Journal DOI 10.68956/journal.human-performance-futures

Creative Commons source reading · Machine learning for performance

Artificial Intelligence Applications to Support Physical Activity, Mobility, and Fatigue Management in People with Multiple Sclerosis: A Scoping Review

Pantazis Deligiannis; Iosif Alexandros Kouidis; Anastasia Theofanous; Maria Anifanti; Asterios Deligiannis; Evangelia Kouidi

Originally published in Healthcare (Basel) · 2026-07-21

From the article

Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.

Abstract

Background: Physical activity plays a vital role in caring for people with multiple sclerosis (MS). Yet, challenges like fatigue, mobility impairment, fall risk, symptom fluctuation, and poor access to rehabilitation often make sustained participation difficult. Adhering to physical activity programmes is tough. Artificial intelligence (AI) may transform wearable, smartphone, clinical, and patient-reported data into interpretable information for monitoring, prediction and individualized support. Objective: Building on the identified need for individualized support, this scoping review mapped original AI-based studies relevant to physical activity, gait, mobility, ambulation, fatigue, fall risk, and real-world functioning in people with MS. Methods: The review followed PRISMA-ScR principles. Search covered records published from 1…

4.1. Principal Findings

This scoping review identified 21 original AI studies on physical activity, mobility, gait, fatigue, fall risk, and real-world functioning in people with MS. The evidence base was particularly informative for fall risk prediction, gait analysis, and wearable/sensor-based mobility modelling. The field has progressed from inertial sensor deep learning and wearable gait speed estimation to models that use smartphones, postural sway, instrumented walkways, functional chair stand testing, daily life gait and turning, connected devices, digital biomarkers, and multimodal clinical, sensor-based, and self-reported data. The evidence indicates that AI can detect or predict functional states that are difficult to assess during periodic clinic visits. Most included studies were observational, validation, classification, or prediction studies.…

5. Conclusions

This scoping review identified 21 original AI studies relevant to physical activity, gait, mobility, fatigue, fall risk, and real-world functioning in people with MS. The evidence base indicates that AI can extract clinically relevant patterns from gait, postural sway, wearable, smartphone, connected device, chair stand, daily life turning, clinical, and patient-reported data. However, current evidence does not yet demonstrate that AI-supported systems improve physical activity, adherence, fatigue burden, fall risk, health-related quality of life, or functional independence in people with MS. The field should therefore be interpreted as promising but still early, with AI currently more mature as a monitoring, classification, and prediction tool than as a validated intervention. The next step is prospective, externally validated,…

Editorial reading guide

  • What data created and tested the model, and was evaluation independent?
  • What is the cost of a false positive, false negative or out-of-distribution decision?