Loading your page…
Zenodo
By Waseem Mumtaz Ahamed.
Ward brings these articles into the same app as your cards and questions. One free account for Ward, Suture, Osler and Prognia.
Abstract: Background: Artificial intelligence (AI) and wearable sensors are increasingly capable of quantifying mobility, gait, balance, upper-limb activity, physiological status, and rehabilitation dose outside conventional clinical encounters. These technologies could enable a transition from episodic rehabilitation toward continuous, predictive, and personalized disability care. However, the extent to which AI-enabled wearables can predict functional deterioration, estimate rehabilitation outcomes, and support independent living remains uncertain.
To systematically synthesize evidence on AI-enabled wearable technologies used to predict or quantify functional decline, rehabilitation outcomes, mobility, activities of daily living, fall risk, and related indicators of independent living in adults with physical disabilities, and to develop a clinically grounded translational framework for implementation in Saudi Arabia.
The review is designed and reported in accordance with PRISMA 2020 and PRISMA-S. Eligible evidence includes prospective and retrospective prediction-model studies, validation studies, rehabilitation-monitoring studies, and controlled intervention studies in adults with neurological or physical disability in which wearable sensor data are analyzed using machine-learning or AI methods. The proposed search covers MEDLINE/PubMed, Embase, Scopus, Web of Science, CINAHL, IEEE Xplore, and CENTRAL from inception to September 2026. Data extraction follows CHARMS domains. Prediction-model quality, risk of bias, and applicability are evaluated using PROBAST+AI; reporting completeness is interpreted against TRIPOD+AI. Because of expected heterogeneity in populations, sensors, outcomes, algorithms, and validation strategies, narrative synthesis is primary, with meta-analysis reserved for clinically and methodologically comparable studies.
Verified evidence demonstrates strongest development in post-stroke rehabilitation, where inertial and multimodal wearable signals have been used to estimate clinical motor scales and predict discharge ambulation, independence, fall risk, and longer-term functional status. Wearable data improved prediction over clinical variables alone in several studies, although performance varied by outcome, baseline ambulatory status, and validation design. Parkinson disease studies demonstrate clinically relevant detection and short-horizon prediction of freezing of gait, while multiple-sclerosis studies show the feasibility of predicting disability and fatigue from mobile and wearable features. Across the field, inertial measurement units predominate; random forests, support-vector methods, gradient boosting, neural networks, and deep-learning architectures are frequently used. Major limitations are small samples, single-center development, heterogeneous sensor placement and feature engineering, limited calibration reporting, insufficient external validation, risk of participant-level data leakage, and limited evidence that algorithm use improves patient-centered outcomes.
AI-enabled wearable rehabilitation has progressed from activity recognition toward clinically meaningful prediction, but the evidence base remains stronger for technical validity than for demonstrated clinical impact. The next generation of systems should combine longitudinal individualized baselines, multimodal sensing, uncertainty-aware prediction, explainable clinical decision support, adaptive rehabilitation feedback, and prospective impact evaluation. Saudi Arabia provides a favorable implementation context because national digital-health policy explicitly supports AI, cloud infrastructure, telemedicine, accessibility, and rehabilitation services. A staged national pathway emphasizing validation, interoperability, cybersecurity, equity, and patient-centered outcomes could position AI-enabled rehabilitation as a scalable component of disability care. Keywords: artificial intelligence; wearable sensors; rehabilitation; physical disability; functional decline; machine learning; digital biomarkers; independent living; remote monitoring; Saudi Arabia. Title: Artificial Intelligence Enabled Wearable Technologies for Predicting Functional Decline and Supporting Rehabilitation and Independent Living in Adults with Physical Disabilities: A Systematic Review and Translational Framework for Saudi Arabia Author: Waseem Mumtaz Ahamed International Journal of Healthcare Sciences ISSN 2348-5728 (Online) Vol. 14, Issue 1, April 2026 - September 2026 Page No: 623-634 Research Publish Journals Website: www.researchpublish.com Published Date: 18-September-2026 DOI: https://doi.org/10.5281/zenodo.22829102 Paper Download Link (Source) https://www.researchpublish.com/papers/artificial-intelligence-enabled-wearable-technologies-for-predicting-functional-decline-and-supporting-rehabilitation-and-independent-living-in-adults-with-physical-disabilities-a-systematic-review-and-translational-framework-for-saudi-arabia
Published in Zenodo (CERN European Organization for Nuclear Research). The abstract is shown as published and remains the work of its authors; read the full article at the source.
Prognia lists this article for reference and education. It is not medical advice. Always read the original and follow current guidelines and local protocols before acting on it.
