more clinicians and further provides reminders of upcoming appointments. The user reminder page may provide activity reminders and suggest daily activities, including reminders for standing up, completing specific exercises or games via the exercise and rehabilitation platform, resuming exercises or games that are incomplete. The user reminder page may further provide Al-based suggestions for new exercises to be performed either alone or with caregivers based on the user’s symptoms. The user reminder page may enable users to add, remove, or replace reminders from a calendar, which may synchronize with external calendars.

[0130] In an embodiment, the user game page enables users to access, add or purchase exercises or games available via the exercise and rehabilitation platform, wherein the exercises or games integrate with one or more module sensors for real-time sensor data collection from the one or more body parts to which one or more sensor modules are coupled. The user game page is configured to display, for each exercise or game, one or more of: a dashboard with exercise, diet, or nutrition suggestions; warnings related to potential conflicts with current medications or health concerns based on the cloud platform’s machine learning analyses; a graphical or animation-based depiction of the exercise or game with step-by-step guidance; one or more exercise calendars, exercise suggestions or training progression data; game ranking and statistics, such as calories burned, blood pressure, ECG, IMU plots, time, and exercise duration; and historical data related to previously completed exercises or games, including the associated sensor data. The user game page may also be configured to enable users to access, add or purchase cognitive exercises or games to promote cognitive stimulation for the user. Cognitive exercises or games may include memory training exercises, puzzle solving games, brain fitness challenges, and attention and focus-enhancing activities. The cognitive exercises or games may further integrate real-time sensor data collection to enable a holistic understanding of both physical and cognitive progress.

[0131] In an embodiment, the user virtual community page provides access to one or more community forums, online meeting features, chat rooms, digital marketplaces and advertisements, and personalized recommendations. The one or more community forums are configured to enable users to interact, share experiences, and discuss challenges or progress with other patients, caregivers, orresearchers. The online meeting features may comprise integration with external applications, such as Zoom, for online video meetings between users and clinicians, enabling remote consultations and support. The chat rooms enable real-time communication between patients, caregivers, and clinicians to discuss issues, share advice, and provide social support. The digital marketplace may be configured to enable advertisement of personal items, rehabilitation programs, and rehabilitation devices, wherein users may browse and purchase or otherwise interact with vendors of relevant products or services. The personalized recommendations may comprise personalized suggestions for therapy games based on user preferences and symptoms, relevant educational resources such as webinars, or relevant social communities for users to interact.

[0132] In an embodiment, the mobile application and user interface for caregivers comprises a dashboard, a medication reminders and monitoring feature, a health monitoring and data access feature, an activity and exercise reminder feature, and a clinician communication feature. The caregiver user interface is configured to enable a caregiver to monitor a user’s health status, ensure medication adherence and provide support for the user’s activities.

[0133] In an embodiment, the caregiver dashboard presents a user / patient overview comprising a summary of the user’s current health, including real-time symptom metrics, sensor data related to physiological and biomechanical characteristics, and medication adherence. The caregiver dashboard further presents alerts and notifications for missed medications, abnormal symptoms, or required user activities. The caregiver dashboard further presents a user’s historical and current symptom status as graphical visualizations such as a charts or bar plots for monitoring symptom progress.

[0134] In an embodiment, the medication reminders and monitoring feature of the caregiver user interface enables caregivers to monitor and receive alerts related to a user’s missed medications, wherein caregivers may adjust medication schedules, add reminders, or contact the user about overdue medications. Caregivers may also view a history of the user’s medications, including dosage changes, potential side effects, and the user’s adherence to a prescribed schedule.

[0135] In an embodiment, the health monitoring and data access feature of the caregiver user interface provides enables caregivers to view real-time sensor data generated by the user’s one or more sensor modules and historical data related to symptom trends. Caregivers may also view symptom metrics and medication histories to identify relationships between symptoms and medication adjustments, enabling the caregiver to inform a clinician of potential concerns.

[0136] In an embodiment, the activity and exercise reminders feature of the caregiver user interface enables caregivers to set daily reminders for exercises, therapy games, or physical activities for a user,wherein Al-based suggestions are provided to adjust reminders based on the user’s symptoms and progress. Caregivers may also monitor records of completed exercises or games, along with performance data and statistics, such as the calories burned and time spent by the user in relation to each exercise or game.

[0137] In an embodiment, the clinician communication feature of the caregiver user interface enables caregivers to access a user’s appointment calendar, wherein the calendar synchronizes with one or more appointment schedules of one or more clinicians and further provides reminders of upcoming appointments to the caregiver and user.

[0138] In an embodiment, the web-based application and user interface for clinicians comprises a patient monitoring dashboard, a treatment and medication management feature, a data sharing feature, an Al-based disease progression prediction feature, and an appointment and calendar management feature. The clinician user interface is configured to facilitate diagnoses, user / patient monitoring, treatment management, and communication with caregivers or other clinicians.

[0139] In an embodiment, the patient monitoring dashboard of the clinician user interface presents a user / patient summary, wherein clinicians may have access to a user’s current health status, including information about symptom severity, medication adherence, and real-time sensor data. The patient monitoring dashboard presents historical data of a user, including past symptoms, medications, and progress trends. The patient monitoring dashboard further provides alerts related to significant changes in a user’s health, missed medications, or abnormal symptoms that require urgent attention.

[0140] In an embodiment, the treatment and medication management feature of the clinician user interface enables clinicians to view or modify a user’s medication history, treatment plans, and side effects. Clinicians may prescribe or adjust medications and may recommend new therapies, medication adjustments, or exercises directly through the clinician user interface.

[0141] In an embodiment, the data sharing feature of the clinician user interface enables clinicians to directly communicate with caregivers to provide guidance on symptom management and medication adherence. Clinicians may also share user / patient data with other clinicians or specialists involved in the user’s care, wherein the user / patient data may comprise real-time health and symptom metrics, symptom trends, and medication history.

[0142] In an embodiment, the Al-based disease progression prediction feature of the clinician user interface provides clinicians with recommendations personalized for a user / patient and disease progression insights based on the cloud platform’s analyses of the user’s sensor data and metrics.

[0143] In an embodiment, the appointment and calendar management feature of the clinician user interface enables clinicians to schedule appointments that integrate with a user’s calendar and provides clinicians with reminders for upcoming appointments, medical tests, or check-ins with other clinicians or specialists.

[0144] In an embodiment, the desktop / web-based application and user interface for researchers comprises a research dashboard, a data collection and management feature, a data preprocessing and filtering feature, a machine learning and Al integration feature, a clinical study integration feature, a collaborative tools feature, a patient group insights feature, and a cloud integration feature. The researcher user interface is configured to enable data collection, data analysis, and researcher collaboration for advancing scientific understanding of Parkinson’s disease and other chronic conditions. The researcher user interface enables researchers to ensure data integrity, preprocess raw sensor data, apply filters to extract meaningful metrics, and securely share metrics with clinicians or other healthcare providers. The researcher user interface may further support machine learning features for personalized treatment recommendations and provide seamless collaboration across research teams.

[0145] In an embodiment, the research dashboard of the researcher user interface presents an overview of aggregated data across multiple users / patients, including symptom progression trends, medication adherence and efficacy, and health outcomes based on real-time and historical data collected from sensors. The research dashboard enables patient group monitoring and comparison of patient groups based on treatment groups, age groups, and symptom severity. The research dashboard further enables researchers to view real-time health data from users’ sensor modules, accessory modules or other monitoring devices, wherein researchers may continuously monitor sensor data during therapy exercises or daily living activities.

[0146] In an embodiment, the data collection and management feature of the researcher user interface enables researchers to access and analyze users’ historical data, including symptom progression, medication histories, and treatment responses. Researchers may download user data in various formats, such as CSV, PDF, or JSON for external analysis, preprocessing, or publication. The data collection and management feature ensures that all sensor data and metrics are timestamped and securely stored in the one or more databases of the cloud platform to maintain data integrity and prevent tampering. Anonymization protocols are implemented for user data to protect confidentiality during analysis.

[0147] In an embodiment, the data preprocessing and filtering feature of the researcher user interface enables researchers to apply specific filters, such as bandpass filters or Kalman filters, to users’ rawsensor data, enabling researchers to extract relevant metrics for symptoms such as tremor severity, gait irregularities, and other symptoms related to Parkinson’s disease or other diseases, disorders or conditions. Researchers may define and extract customized metrics from the sensor data based on specific symptoms and behaviours observed during therapy exercises or daily activities.

[0148] In an embodiment, the machine learning and Al integration feature of the researcher user interface integrates data from users’ sensor modules to train machine learning models for recommending therapy exercises or games, cognitive activities, and personalized rehabilitation plans for patients. The machine learning and Al integration feature further integrates historical user data to develop machine learning models configured to suggest appropriate medications and dosage adjustments based on users’ current and historical symptom metrics. Researchers may apply transfer learning on labeled data to fine-tune models for specific symptoms or conditions to enhance model accuracy for individual users. Raw and preprocessed data may be used to train predictive models that aid in patient management and clinical decision-making, including symptom progression and treatment efficacy data.

[0149] In an embodiment, the clinical study integration feature of the researcher user interface enables researchers to monitor study progress and protocol compliance, ensure data integrity across different study locations, and ensure that research protocols are consistently followed. The clinical study integration feature further enables researchers to manage patient recruitment, obtain consent, and monitor enrollment in clinical trials and studies to simplify the participant enrollment process and ensure that ethical standards are satisfied.

[0150] In an embodiment, the collaborative tools feature of the researcher user interface enables data sharing among researchers, clinicians, and other collaborators involved in clinical studies and provides secure access controls to maintain confidentiality of user data. The collaborative tools feature enables researchers to share findings and recommendations directly with clinicians or other healthcare providers to assist in real-time clinical decision-making. The collaborative tools feature further provides a feedback loop, wherein researchers may provide feedback to clinicians and caregivers based on data collected during clinical studies to improve treatment strategies and management plans.

[0151] In an embodiment, the patient group insights feature of the researcher user interface enables cross-group comparisons, wherein researchers may compare symptom progression, treatment efficacy, and health outcomes across different patient groups, facilitating deeper insights into therapeutic interventions. The patient group insights feature provides visual data representation tools, including heatmaps, regression plots, and cohort comparison charts to enable researchers to identify trends, correlations, and specific aspects of patient treatment requiring additional attention.

[0152] In an embodiment, the cloud integration feature of the researcher user interface provides secure cloud storage of users’ raw sensor data and preprocessed user data and metrics to enable convenient access and long-term storage in the one or more databases of the cloud platform. Suitable cloud platforms for reliable data storage may include Amazon Web Services, Google Cloud or similar cloud platforms. The cloud integration feature synchronizes data across different study locations and time zones, ensuring that metadata such as timestamps and user / patient identifiers are consistent and aligned.

[0153] A feature of any method herein has an equivalent apparatus aspect such as a computing device, a system or a computer program product and vice versa.

[0154] Practical implementation may include any or all the features described herein. These and other aspects, features and various combinations may be expressed as methods, apparatus, systems, means for performing functions, program products, and in other ways, combining the features described herein. A number of embodiments have been described. Nevertheless, it will be understood that various modifications can be made without departing from the spirit and scope of the processes and techniques described herein. In addition, other steps can be provided, or steps can be eliminated, from the described process, and other components can be added to, or removed from, the described systems. Accordingly, other embodiments are within the scope of the following claims.

[0155] Throughout the description and claims of this specification, the word “comprise” and “contain” and variations of them mean “including but not limited to” and they are not intended to (and do not) exclude other components, integers or steps. Throughout this specification, the singular encompasses the plural unless the context requires otherwise. In particular, where the indefinite article is used, the specification is to be understood as contemplating plurality as well as singularity, unless the context requires otherwise.

[0156] Features, integers, characteristics, compounds, chemical moieties or groups described in conjunction with a particular aspect, embodiment or example of the invention are to be understood to be applicable to any other aspect, embodiment or example unless incompatible therewith. All the features disclosed herein (including any accompanying claims, abstract and drawings), and / or all the steps of any method or process so disclosed, may be combined in any combination, except combinations where at least some of such features and / or steps are mutually exclusive. The invention is not restricted to the details of any foregoing examples or embodiments. The invention extends to anynovel one, or any novel combination, of the features disclosed in this specification (including any accompanying claims, abstract and drawings) or to any novel one, or any novel combination, of the steps of any method or process disclosed.

Claims

ClaimsWhat is claimed is1. A method of monitoring biomechanical and physiological metrics of a user and providing feedback to the user, the method comprising:receiving, by a computing device, (i) one or more first biomechanical time series metrics or sensor module-originated inertial measurement unit (“IMU”) sensor data related to one or more body parts of the user and (ii) one or more physiological time series metrics or accessory sensor data, wherein:the computing device comprises a communication unit configured to receive sensor data and metrics, at least one processor, two or more dual antenna ultra-wideband (“UWB”) anchors, and at least one storage device storing instructions executable by the at least one processor to perform the method;the one or more first biomechanical time series metrics are received from one or more sensor modules, each sensor module coupled to the user and comprising a sensor module IMU configured to generate sensor module-originated IMU sensor data responsive to body movement of the one or more body parts for generating the one or more first biomechanical time series metrics, one or more sensor processors configured to determine whether to provide real-time feedback to the user by the respective sensor module, a UWB tag, and a feedback actuator; andthe one or more physiological time series metrics are received from one or more accessory modules, each accessory module comprising one or more accessory sensors configured to generate accessory sensor data used to generate the one or more physiological time series metrics;generating, by the computing device, timestamped three-dimensional (“3D”) position data of each of the one or more sensor modules based on communication between the UWB tag of each of the one or more sensor modules and the UWB anchors;synchronizing and processing, by the computing device, the one or more first biomechanical time series metrics with the 3D position data of each of the one or more sensor modules to generate one or more refined biomechanical time series metrics for each of the one or more body parts;determining, by the computing device, whether to provide real-time feedback to the user in response to analysis of one or more of the one or more first or refined biomechanical time series metrics or physiological time series metrics, the analysis determining an occurrence of or quality of one or more predefined physiological events and one or more relevant sensor modules associated therewith for providing corrective feedback; andcommunicating with one or more relevant sensor modules identified by the analysis to provide the feedback via a respective feedback actuator.

2. The method of claim 1, wherein:the computing device is coupled to the user; andthe computing device further comprises a local IMU configured to generate computing deviceoriginated IMU sensor data responsive to body movement of the one or more body parts for generating and / or improving accuracy of the one or more first biomechanical time series metrics.

3. The method of claim 1 or claim 2, further comprising:determining, by one or more sensor processors of each respective sensor module, whether to provide real-time feedback to the user in response to analysis of one or more of the one or more first biomechanical time series metrics, the analysis determining an occurrence of or quality of one or more predefined physiological events; andbased on the sensor processor determination to provide the feedback, communicating with the feedback actuator of the respective sensor module to provide the feedback for a predefined duration or responsive to further analysis of additional one or more of the first biomechanical time series metrics associated with the occurrence of or quality of one or more predefined physiological events.

4. The method of any one of claims 1 to 3, wherein the feedback actuator is a haptic actuator, the eedback is haptic feedback, and the feedback is provided for a predefined duration or responsive to urther analysis of additional one or more of the first or refined biomechanical time series metrics or physiological time series metrics associated with the occurrence of or quality of one or more predefined physiological events.

5. The method of any one of claims 1 to 4, wherein:the one or more first biomechanical time series metrics for the respective sensor module comprise the IMU sensor data for processing by the computing device; orthe IMU sensor data is processed by the respective sensor module to define the one or more first biomechanical time series metrics for the respective sensor module.

6. The method of any one of claims 1 to 5, wherein:the one or more physiological time series metrics for the respective accessory module comprise the accessory sensor data for processing by the computing device; orthe accessory sensor data is processed by the respective accessory module or by one of the one or more sensor modules to define the one or more physiological time series metrics.

7. The method of any one of claims 1 to 6, further comprising identifying a respective body part to which each respective one of the one or more sensor modules is coupled, the respective body part identified from an analysis of the IMU sensor data of each respective sensor module and reference IMU sensor data comprising signatures indicative of predefined body parts, wherein data identifying the respective body part to which a sensor module is coupled may be transmitted to the computing device by the respective sensor module to facilitate the analysis determining the one or more relevant sensor modules associated with an occurrence of or quality of one or more predefined physiological events for providing corrective feedback.

8. The method of any one of claims 1 to 7, wherein the computing device is configured as a base station including one or more rechargeable base power sources and at least one base / sensor adapter, each base / sensor adapter configured to receive a sensor module for i) charging a rechargeable sensor power source of the sensor module and / or ii) for communicating between the base station and the sensor module.

9. The method of any one of claims 1 to 8, wherein:the one or more base rechargeable power sources charge the rechargeable power source of each sensor module received by a base / sensor adapter of the base station; andthe UWB tag of each sensor module received by a base / sensor adapter is configured to be used by the base station as an additional UWB anchor antenna in addition to the two or more dual antenna UWB anchors of the base station.

10. The method of any one of claims 1 to 9, wherein the I MU sensor data for each respective sensor module comprises time series measurements of vibration, acceleration, velocity, angular velocity and orientation for the respective sensor module.

11. The method of any one of claims 1 to 10, wherein:each of the one or more sensor modules further comprises one or more sensor flash memories configured to store the IMU sensor data and the one or more first biomechanical time series metrics of the respective sensor module and instructions for controlling the sensor module; andthe one or more sensor flash memories are further configured to store accessory sensor data generated by the one or more accessory modules and instructions for controlling the one or more accessory modules.

12. The method of any one of claims 1 to 11, wherein:the one or more first biomechanical time series metrics comprise one or more biomechanical characteristics of the one or more body parts, including heart rate, swallowing activity, vocal activity, gait, movement and orientation;the one or more refined biomechanical metrics comprise the one or more first biomechanical metrics having improved accuracy and one or more position characteristics of the one or more body parts, including position, pose, posture, pathlength, trajectory and range of motion; andthe one or more physiological time series metrics comprise physiological characteristics of muscle activity, fatigue, neural activity, blood oxygen saturation, pulse, blood pressure, respiration, stress, sleep, speech, temperature or other characteristics determined by biological, chemical, electrical or optical indicators.

13. The method of any one of claims 1 to 12, wherein:the occurrence of a predefined physiological event comprises an onset or cessation of a clinical symptom or an indication that a first or refined biomechanical metric or physiological metric complies with or deviates from one or more reference metrics; andthe quality of a predefined physiological event comprises a severity of a clinical symptom or an extent to which a first or refined biomechanical metric or physiological metric complies with or deviates from one or more reference metrics.

14. The method of any one of claims 1 to 13, wherein:the analysis uses one or more predefined thresholds determined using one or more biomechanical or physiological reference metrics generated from historical metrics of the user or a plurality of other users, model biomechanical or physiological metrics recorded by one or more clinicians, therapists, researchers or instructors using the one or more sensor modules and other model metrics derived from suitable data sources; andthe reference metrics are obtained from one or more individuals having no symptoms, individuals having a known type, severity or frequency of one or more symptoms or individuals recording model metrics comprising one or more target positions, orientations, poses, postures, pathlengths, trajectories, ranges of motion, movements or exercises involving one or more body parts.

15. A method of monitoring biomechanical and physiological metrics of a sensor module user and providing feedback to the sensor module user, the method comprising:receiving, by a cloud platform providing cloud services, sensor data and metrics of the sensor module user from a computing device, wherein the cloud platform comprises one or more processors and one or more databases storing instructions that when executed by the one or more processors configures the cloud platform to provide the cloud services;processing, by the cloud platform, the sensor data and metrics using machine learning algorithms to one or more of:extract symptom metrics from the sensor data and metrics for real-time analysis;predict disease progression;detect anomalies using anomaly detection algorithms;make personalized recommendations, including physical therapy exercises, cognitive exercises, medication adjustments, and health products and services; orprovide clinicians with data-driven insights related to one or more sensor module users, including treatment efficacy, therapy efficacy, recommended treatment parameters, and recommended exercise parameters; andproviding, by the cloud platform, one or more digital platforms accessible by sensor module users, clinicians, instructors, researchers, or caregivers, the digital platforms configured to:enable viewing and sharing of sensor data and metrics, real-time and historical extracted symptom metrics, disease progression predictions, personalized recommendations and data-driven treatment insights; andprovide virtual health support services comprising artificial intelligence-based health guidance, online consultations with clinicians and self-assessment tests for sensor module users.

16. The method of claim 15, wherein:the sensor data and metrics comprise IMU sensor data, accessory sensor data, 3D position data, one or more first biomechanical metrics, one or more refined biomechanical metrics and one or more physiological metrics related to one or more body parts of the sensor module user;the one or more first biomechanical time series metrics comprise one or more biomechanical characteristics of the one or more body parts, including heart rate, swallowing activity, vocal activity, gait, movement and orientation;the one or more first biomechanical time series metrics are generated by one or more sensor modules, each sensor module coupled to the sensor module user and comprising a UWB tag and an IMU, the IMU configured to generate IMU sensor data responsive to body movement of the one or more body parts for generating the one or more first biomechanical time series metrics;the IMU sensor data for each respective sensor module comprises time series measurements of vibration, acceleration, velocity, angular velocity and orientation for the respective sensor module;the 3D position data comprises timestamped information about a position of each of the one or more sensor modules in 3D space based on communication between the UWB tag of each sensor module and two or more dual antenna UWB anchors of the computing device, wherein the computing device synchronizes and processes the one or more first biomechanical time series metrics with the 3D position data of each of the one or more sensor modules to generate the one or more refined biomechanical metrics;the one or more refined biomechanical metrics comprise the one or more first biomechanical metrics having improved accuracy and one or more position characteristics of the one or more body parts, including position, pose, posture, pathlength, trajectory and range of motion;the one or more physiological time series metrics comprise physiological characteristics of muscle activity, fatigue, neural activity, blood oxygen saturation, pulse, blood pressure, respiration, stress, sleep, speech, temperature or other characteristics determined by biological, chemical, electrical or optical indicators; andthe one or more physiological time series metrics are generated by one or more accessory modules, each accessory module comprising one or more accessory sensors configured to generate accessory sensor data used to generate the one or more physiological time series metrics.

17. The method of claim 15 or claim 16, wherein the sensor data and metrics further comprise health-related data of the sensor module user.

18. The method of claim 17, wherein the health-related data comprises health records and timestamped health diary data related to tracking medication, side effects, exercise, diet, sleep, energy levels and mood.

19. The method of any one of claims 15 to 18, further comprising providing, by the data encryption module, end-to-end encryption, secure access controls and multi-factor authentication.

20. The method of any one of claims 15 to 19, further comprising storing, by the one or more databases, the sensor data and metrics and outputs generated by processing the sensor data and metrics.

21. The method of any one of claims 15 to 20, wherein the machine learning algorithms used for data analysis include neural networks, decision trees, and support vector machines.

22. The method of any one of claims 15 to 21, wherein the digital platforms comprise:a symptom monitoring platform configured to:enable viewing real-time symptom metrics, historical records of disease progression, and generating reports; andinclude features for automatic detection and alerting of anomalies or new or worsening symptoms;a treatment management platform configured to provide medication and event alerts, facilitate personalized medication management, make disease progression predictions, and recommend or schedule clinician appointments;an exercise and rehabilitation platform, wherein:the exercise and rehabilitation platform is configured to provide access to exercises and therapy games involving real-time tracking and real-time feedback using the computing device, one or more sensor modules and optionally one or more accessory modules; andthe exercises and therapy games are created by clinicians, therapists, and instructors using the computing device and one or more sensor modules to record model movements and exercises; anda virtual community platform for sensor module users, caregivers, clinicians, therapists and instructors to interact, the virtual community platform comprising forums, online meeting capabilities, chat rooms and a digital marketplace.

23. The method of any one of claims 15 to 22, wherein the digital platforms are configured to provide ne or more interfaces to communicate one or more applications comprising:a web-based clinician application configured to:enable clinicians to access and monitor sensor user data; andfacilitate treatment and medication management, data sharing with caregivers and other clinicians, appointment management, and artificial intelligence-based disease progression insights;a web-based instructor application configured to enable instructors, clinicians and therapists to:create exercises and therapy games by recording model movements and exercises using the computing device and one or more sensor modules;monitor the performance of sensor users engaging with the exercises and therapy games; andprovide access to sensor user sensor data and metrics for analysis and adjustment of exercise programs;a mobile or web-based caregiver application configured to enable caregivers to access and monitor a sensor user's data, including real-time symptom metrics and medication monitoring; ora web-based researcher application configured to enable researchers to access, share and analyze sensor user data for research purposes, collaborate on research projects, and enable clinical study integration.

24. The method of claim 22 or claim 23, wherein:the exercises and therapy games are based on the creation of zones comprising virtual 3D spaces;the zones comprise model biomechanical metrics created by one or more clinicians, therapists or instructors by performing one or more predefined exercises comprising predefined positions, orientations, poses, postures, pathlengths, trajectories or ranges of motion of one or more relevant body parts using one or more sensor modules worn on the one or more relevant body parts and the computing device;the performance of the predefined exercise is recorded by the I MU sensors and by the communication between the UWB anchors of the computing device and the UWB tags of each of the one or more sensor modules worn during the performance to generate model IMU sensor data and model 3D position data comprising a plurality of points in 3D space;responsive to the predefined exercise comprising a predefined trajectory, a virtual circle with a predefined radius is created around each point to construct a cylindrical zone, the zone comprising model biomechanical metrics;25. A computing device comprising at least one processor and at least one storage device storing instructions executable by the at least one processor to perform the method according to any preceding claim.

26. A system for monitoring biomechanical and physiological metrics and for guiding movements, omprising:one or more sensor modules configured to be worn one or more body parts of a user, each sensor module comprising an IMU configured to generate IMU sensor data, a UWB tag, a feedback actuator, one or more processors configured to generate biomechanical metrics from the IMU sensor data, activate the haptic actuator, and control an accessory module, a wireless communication unit configured to communicate with a base station or a user device, one or more rechargeable power sources, an adapter configured to operably connect to an accessory module or a base station, and one or more flash memories configured to store sensor data, 3D position data, metrics and instructions;a base station comprising two or more dual-antenna UWB anchors for communicating with the UWB tag of the one or more sensor modules, one or more base adapters configured to operably receive and charge the one or more power sources of each of the one or more received sensor modules, a wireless communication unit configured to communicate with the one or more sensor modules and a user device, one or more processors for processing sensor data, 3D position data and metrics, one or more rechargeable power source and one or more flash memories for storing sensor data, 3D position data, metrics and instructions;a user device comprising a wireless communication unit configured to communicate with the one or more sensor modules and the base station, a network adapter configured to communicate with a cloud platform, a mobile or web-based user application, one or more processors configured to run the user application, one or more flash memories and a display to present the user application to the user;a cloud platform configured to provide cloud services, the cloud platform comprising a data ingestion module for receiving the sensor data, 3D position data and metrics from theuser device, one or more cloud processors configured to apply machine learning algorithms to generate inferences based on the sensor data, 3D position data, metrics and user health-related data; a data encryption and security module, and one or more databases for storing instructions, reference data, sensor data, 3D position data, metrics, and inferences.

Images