ePhysio: A Wearables-Enabled Platform for the Remote Management of Musculoskeletal Diseases

Abstract

Technology advancements in wireless communication and embedded computing are fostering their evolution from standalone elements to smart objects seamlessly integrated in the broader context of the Internet of Things. In this context, wearable sensors represent the building block for new cyber-physical social systems, which aim at improving the well-being of people by monitoring and measuring their activities and provide an immediate feedback to the users. In this paper, we introduce ePhysio, a large-scale and flexible platform for sensor-assisted physiotherapy and remote management of musculoskeletal diseases. The system leverages networking and computing tools to provide real-time and ubiquitous monitoring of patients. We propose three use cases which differ in scale and context and are characterized by different human interactions: single-user therapy, indoor group therapy, and on-field therapy. For each use case, we identify the social interactions, e.g., between the patient and the physician and between different users and the performance requirements in terms of monitoring frequency, communication, and computation. We then propose three related deployments, highlighting the technologies that can be applied in a real system. Finally, we describe a proof-of-concept implementation, which demonstrates the feasibility of the proposed solution.

Wearable Sensors System for an Improved Analysis of Freezing of Gait in Parkinson’s Disease Using Electromyography and Inertial Signals

“…Finally, the continuous acquisition and storage of the patient physiological parameters (number of FOG episodes, FOG phenotype and muscle activity type) permits the development of an up-to-date electronic agenda, specific for each patient, thus opening to telemedicine applications, including tele-rehabilitation. Several studies [ 70 , 71 , 72 , 73 ] have already shown practical perspectives of wearable sensors use in the home environment to remotely monitor patients’ clinical state and improve therapeutic strategies. The objective and long-term measures by means of wearable sensors in free living-like conditions would support patients’ physical activity by giving feedback about motor performance and tailored instructions [ 74 ], such as lengthen the stride length during walking to limit the sequence effect (step-to-step decrease in amplitude) and thus potentially reduce FOG occurrence [ 75 ].…”

A Review on Efficacy of Sensors in Capturing Biophysical Measures and its Application in the Field of Physical Therapy and Rehabilitation

“…Monitoring correctness and irregularities in patterns different from normalprototype, identification of setbacks and unwarranted behavior [1,4] . Regular association between health information being transferred to health care professionals as exact and confirmative values [5] . Data stored in the sensors to be transferred and expanded to provide visual and auditory feedback to subjects [6][7].…”

Recognition and Repetition Counting for Local Muscular Endurance Exercises in Exercise-Based Rehabilitation: A Comparative Study Using Artificial Intelligence Models

“…The application of ML methods to study data from human movements and activities to detect and understand these activities are referred to as human activity recognition (HAR). In recent years, many ML and deep learning-based models have been used along with wearable sensors in the assessment of human movement activities in many domains including: health [ 11 ], recreation activities [ 12 ], musculoskeletal injuries or diseases [ 13 ], day-to-day routine activities (e.g., walking, jogging, running, sitting, drinking, watching TV) [ 11 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 ], sporting movements [ 22 ] and exercises [ 23 , 24 , 25 , 26 , 27 ]. The ML models used for exercise recognition have predominantly used multiple wearable sensors [ 28 , 29 , 30 , 31 ], specifically in the areas of free weight exercise monitoring [ 32 ], the performance of lunge evaluation [ 24 ], limb movement rehabilitation [ 33 ], intensity recognition in strength training [ 34 ], exercise feedback [ 24 ], qualitative evaluation of human movements [ 28 ], gym activity monitoring [ 29 ], rehabilitation [ 23 , 25 , 33 , 35 ] and indoor-based exercises for strength training [ 36 ].…”