JMIR Publications

ABSTRACT

We present machine learning (ML) approaches that enable longitudinal monitoring of patient-reported symptoms for people with multiple sclerosis (pwMS) by harnessing passively collected data from sensors in smartphones and fitness trackers. For each patient, we divided collected data into discrete periods. From each period, we extract patient-level behavioral features from the current period (action features) and the previous period (context features). Next, we apply Support Vector Machine with Radial Bias Function Kernel and AdaBoost to predict the presence of depressive symptoms (every 2-weeks) and high global MS symptom burden, severe fatigue, and poor sleep quality (every 4-weeks). We collected ~12,500 days of passive sensor and behavioral health data from 104 pwMS participants who completed 12-weeks and a subset of 44 pwMS who completed 24-weeks of data collection. Among the best-performing models with the least sensor data requirement, ML algorithm predicts depressive symptoms with an accuracy of 80.6% (35.5% improvement over baseline; F1-score: 0.76), high global MS symptom burden with an accuracy of 77.3% (51.3% improvement over baseline; F1-score: 0.77), severe fatigue with an accuracy of 73.8% (45.0% improvement over baseline; F1-score: 0.74), and poor sleep quality with an accuracy of 72.0% (28.1% improvement over baseline; F1-score: 0.70). Sensor data were largely sufficient for predicting symptom severity, while the prediction of depressive symptoms benefited from minimal active patient input (i.e., response to two brief questions on the day before prediction). Our digital phenotyping approach using passive sensors on smartphones and fitness trackers may help patients with real-world, continuous, self-monitoring of common symptoms in their own environment and assist clinicians with better triage of patient needs for timely interventions in MS.