This study investigates the feasibility of using mobile and wearable sensor data to monitor multiple sclerosis (MS) in free-living conditions. The research aims to identify reliable, clinically useful, and available features from mobile and wearable devices that can distinguish between people with MS (PwMS) and healthy controls (HC), recognize MS disability and fatigue levels, and evaluate the effectiveness of treatments. The dataset includes 55 PwMS and 24 HC participants, collected over 489 days, with data from wearable sensors, smartphones, patient health records, and self-reports. The study evaluates the reliability of features derived from these data sources and their clinical utility in monitoring MS. The results show that features such as heart rate variability, physical activity, and sleep patterns can be used to distinguish between PwMS and HC, and to recognize MS disability and fatigue levels. The study also demonstrates the feasibility of using machine learning to automatically assess clinical measurements. The findings suggest that continuous monitoring of MS using mobile and wearable devices can provide valuable insights into disease progression and help guide treatment decisions. The study highlights the potential of these technologies for real-world MS monitoring and management.This study investigates the feasibility of using mobile and wearable sensor data to monitor multiple sclerosis (MS) in free-living conditions. The research aims to identify reliable, clinically useful, and available features from mobile and wearable devices that can distinguish between people with MS (PwMS) and healthy controls (HC), recognize MS disability and fatigue levels, and evaluate the effectiveness of treatments. The dataset includes 55 PwMS and 24 HC participants, collected over 489 days, with data from wearable sensors, smartphones, patient health records, and self-reports. The study evaluates the reliability of features derived from these data sources and their clinical utility in monitoring MS. The results show that features such as heart rate variability, physical activity, and sleep patterns can be used to distinguish between PwMS and HC, and to recognize MS disability and fatigue levels. The study also demonstrates the feasibility of using machine learning to automatically assess clinical measurements. The findings suggest that continuous monitoring of MS using mobile and wearable devices can provide valuable insights into disease progression and help guide treatment decisions. The study highlights the potential of these technologies for real-world MS monitoring and management.