Digital remote monitoring of people with multiple sclerosis

Multiple sclerosis (MS) is a chronic neurodegenerative disease that affects over 2.8 million people globally, leading to significant motor and non-motor symptoms. Effective disease monitoring is critical for improving patient outcomes but is often hindered by the limitations of infrequent clinical assessments. Digital remote monitoring tools leveraging big data and AI offer new opportunities to track symptoms in real time and detect disease progression.

This narrative review explores recent advancements in digital remote monitoring of motor and non-motor symptoms in MS. We conducted a PubMed search to collect original studies aimed at evaluating the use of AI and/or big data for digital remote monitoring of pwMS. We focus on tools and techniques applied to data from wearable sensors, smartphones, and other connected devices, as well as AI-based methods for the analysis of big data.

Wearable sensors and machine learning algorithms show significant promise in monitoring motor symptoms, such as fall risk and gait disturbances. Many studies have demonstrated their reliability not only in clinical settings and for independent execution of motor assessments by patients, but also for passive monitoring during everyday life. Cognitive monitoring, although less developed, has seen progress with AI-driven tools that automate the scoring of neuropsychological tests and analyse passive keystroke dynamics. However, passive cognitive monitoring is still underdeveloped, compared to monitoring of motor symptoms. Some preliminary evidence suggests that application of AI and big data to other understudied aspects of MS (namely sleep and circadian autonomic patterns) may provide novel insights.

Advances in AI and big data offer exciting possibilities for improving disease management and patient outcomes in MS. Digital remote monitoring has the potential to revolutionize MS care by providing continuous, long-term granular data on both motor and non-motor symptoms. While promising results have been demonstrated, larger-scale studies and more robust validation are needed to fully integrate these tools into clinical practice and generalise their results to the wider MS population.