Shoulder pain represents the most frequently reported musculoskeletal disorder, often leading to significant functional impairment and pain, impacting quality of life. Home-based rehabilitation programs offer a more accessible and convenient solution for an effective shoulder disorder treatment, addressing logistical and financial constraints associated with traditional physiotherapy. The aim of this systematic review is to report the monitoring devices currently proposed and tested for shoulder rehabilitation in home settings. The research question was formulated using the PICO approach, and the PRISMA guidelines were applied to ensure a transparent methodology for the systematic review process. A comprehensive search of PubMed and Scopus was conducted, and the results were included from 2014 up to 2023. Three different tools (i.e., the Rob 2 version of the Cochrane risk-of-bias tool, the Joanna Briggs Institute (JBI) Critical Appraisal tool, and the ROBINS-I tool) were used to assess the risk of bias. Fifteen studies were included as they fulfilled the inclusion criteria. The results showed that wearable systems represent a promising solution as remote monitoring technologies, offering quantitative and clinically meaningful insights into the progress of individuals within a rehabilitation pathway. Recent trends indicate a growing use of low-cost, non-intrusive visual tracking devices, such as camera-based monitoring systems, within the domain of tele-rehabilitation. The integration of home-based monitoring devices alongside traditional rehabilitation methods is acquiring significant attention, offering broader access to high-quality care, and potentially reducing healthcare costs associated with in-person therapy.

Shoulder rehabilitation is considered one of the most effective treatments for restoring functional abilities, reducing shoulder pain, and enabling the leading of an active life, improving mobility, strength, and endurance. However, the burdens of travel and time may prevent patients from taking part in such rehabilitation programs. The increased availability of wearable sensors and the development of machine learning (ML) algorithm has shown the feasibility of remote home-based rehabilitation therapy. In this study, we proposed a wearable system based on 3 magneto-inertial sensors to classify shoulder rehabilitation exercises. The classification has been performed by 5 different supervised ML algorithms (i.e., k-Nearest Neighbours, Support Vector Machine, Naïve Bayes, Decision Tree, and Random Forest) to find out the most performant one. The feasibility of the wearable system was assessed on nineteen healthy subjects during six rehabilitation exercises. Each exercise was performed six times, for a total of 684 samples. The data were analysed and classified using the five mentioned classification models. Performances of the algorithms in accurately classifying exercise activity were evaluated with the k-fold cross-validation method and the nested validation method. The results demonstrated the effectiveness of the proposed algorithms in recognizing all the exercises. Features derived from acceleration, angular velocity, and orientation data were shown to reach the optimal predictive accuracies. Future work should focus on evaluating the performance of such systems on data acquired on patients with musculoskeletal disorders and on the inclusion of more shoulder rehabilitation exercises in the protocol.

Purpose: The objective of this study is to train and test machine‐learning (ML) models to automatically classify shoulder rehabilitation exercises.Methods: The cohort included both healthy and patients with rotator‐cuff (RC) tears. All participants performed six shoulder rehabilitation exercises, following guidelines developed by the American Society of Shoulder and Elbow Therapists. Each exercise was repeated six times, while wearing a wearable system equipped with three magneto‐inertial sensors. Six supervised machine‐learning models (k‐Nearest Neighbours, Support Vector Machine, Decision Tree, Random Forest (RF), Logistic Regression and Adaptive Boosting) were trained for the classification. The algorithms' ability to accurately classify exercise activities was evaluated using the nested cross‐validation method, with different combinations of outer and inner folds.Results: A total of 19 healthy subjects and 17 patients with complete RC tears were enroled in the study. The highest classification performances were achieved by the RF classifier, with an accuracy of 89.91% and an F1‐score of 89.89%.Conclusion: The results of this study highlight the feasibility and effectiveness of using wearable sensors and ML algorithms to accurately classify shoulder rehabilitation exercises. These findings suggest promising prospects for implementing the proposed wearable system in remote home‐based monitoring scenarios. The ease of setup and modularity of the system reduce user burden enabling patient‐driven sensor positioning.Level of Evidence: Level III.