Predicting Depressive Relapse in Patients with Major Depressive Disorder Using AI from Smartphone Behavioral Data
Applied Sciences · 07.04.2026 · 16 (7) · 3582
DOI: 10.3390/app16073582 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 07.04.2026. Verfasst von Brian Premchand und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Enterprise Singapore Enterprise Development Grant, Cogniant Pte. Ltd., Universal Health Pte. Ltd..
Abstract (Originalsprache)
Major depressive disorder (MDD) is a prevalent mental health condition that inflicts a high burden on individuals and healthcare systems. There is a clinical need to detect MDD relapse practically and effectively to improve treatment outcomes for patients. To address this, we developed a smart monitoring system using an Artificial Intelligence (AI) approach to estimate MDD severity and relapse risk from patients’ smartphone behavioral data (i.e., digital phenotyping). Thirty-five MDD patients were recruited from the Institute of Mental Health in Singapore, who installed the smartphone study app Sallie. Their symptoms were quantified using the Hamilton Depression Rating Scale (HAMD-17) at the start of the trial, and every 30 days after over 3 months. The app collected behavioral data such as activity, activity type, and GPS location used to train AI models such as logistic regression, decision trees, and random forest classifiers. We found that passive data collection continued for most participants (up to 79% retention rate) after 3 months. We also used five-fold cross-validation to predict HAMD-17 severity ranging from two to four classes and the relapse status, achieving 91%, 88%, and 78% accuracies for two to four classes, respectively, and a relapse prediction accuracy of 86% whereby four patients relapsed during the study. Additionally, anxiety factors within the HAMD-17 were significantly predicted (Pearson correlation coefficient = 0.78, p = 1.67 × 10−14). These results demonstrate the promise of using smartphone behavioral data to estimate depressive symptoms and identify early indicators of relapse.
Förderung
- Enterprise Singapore Enterprise Development Grant
- Cogniant Pte. Ltd.
- Universal Health Pte. Ltd.
Zitieren
APA
Premchand, B., Kothari, N., Tay, I. Q., Shah, K., Mok, Y. M., Kuek, J. H. L., Lim, W. O., & Ang, K. K. (2026). Predicting Depressive Relapse in Patients with Major Depressive Disorder Using AI from Smartphone Behavioral Data. Applied Sciences, 16(7), 3582. https://doi.org/10.3390/app16073582
Vancouver
Premchand B, Kothari N, Tay IQ, Shah K, Mok YM, Kuek JHL, et al. Predicting Depressive Relapse in Patients with Major Depressive Disorder Using AI from Smartphone Behavioral Data. Applied Sciences. 2026;16(7):3582. doi:10.3390/app16073582
BibTeX
@article{Premchand2026,
author = {Premchand, Brian and Kothari, Neeraj and Tay, Isabelle Q. and Shah, Kunal and Mok, Yee Ming and Kuek, Jonathan Han Loong and Lim, Wee Onn and Ang, Kai Keng},
title = {Predicting Depressive Relapse in Patients with Major Depressive Disorder Using AI from Smartphone Behavioral Data},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {7},
pages = {3582},
doi = {10.3390/app16073582}
}
EUVIMED