Dynamic clustering via branched deep learning enhances personalization of stress prediction from mobile sensor data

• Published in: Scientific reports Vol. 14; no. 1; pp. 6631 - 16
• Main Authors: Luo, Yunfei, Deznabi, Iman, Shaw, Abhinav, Simsiri, Natcha, Rahman, Tauhidur, Fiterau, Madalina
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 19.03.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 631/378/1831; 631/477/2811; Cellular telephones; Data collection; Deep learning; Distance learning; Health problems; Humanities and Social Sciences; Machine learning; Mobile computing; multidisciplinary; Multitask learning; Science; Science (multidisciplinary); Stress prediction; Students; Multitask learning; Stress prediction; Mobile computing; Machine learning
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-56674-2

College students experience ever-increasing levels of stress, leading to a wide range of health problems. In this context, monitoring and predicting students’ stress levels is crucial and, fortunately, made possible by the growing support for data collection via mobile devices. However, predicting stress levels from mobile phone data remains a challenging task, and off-the-shelf deep learning models are inapplicable or inefficient due to data irregularity, inter-subject variability, and the “cold start problem”. To overcome these challenges, we developed a platform named Branched CALM-Net that aims to predict students’ stress levels through dynamic clustering in a personalized manner. This is the first platform that leverages the branching technique in a multitask setting to achieve personalization and continuous adaptation . Our method achieves state-of-the-art performance in predicting student stress from mobile sensor data collected as part of the Dartmouth StudentLife study, with a ROC AUC 37% higher and a PR AUC surpassing that of the nearest baseline models. In the cold-start online learning setting, Branched CALM-Net outperforms other models, attaining an average F1 score of 87% with just 1 week of training data for a new student, which shows it is reliable and effective at predicting stress levels from mobile data.