Our research focuses on advancing digital healthcare through augmented reality (AR), virtual reality (VR), extended reality (XR) and computer-vision-based technologies to enable accessible, data-driven, and personalized remote physical therapy. We develop immersive system applications that capture real-time hand, eye and upper-limb movements using markerless tracking, transforming traditional rehabilitation into an interactive and measurable experience.
By integrating AI-based motion analysis with model-based systems engineering (MBSE) frameworks, our work ensures that patient data, clinical requirements, and system design are seamlessly connected. This approach allows us to generate accurate metrics such as joint angles and range of motion, supporting clinicians in monitoring progress and customizing therapy protocols for individual patients.
We also explore the broader healthcare ecosystem by incorporating enterprise-level architectures to improve trust, scalability, and integration of digital health solutions. Through close collaboration with physical therapists and healthcare stakeholders, our research aims to bridge the gap between emerging immersive technologies and real-world clinical practice.
Gayathri Boopathy is developing TheraXP — AI-powered gamified digital rehabilitation platform that integrates augmented reality (AR), computer vision, human–machine interaction, and Model-Based Systems Engineering (MBSE) to create a human-centric healthcare ecosystem for aging populations. Built on an enterprise architecture vision, TheraXP unifies multimodal rehabilitation pathways—hand therapy, eye therapy, and full-body recovery—into a scalable and connected care framework. By combining real-time biomechanical sensing, intelligent motor-function assessment, clinician-in-the-loop feedback, and gamified therapy experiences, TheraXP enables personalized, accessible, and data-driven rehabilitation. Its long-term vision is to establish a continuous human-centric healthcare architecture where AI, digital therapeutics, and clinical systems work together to improve recovery outcomes, independence, and quality of life.
Future work in digitalized environments will engage a multi-generational workforce in new work contexts that can include immersive technology and interaction with remote robotic systems. The overall health and well-being of workers will be a high priority for organizations, as envisioned in the Industry 5.0 framework. This vision requires an architectural framework that integrates work contexts with associated health data and engages health providers as key stakeholders in the design. Digital models created using a model-based systems engineering (MBSE) methodology are proposed as context-aware informatics that can support these needs. A case study of an augmented reality (AR) system that customizes hand gestures to support humans with varied abilities to conduct required tasks is presented. The conceptual design of this system is presented using MBSE models that can serve as context-aware informatics to the work place and the connected health enterprise.
The digital transformation of healthcare organizations is taking place on many different levels ranging from digital platforms for patient management to digital health solutions with emerging technology. Even as technology advances at a rapid pace with potential fo
r more equitable access to healthcare, culture and mind-set, organizational structure and governance have been cited by medical experts as the key barriers to digital transformation. We investigate the application of modern system engineering tools and methods for engaging healthcare professionals, systems engineers and other stakeholders in a collaborative effort to drive this transformation. The Unified Architecture Framework (UAF) is considered for digitally capturing strategic elements such as vision, goals, missions, capabilities, along with resources, and security profiles and connecting them to the roadmaps within UAF. This approach will highlight how UAF can enable healthcare organizations to align their strategies with actionable, evolving roadmaps, moving beyond static documents. UAF will be employed to architect and model the enterprise elements, and the Systems Modeling Language (SysML) will be employed to model the technical details of the system. These platforms can provide healthcare professionals experience on model-based system design throughout the lifecycle phases. Examples of modular training material designed to engage stakeholders with varied backgrounds in healthcare systems are presented.
Digital health interventions and wearable health devices have the potential to become significant enablers for proactive management of individual and population health. For this to happen, their effectiveness integration in the larger health ecosystem must be considered from the perspectives of all stakeholders involved. Considerations of enabling trust in wearable health technology, ensuring secure data exchange, transparency in the goals of the health enterprise, reducing burn-out of healthcare professionals and cost of healthcare are system-wide factors that need to be addressed for the digital transformation of healthcare systems. A unified architecture framework (UAF) is presented in this work to capture the strategic and operational viewpoints of the health enterprise, where the enterprise includes the network of people, processes, organizations, technologies and other resources involved in receiving and delivery of healthcare. The strategic motivation view specifications in the UAF highlight drivers, challenges and opportunities and their alignment to the enterprise goals and capabilities. The operational viewpoints present the taxonomy, structure and connectivity of various performers in a scenario representing remote delivery of physical therapy (PT) through wearable health systems. The case study of an augmented reality system that enables remote PT shows the extension of the enterprise UAF to a solution architecture of the system using elements of model-based systems engineering.
This thesis investigates the application of augmented reality (AR) technology as a digital health solution for physical therapy and rehabilitation of hand mobility. Physical therapy relies on tracking joint flexibility, range of motion, and neuromuscular coordination. Quantifying the degree to which the bone joints of the fingers can extend is an important consideration in the progression of therapy. The Magic Leap 2 AR device and it’s hand-tracking software was utilized to capture the three-dimensional positions of the bone joints of each of the fingers as the user executes different types of gestures. The time series of the joint positions was processed to estimate the dynamics of the angles that the bone joints traverse during the gesture. AR-based tracking can enhance static measurements made with instruments such as goniometers by providing a dynamical measure of the joint angles. A key contribution of this work is the application of machine learning algorithms to classify hand movements using time series data captured from the AR device. The feature analysis incorporates the 3-dimensional position of bone joints, inter-joint distances, and joint angles for movement classification. The gesture was classified into a sequence of states that captured the movement of the hand during open, extension, flexion, and closed actions. The random forest algorithm demonstrated the highest accuracy in classifying states. The time series of angle dynamics was further applied to distinguish between various levels of flexion and extension such as hypermobility, hyperextension, extension, mild flexion, moderate flexion, deep flexion, full flexion, and max flexion. This interdisciplinary study, combining AR, ML, and biomechanics of the hand has the potential to advance point-of-care digital health solutions for the millions of people recovering from strokes and injuries. Future work will focus on enabling real-time visual feedback and artificial intelligence based systems to motivate the AR user towards daily therapeutical practice. The integration of AI to automate gesture recognition and provide real-time guidance to the user will also be explored.
The need for point-of-care health solutions and digital health interventions continues to increase, driven by an aging population and those displaced from the systemic impacts of environmental, infrastructural, and economic factors. These demographic and social shifts are placing unprecedented strain on the
healthcare system. In response to these challenges, digital health solutions are emerging, although data indicates low confidence among both consumers and healthcare professionals due to a lack of regulatory oversight compared to traditional medical systems. This research explores the use of augmented reality (AR) technology in physical therapy and rehabilitation as a potential digital health intervention. The focus is on improving upper limb and hand mobility. This study em
ploys a digital engineering design process in collaboration with physical therapists and clinical researchers. The goal is to utilize data from the AR sensors to capture quantitative information about a patient’s therapeutic progress. The Digital Engineering framework presented can be applied for improving the validation and verification of technology-based digital health interventions, with the potential to enhance access to rehabilitation resources. Use-case and requirement diagrams are developed through close collaboration with physical therapy clinicians, to assess user engagement and therapeutic outcomes. Activity diagrams capture successive stages of improvement in the proposed system. The performance of the AR application in tracking joint angles and measuring mobility during prescribed gestures is evaluated against published normative values, highlighting the potential of this technology to improve upon manual measurement methods.
