Ai-based patient engagement and progress tracking system for enhanced physiotherapy in a gaming environment, eliminating the need for wearables or additional sensors

Abstract

The present invention relates to an AI-based physiotherapy system (100) and method for enhancing patient engagement and rehabilitation outcomes by integrating real-time body tracking with an interactive gaming environment. The system employs a mobile device with an inbuilt camera and an AI-powered body tracking module (101) to capture patient movements and track 33 anatomical joints. A cloud server (109) stores physiotherapist-annotated postures, enabling comparison and generating feedback. An occlusion-aware correction algorithm reconstructs hidden joints in side postures, improving accuracy without requiring wearable devices or external sensors. A gaming environment module (102) powered by UNITY dynamically adjusts gameplay based on performance, while a feedback module (103) provides color-coded indicators (green, red, orange) for real-time posture guidance. The invention includes a self-examination mode (107) for independent screening and a doctor monitoring module (108) for remote supervision. Progress reports generated by a monitoring module (104) are securely stored in the cloud, ensuring accountability, scalability, and improved therapeutic outcomes. Published with figure 1.

Description

Title: AI-BASED PATIENT ENGAGEMENT AND PROGRESS TRACKING SYSTEM FOR ENHANCED PHYSIOTHERAPY IN A GAMING ENVIRONMENT, ELIMINATING THE NEED FOR WEARABLES OR ADDITIONAL SENSORSFIELD OF INVENTION

[0001] The present invention relates to the field of biomedical engineering and healthcare technology, and more particularly to systems and methods for AI- assisted physiotherapy and rehabilitation. The invention employs Al-powered body tracking, real-time gaming integration, and cloud-based feedback mechanisms to improve patient engagement and recovery outcomes. In one aspect, the invention also utilizes techniques from computer vision and image processing applied to video frames captured by a mobile device camera to extract joint positions and assess posture accuracy.BACKGROUND OF THE INVENTION

[0002] Physiotherapy is a critical component of the rehabilitation process for patients recovering from injuries, surgeries, or managing chronic conditions. Traditional physiotherapy involves a series of prescribed exercises aimed at restoring movement, strength, and function. However, these exercises can often be monotonous and repetitive, leading to decreased patient motivation and adherence. This lack of engagement can result in suboptimal recovery outcomes, as patients may not perform the exercises consistently or correctly.

[0003] Moreover, physiotherapists face significant challenges in providing individualized attention to each patient. In conventional settings, therapists are typically restricted to handling one patient at a time, which limits their ability to monitor multiple patients simultaneously. This constraint not only reduces the efficiency of therapeutic care but also impacts the accessibility of physiotherapy services, especially in regions with limited healthcare resources.

[0004] To overcome these drawbacks, many digital health technologies have emerged in the market. One example is described in the paper "Description Of A Self-Adaptive Architecture For Upper-Limb Rehabilitation" by Heloir et al., published on December 31, 2014. This paper presents a natural and intuitive user interface architecture that uses a consumer-range 3D hand capture device to interactively edit objects in 3D space. While running, the system monitors the user's behaviors and performance in order to maintain an up-to-date model of the user. This model then drives the real-time re-arrangement and re-parameterization of a rule-based system that controls the interaction. A preliminary user study defined the initial parameters of this self-adaptive system. While well-suited to upper-limb rehabilitation, the system still requires specialized devices and additional hardware for monitoring, limiting its scope and accessibility.

[0005] However, systems like the one described by Heloir et al. often require additional devices to monitor patients, which can be cumbersome and costly. These systems also primarily focus on upper-limb rehabilitation and may not address the comprehensive needs of physiotherapy for other body parts or conditions. The need for specialized equipment and the potential limitations in scope highlight the necessity for a more integrated, versatile, and engaging solution.

[0006] The prior art described in US 9, 107,586 B2 outlines a mobile system for fitness monitoring that includes a telephone equipped with sensors to capture fitness or vital sign data. While this system offers a convenient method to monitor health metrics, it has significant drawbacks. The reliance on a mobile phone's built-in sensors limits the accuracy and comprehensiveness of the data collected, as these sensors are not specifically designed for physiotherapy tracking. This lack of tailored rehabilitation functionality and the dependency on continuous connectivity through sensors also pose challenges in accessibility and therapeutic consistency.

[0007] The prior art described in US 2021 / 0162262 Al pertains to a rehabilitation system that employs a wearable device to measure rehabilitation exerciseinformation and a user electronic device to drive an avatar training program based on this data. While this system enhances rehabilitation by providing a customized exercise program, it has notable drawbacks. The dependence on wearable devices may introduce limitations in the accuracy and scope of movement tracking, particularly for exercises requiring precise monitoring of multiple joints and muscle groups. Furthermore, managing multiple devices can be cumbersome for users, reducing overall engagement.

[0008] The advent of digital health technologies and artificial intelligence (Al) has opened new avenues for enhancing physiotherapy. Al-powered systems have the potential to offer real-time monitoring, personalized feedback, and adaptive exercise programs, thereby improving patient outcomes. By integrating Al with a gaming environment, this invention aims to address the key challenges of traditional physiotherapy. The gamification of physiotherapy exercises introduces an element of fun and engagement, transforming routine exercises into interactive activities. This approach can significantly boost patient motivation and adherence, leading to better rehabilitation results.

[0009] Furthermore, the proposed system utilizes a standard mobile device equipped with a built-in camera to capture patient movements. An Al-powered mobile application processes the captured video in real-time, mapping 33 body joints. Physiotherapist-annotated reference postures are securely stored on a cloud server (e.g., Microsoft Azure), enabling accurate comparison and feedback. The results are displayed through the mobile screen or a connected television, which acts as the output device, while the gaming environment is powered by a UNITY engine integrated within the app. In particular, the proposed system maps 33 body joints as dots using a mobile camera and employs a novel occlusion-aware correction algorithm to reconstruct hidden joints in side postures, reducing jitter and improving accuracy. Reference postures, annotated by physiotherapists and stored in the cloud, serve as benchmarks for validating movements. Real-timeanalysis ensures patients perform exercises correctly, reducing the risk of injury and enhancing therapeutic effectiveness.

[0010] The system also generates comprehensive progress reports, empowering patients with data-driven insights into their rehabilitation journey. Reports include movement ranges, response times, and grading levels (A / B / C), as well as graphical indicators such as green (correct execution), red (incorrect), and red with orange center (partial completion) to provide intuitive feedback. This makes the system practical, motivating, and accessible even in home environments.

[0011] In addition to guided physiotherapy sessions, the present invention introduces a self-examination option that allows patients to perform an initial screening independently. By sitting in front of the camera and following a few guided exercises, the system measures the range of motion, rate of movement, and joint alignment. Based on these results, the system predicts whether the patient’s condition can be managed through continued exercises or if consultation with a physiotherapist or orthopaedic specialist is necessary. This feature is particularly useful for individuals uncertain about whether to seek physiotherapy, as it provides a reliable, Al-driven first-level assessment that can trigger timely professional intervention if required.

[0012] Post-surgery patients often struggle to attend physiotherapy centers regularly due to limited mobility or logistical constraints. Existing digital rehabilitation systems usually depend on therapists or intermediaries and rarely provide direct doctor oversight, creating a communication gap between patient and physician. This lack of direct monitoring reduces patient confidence and may delay timely medical intervention. The present invention addresses this issue by enabling doctors to remotely monitor incremental improvements, access patient reports through secure logins, and provide timely guidance. Patients, doctors, and therapists can all view the same reports, which fosters accountability, ensures error-freecommunication, and provides patients with a psychological boost by knowing their recovery is being directly supervised by their doctor.

[0013] In summary, the background of this invention highlights the limitations of traditional physiotherapy and prior digital health systems, and demonstrates how Al and gaming technologies, combined with sensor-free body tracking, occlusion- aware correction, self-examination, and direct doctor monitoring, can revolutionize the rehabilitation process. By making physiotherapy more engaging, accurate, personalized, and accessible, this invention aims to improve patient outcomes and overall quality of life.OBJECT OF THE INVENTION

[0014] With reference to the above background explanation, the present invention of Al-based patient engagement and progress tracking system and method with enhanced physiotherapy in a gaming environment to enhance patient engagement and adherence. Specifically, the invention has the following objectives to solve the limitations of the conventional systems.

[0015] The primary object of the present invention is to provide a physiotherapy system and method that enhances patient engagement, motivation, and therapeutic effectiveness by integrating Al -powered body tracking with an interactive gaming environment, while eliminating the need for additional sensors or wearable devices.

[0016] Another object of the invention is to deliver accurate and reliable posture assessment by mapping 33 body joints as dots and applying a novel occlusion- aware correction algorithm that reconstructs hidden joints in side postures, thereby overcoming limitations of conventional Al pose estimation systems.

[0017] A further object of the invention is to provide a self-examination option that enables patients to perform guided exercises independently, generating graphical reports with intuitive indicators of joint performance. This allows patients to identify whether they can continue rehabilitation exercises at home or requireconsultation with a physiotherapist or orthopaedic specialist, offering an Al-driven first-level screening tool.

[0018] Another object of the invention is to facilitate direct doctor monitoring of patient progress through secure cloud-based reporting, enabling doctors and physiotherapists to remotely supervise incremental improvements. This feature ensures error-free communication, fosters accountability, and provides patients with psychological assurance by knowing their recovery is being directly monitored by their healthcare provider.

[0019] Yet another object of the invention is to generate comprehensive progress reports, including joint angles, range of motion, response times, and grading, thereby empowering both patients and healthcare professionals with actionable data for rehabilitation planning.

[0020] An additional object of the invention is to ensure low-latency performance by employing lightweight Al model adaptation, enabling smooth real-time body tracking and feedback even with standard mobile internet connectivity.

[0021] Overall, the invention aims to provide a scalable, cost-effective, and motivating rehabilitation solution that bridges the shortcomings of traditional physiotherapy and prior art digital health systems, while delivering improved clinical reliability, patient confidence, and recovery outcomes.

[0022] Further object of the present application will be highly appreciated and be easily understood upon reading the detailed description taking into consideration the appended drawings.SUMMARY OF THE INVENTION

[0023] The present invention provides a physiotherapy system and method that enhances patient engagement, motivation, and rehabilitation outcomes byintegrating Al-powered real-time body tracking with an interactive gaming environment. The system requires only a mobile device equipped with a built-in camera, a dedicated mobile application, a cloud server for storing physiotherapist- annotated reference postures and progress reports, and an output display such as a mobile screen or a connected television. Importantly, the system operates without the need for additional sensors or wearable devices, reducing complexity and cost.

[0024] The mobile camera captures the patient’s movements, which are processed by the application’s body tracking module to map 33 anatomical joints as dots. A novel occlusion-aware correction algorithm reconstructs hidden joints in side postures, improving accuracy and reducing jitter. Correct postures stored in the cloud are used as benchmarks for comparison. Feedback is provided in real time through color-coded visual indicators (green for correct posture, red for incorrect posture, orange for partial completion) displayed alongside an interactive gaming environment powered by the UNITY engine, where gameplay dynamically adjusts to the patient’s performance.

[0025] The system also introduces a self-examination mode, allowing patients to perform guided exercises independently. The app generates reports showing movement sufficiency and response times, enabling patients to decide whether to continue home rehabilitation or seek consultation with a physiotherapist or orthopaedic specialist. A further embodiment supports direct doctor monitoring, whereby progress reports are securely stored in the cloud and accessed by healthcare providers through secure logins. This ensures error-free communication, fosters accountability, and provides patients with the psychological confidence that their recovery is being actively monitored by their doctor.

[0026] By leveraging standard mobile hardware, cloud integration, and AI- powered analysis, the invention achieves technical effects such as accurate posture detection in occluded scenarios, low-latency real-time performance, and scalable remote rehabilitation. Industrial applicability lies in hospitals, physiotherapyclinics, tele-rehabilitation platforms, and home-based recovery, offering a cost- effective and reliable alternative to traditional sensor-based systems.BRIEF DESCRIPTION OF DRAWINGSSo that the manner in which the above recited features of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may have been referred by embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments of this invention and are therefore not to be considered limiting of its scope, for the invention may admit to other equally effective embodiments. These and other features, benefits, and advantages of the present invention will become apparent by reference to the following text figure, with like reference numbers referring to like structures across the views, wherein:Figure 1 and Figure 2 depict an Al-based patient engagement and progress tracking system.Figure 3 presents the process flow chart of the proposed invention.Figure 4 shows the indication of colour change during the posture capturing.Figures 5 through 8 showcase different poses and their corresponding scores within distinct gaming environments, each with a unique background. This variety in settings enhances user engagement by providing a fresh experience and minimizing repetition.Figure 9 shows the report image.LIST OF REFERENCE NUMERALSDETAILED DESCRIPTION OF THE INVENTION

[0027] As required, detailed embodiments of the present invention are disclosed herein, however, it is to be understood that the disclosed embodiments are merely exemplary of the invention which may be embodied in various forms. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present invention in virtually any appropriately detailed structure. It is to be understood that other embodiments may be utilized, and structural changes may be made without departing from the scope of the invention.

[0028] All referenced methods are incorporated herein by reference in their entirety. Furthermore, where a definition or use of a term in a reference, which is incorporated by reference herein, is inconsistent or contrary to the definition of that term provided herein, the definition of that term provided herein applies and the definition of that term in the reference does not apply.

[0029] While certain aspects of conventional technologies have been discussed to facilitate disclosure of the invention, Applicants in no way disclaim these technical aspects, and it is contemplated that the claimed invention may encompass one or more of the conventional technical aspects discussed herein.

[0030] The present invention may address one or more of the problems and deficiencies of the prior art discussed above. However, it is contemplated that the invention may prove useful in addressing other problems and deficiencies in anumber of technical areas. Therefore, the claimed invention should not necessarily be construed as limited to addressing any of the particular problems or deficiencies discussed herein

[0031] In this specification, where a document, act or item of knowledge is referred to or discussed, this reference or discussion is not an admission that the document, act or item of knowledge or any combination thereof was at the priority date, publicly available, known to the public, part of common general knowledge, or otherwise constitutes prior art under the applicable statutory provisions; or is known to be relevant to an attempt to solve any problem with which this specification is concerned.

[0032] As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” include plural referents unless the content clearly dictates otherwise. As used in this specification and the appended claims, the term “or” is generally employed in its sense including “and / or” unless the context clearly dictates otherwise.

[0033] In one of the preferred embodiment, the invention discloses a physiotherapy system (100) for enhancing patient engagement and rehabilitation outcomes. The system comprises a mobile device with an inbuilt camera running a dedicated mobile application, and an Al-powered body tracking module (101) configured to capture and process anatomical joint movements from the captured video stream. A cloud server (109) stores physiotherapist-annotated reference postures and progress reports. A gaming environment module (102) configured to map patient movements into corresponding in-game actions and dynamically adjust gameplay based on performance. In one embodiment, the gaming environment module (102) powered by a UNITY engine translates the patient’s movements into corresponding in-game actions, while a feedback module (103) provides real-time visual indicators on posture accuracy. A progress monitoring module (104) generates rehabilitation reports including joint angles, movement ranges, and grading, whichare displayed via the mobile device screen or a connected television in a split-screen format. The body tracking module (101) maps anatomical joints as dots and applies an occlusion-aware correction algorithm to reconstruct hidden joints, further adapted by supervised calibration using physiotherapist-annotated exercise data and synthetic pose datasets. This ensures accuracy and low latency on mobile devices, thereby eliminating the need for wearable sensors. The system also incorporates a self-examination module (107) for independent screening and a doctor monitoring module (108) enabling healthcare providers to access reports through secure logins.

[0034] In another embodiment, the invention provides a method for physiotherapy engagement and progress tracking in a patient rehabilitation system. The method begins by selecting a physiotherapy activity on a mobile application, followed by capturing patient movements using the inbuilt camera of a mobile device. The captured movements are processed by an Al-powered body tracking module (101), which extracts joint positions and compares them with physiotherapist-annotated reference postures stored on a cloud server (109). The method includes mapping anatomical joints as dots and applying occlusion-aware correction for hidden joints. The Al model is adapted through supervised calibration using physiotherapist- annotated and synthetic pose datasets, employing angular deviation loss with gradient-based optimization for personalization and low-latency performance. Feedback is displayed in real time through visual indicators and an interactive gaming environment (102) on a split screen, motivating the patient through gameplay dynamics. A progress report is generated by the progress monitoring module (104), stored securely in the cloud server, and made accessible to both patients and healthcare providers. The method further supports a self-examination mode (107) for initial independent assessment and a doctor monitoring mode (108) for remote supervision and guidance.

[0035] The present invention discloses a system and method for enhancing physiotherapy through the integration of Al-powered body tracking with an interactive gaming environment. The system operates using a mobile deviceequipped with an inbuilt camera, which acts as the primary input device. A dedicated mobile application processes the video stream using an Al algorithm configured to track 33 anatomical joints of the patient’s body. For each physiotherapy-assigned activity, such as the Cat Cow Pose or Bird Dog Pose, the algorithm selects the relevant joints for monitoring. For example, in the Cat Cow Pose, the spine, hips, and shoulders are analyzed, while in the Bird Dog Pose, shoulders, hips, and knees are primarily tracked.

[0036] The captured joint data is processed in real time and compared against reference postures stored on a cloud server, which are uploaded and curated by professional physiotherapists. Each reference posture is stored as anonymized keypoint coordinate sets and metadata, ensuring accurate and clinically valid benchmarks. The system applies an occlusion-aware correction algorithm to reconstruct hidden joints in side postures, thereby reducing jitter and improving accuracy. This ensures precise analysis of posture, range of motion, and response time, reducing the risk of injury and improving therapeutic reliability.

[0037] The invention provides split-screen feedback, where one zone displays realtime body tracking and the other zone displays an interactive gaming environment powered by the UNITY engine. The gameplay dynamically adjusts to reflect the patient’s execution quality, rewarding accurate posture with higher scores and smoother gameplay, while poor posture limits progress. This gamification of physiotherapy makes rehabilitation more enjoyable, motivating patients to repeat prescribed exercises consistently.

[0038] Figure 1 and Figure 2 depict the overall architecture of the system, showing how the mobile device captures patient movements, processes them with the AI- powered body tracking module, and interacts with the cloud server to provide realtime feedback and gameplay. Figure 3 presents the process flow chart, showing the sequence from exercise selection to movement capture, Al analysis, comparison with cloud-stored postures, and dynamic adjustment of the gaming environment.

[0039] Figure 4 illustrates real-time posture capture feedback using color-coded indicators: red for incorrect posture, green for correct posture, and orange for partial completion. This visual guidance enables patients to understand alignment accuracy intuitively. Figures 5 through 8 demonstrate different physiotherapy poses within varied gaming environments, each with unique backgrounds and corresponding scoring. The variation in environments prevents repetition and enhances user engagement. Figure 9 shows a sample report generated after a session, containing details such as joint angles, range of motion, response times, and performance grading. Reports are securely stored in the cloud and accessible to both patient and healthcare provider.

[0040] Figure 10 illustrates the self-examination mode. The split screen is used differently here: the left side shows the patient’s live movements captured by the camera, while the right side displays exercise instructions and demo guidance. After completing the activity, the system generates a self-exam report. Figure 11 shows such a report, including color-coded joint performance indicators and a recommendation section. For example, if movement falls below the defined angular range, the report advises consultation with a physiotherapist or orthopaedic specialist. If movements are within acceptable limits, the system recommends continuing the home rehabilitation routine.

[0041] In one best method of working, the invention is implemented using the Bird Dog Pose. The system tracks six joints — left and right shoulders, hips, and knees. Acceptable joint angles are set between 80°-100°. The Al algorithm maps the joints, applies occlusion-aware correction for hidden legs, and compares them with physiotherapist-annotated postures stored in the cloud. Real-time color-coded indicators are displayed alongside a UNITY -based game, which adjusts gameplay according to performance. At the end of the session, a report is automatically generated and stored in the cloud, accessible to both the patient and healthcare provider.

[0042] In another embodiment, the invention supports direct doctor monitoring. Reports generated after each session are securely stored in the cloud and can be accessed by healthcare providers via secure logins. Doctors and physiotherapists can remotely review incremental improvements, ensuring error-free communication and timely intervention. Patients benefit from the psychological confidence of knowing they are directly monitored by their healthcare provider.

[0043] In yet another embodiment, the invention provides multi-patient monitoring capability. Using a centralized dashboard, a physiotherapist or doctor can simultaneously oversee multiple patients, reviewing their progress reports in real time. This increases clinical efficiency, particularly in resource-limited healthcare environments, and allows wider adoption of tele-rehabilitation.

[0044] In one implementation, the Al body tracking module is based on Google’s MediaPipe Pose Estimation model, fine-tuned using physiotherapist-annotated exercise demonstrations and approximately 50 synthetic pose sequences. Correct postures were defined by physiotherapists and stored as anonymized keypoint datasets. Training was performed using supervised calibration with angular deviation loss, applying lightweight gradient optimization with a low learning rate to ensure fast convergence on mobile devices without full retraining.

[0045] Validation was performed by comparing the original reference angles with patient-captured angles. Mean Absolute Error (MAE) was calculated using angular deviation. Hidden joints were identified and excluded from validation to reduce jitter. Temporal smoothing was applied across frames to improve stability. Results showed that the occlusion-aware correction algorithm reduced angular error significantly and ensured reliable side-pose assessment.

[0046] In another embodiment, the invention may be implemented as a non- transitory computer-readable medium storing instructions that, when executed by amobile processor, perform the steps of capturing patient movements, tracking 33 joints, applying occlusion-aware correction, comparing with cloud-stored postures, and generating reports. This embodiment protects the mobile application and ensures broader applicability across hardware platforms.

[0047] Across embodiments, the invention achieves distinct technical effects:• eliminating the need for wearable devices and external sensors,• improving accuracy of posture tracking through 33-joint mapping and occlusion-aware correction,• providing low-latency real-time analysis suitable for standard mobile internet connections,• motivating patients via gaming-based physiotherapy,• empowering patients through self-exam capability, and• enabling scalable doctor and multi-patient monitoring.

[0048] Industrial applicability lies in hospitals, physiotherapy clinics, telerehabilitation platforms, home rehabilitation setups, and sports injury recovery programs, where the system provides a cost-effective, scalable, and clinically reliable alternative to conventional physiotherapy monitoring methods.

[0049] Further embodiment of the invention discloses about a system, which is implemented as a physiotherapy system (100) comprising a processor and a memory configured to execute program instructions for physiotherapy engagement and progress tracking. The processor is operatively coupled to the mobile device camera and to the memory, which stores the program logic for performing the steps described in the method claims. When the instructions are executed by the processor, the system performs the following operations:• receiving user input to select a physiotherapy activity,• capturing patient movements using the inbuilt mobile camera,processing the captured video stream with the Al-powered body tracking module (101),• mapping anatomical joints as dots and applying occlusion-aware correction to reconstruct hidden joints,• comparing the extracted joint positions with physiotherapist-annotated postures stored on the cloud server (109),• displaying posture accuracy feedback through visual indicators and gaming environment (102) in a split-screen format,• generating and storing a progress report using the progress monitoring module (104), and• enabling additional functions including the self-examination module (107) for independent screening and the doctor monitoring module (108) for remote supervision.

[0050] The processor may be a general-purpose CPU, GPU, or Al accelerator integrated within the mobile device or an associated computing unit, while the memory may include non-volatile storage and RAM. The stored instructions are optimized to ensure low latency, real-time performance even on mobile hardware. By embedding the rehabilitation logic in a processor-and-memory architecture, the invention ensures that the Al model is not a program per se but a technical solution implemented through tangible hardware, compliant with patentability requirements.

[0051] Applications of the Invention

[0052] l.Hospital Rehabilitation Units :The invention can be deployed in hospital physiotherapy departments to provide continuous monitoring of post-surgerypatients. Doctors can review reports directly via cloud access, reducing the need for frequent hospital visits.

[0053] 2.Physiotherapy Clinics: Clinics can use the system to supervise multiple patients simultaneously. The centralized cloud reporting enables therapists to track progress and adjust exercise programs without one-on-one physical presence at all times.

[0054] 3.Tele-Rehabilitation Platforms: Patients in remote or underserved areas can access rehabilitation through their smartphones and internet connectivity. The invention supports telemedicine programs by offering scalable physiotherapy monitoring without requiring additional hardware.

[0055] 4.Home-Based Rehabilitation: Patients recovering from injuries or surgeries at home can perform guided physiotherapy with gaming integration. The self-examination mode provides Al -driven first-level assessment, helping patients decide when professional consultation is necessary.

[0056] 5.Sports Injury Recovery and Preventive Fitness: The system can also be applied in sports medicine for monitoring recovery exercises and ensuring posture accuracy. It can help athletes detect early signs of misalignment, preventing further injuries.

[0057] Advantages of the Invention1. Elimination of Wearables and External Sensors: Operates solely with a mobile device, inbuilt camera, mobile application, cloud server, and output display, reducing cost and complexity.2. Accurate Posture Tracking: Tracks 33 anatomical joints with occlusion- aware correction to handle side poses, reducing jitter and improving reliability compared to prior systems.3. Real-Time Visual Feedback: Uses color-coded indicators (green, red, orange) and instructional overlays to guide patients toward correct execution.4. Enhanced Patient Motivation: Integrates physiotherapy with a UNITY- powered gaming environment, dynamically adjusting rewards and difficulty, making rehabilitation more engaging and consistent.5. Self-Examination Capability: Patients can independently assess their condition, generating reports with recommendations on whether continued exercise or medical consultation is needed.6. Direct Doctor Monitoring: Enables healthcare providers to securely access reports, fostering accountability and providing psychological confidence for patients.7. Multi-Patient Scalability: Allows one physiotherapist or doctor to monitor multiple patients remotely via a centralized dashboard, improving efficiency of healthcare delivery.8. Low Latency and High Accessibility: The system is optimized for smooth performance even with mobile internet, ensuring accessibility across diverse regions, including rural areas.

[0058] The advantages set forth above, and those made apparent from the foregoing description, are efficiently attained. Since certain changes may be made in the above construction without departing from the scope of the invention, it is intended that all matters contained in the foregoing description or shown in the accompanying drawings shall be interpreted as illustrative and not in a limiting sense.

Claims

I CLAIM1. A physiotherapy system (100) for enhancing patient engagement and rehabilitation outcomes, the system comprising,• a mobile device with an inbuilt camera running a dedicated mobile application;• an Al-powered body tracking module (101) configured to capture and process anatomical joint movements of a patient from the captured video stream,• a cloud server (109) for storing physiotherapist-annotated reference postures and progress reports,• a gaming environment module (102) configured to map patient movements into corresponding in-game actions and dynamically adjust gameplay based on performance,• a feedback module (103) configured to provide real-time visual indicators on posture accuracy,• a progress monitoring module (104) configured to generate rehabilitation reports including joint angles, movement ranges, and grading, and• an output display via the mobile device screen or a connected television in split-screen format, characterized in that the body tracking module (101) is configured to map anatomical joints as dots, apply an occlusion-aware correction algorithm to reconstruct hidden joints, and is further adapted through supervised calibration using physiotherapist-annotated exercise data and synthetic pose datasets, employing angular deviation as a loss function with lightweight gradient-based optimization to ensure accuracy and low latency on mobile devices, thereby eliminating the need for external sensors or wearable devices; the system further comprises a self-examination module (107) for independent screening and a doctor monitoring module (108) enabling healthcare providers to remotely access patient reports through secure logins.

2. The system as claimed in claim 1, wherein the body tracking module (101) is configured to map 33 anatomical joints as dots.

3. The system as claimed in claim 1, wherein training datasets include physiotherapist-annotated postures and synthetic pose sequences to cover posture variations.

4. The system as claimed in claim 1, wherein accuracy is validated using Mean Absolute Error (MAE) between reference angles and patient-tracked angles.

5. The system as claimed in claim 1, wherein temporal smoothing and occlusion- aware correction are applied to reduce jitter and ensure stability of hidden joint reconstruction.

6. The system as claimed in claim 1, wherein the feedback module (103) displays posture accuracy using green for correct posture, red for incorrect posture, and orange for partial completion.

7. The system as claimed in claim 1, wherein the gaming environment module (102) dynamically adjusts gameplay difficulty and rewards based on the patient’s posture execution quality.

8. A method for physiotherapy engagement and progress tracking in a patient rehabilitation system, the method comprising the steps of,• selecting a physiotherapy activity on a mobile application,• capturing patient movements using the inbuilt camera of a mobile device.• processing the captured movements using an Al-powered body tracking module (101),• comparing the captured data with physiotherapist-annotated postures stored on a cloud server (109).• displaying feedback on posture accuracy through visual indicators and a gaming environment (102) on a split screen, and• generating a progress report using the progress monitoring module (104), the report stored in the cloud server and accessible to patients and healthcare providers, characterized in that the method includes mapping anatomical joints as dots, applying an occlusion-aware correction algorithm to reconstruct hidden joints, and adapting the Al model through supervised calibration using physiotherapist- annotated and synthetic pose datasets, employing angular deviation loss withgradient-based optimization for personalization and low latency on mobile devices, thereby eliminating the need for wearable devices or external sensors, and further comprising a self-examination mode (107) for independent patient assessment and a doctor monitoring mode (108) for remote supervision.

9. The method as claimed in claim 8, wherein the body tracking module (101) is configured to map 33 anatomical joints as dots.

10. The method as claimed in claim 8, wherein accuracy is validated by calculating Mean Absolute Error (MAE) between captured and reference joint angles.

11. The method as claimed in 8, wherein temporal smoothing is applied across consecutive frames to reduce jitter in posture tracking.

12. The method as claimed in claim 8, wherein progress reports include recommendations advising whether to continue home rehabilitation or consult a specialist.

13. The method as claimed in claim 8, wherein multiple patients are monitored simultaneously through centralized cloud reporting, enabling a single healthcare provider to oversee concurrent rehabilitation sessions.

14. A physiotherapy system (100) comprising a processor and a memory storing instructions that, when executed by the processor, cause the system to perform the steps of the method of any one of claims 8 to 13.

Images