Student Mental Health Screening via Fitbit Data Collected During the COVID-19 Pandemic

2026-01-22

AI Summary

The COVID-19 pandemic has exacerbated psychological distress among university students, including anxiety, depression, and stress, underscoring the urgent need for non-invasive, continuous screening methods. This study presents the first systematic integration of multidimensional psychological scales with multimodal physiological time-series data—such as heart rate and sleep patterns—collected via Fitbit wearable devices to develop machine learning models for mental health assessment. The research investigates the predictive efficacy of each modality across varying data aggregation granularities. The resulting models achieve F1 scores of 0.79, 0.77, and 0.78 for detecting anxiety, stress, and depression, respectively, demonstrating the feasibility and practical utility of real-time mental health monitoring using wearable technology.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Security and Privacy: Large-scale security measurements
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

College students experience many stressors, resulting in high levels of anxiety and depression. Wearable technology provides unobtrusive sensor data that can be used for the early detection of mental illness. However, current research is limited concerning the variety of psychological instruments administered, physiological modalities, and time series parameters. In this research, we collect the Student Mental and Environmental Health (StudentMEH) Fitbit dataset from students at our institution during the pandemic. We provide a comprehensive assessment of the ability of predictive machine learning models to screen for depression, anxiety, and stress using different Fitbit modalities. Our findings indicate potential in physiological modalities such as heart rate and sleep to screen for mental illness with the F1 scores as high as 0.79 for anxiety, the former modality reaching 0.77 for stress screening, and the latter modality achieving 0.78 for depression. This research highlights the potential of wearable devices to support continuous mental health monitoring, the importance of identifying best data aggregation levels and appropriate modalities for screening for different mental ailments.

Problem

• mental health screening
• wearable devices
• anxiety
• depression
• stress

Innovation

• wearable sensors
• mental health screening
• machine learning
• physiological modalities
• time series analysis