Machine Learning for Depression Screening and Intervention: an Original Circadian Rhythm Score-based Methodology
2026-07-06 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors created a new way to combine daily behaviors like sleep, activity, and social patterns into a single score called the Circadian Rhythm Score (CRS) to help detect depression. This score keeps important behavioral details and works almost as well as using all the raw data separately. They used this score in a model that can explain how different behaviors relate to depression risk and found specific behavior goals, like how much exercise helps and optimal nap times for those with less sleep. Their approach aims to make depression screening more understandable and also guide personalized behavior changes. They tested their method with data from a large health study in China and showed it works well.
Circadian RhythmDepression ScreeningBehavioral DataRepresentation LearningGradient-Boosted TreesSHAP AnalysisCounterfactual RegressionMET-min/weekInterpretable Modeling
Authors
Bin Wang, Shuo Lian, Yuanyuan Hou, Dexian Wang, Peilan He, Feng Hong, Yanwei Yu, Tianrui Li
Abstract
Depression screening from large-scale behavioral data is challenged by fragmented circadian indicators, limited interpretability, and the lack of intervention-oriented analysis. Existing approaches typically analyze sleep, activity, and social behaviors in isolation, failing to capture their joint circadian structure. To address this limitation, we first propose the Circadian Rhythm Score (CRS), a composite index that compresses multi-domain daily behaviors into a unified representation of circadian rhythm. CRS is constructed to maximize discriminative power for depression screening while preserving behavioral semantics through non-negativity constraints. Empirical results demonstrate near-lossless compression, where a single CRS retains almost the full predictive capability compared with multiple raw behavioral indicators. Building upon CRS, we develop an interpretable depression screening framework based on gradient-boosted trees and SHAP analysis, revealing nonlinear and saturation-like associations between circadian rhythm and depression risk. Beyond risk prediction, we further integrate interaction modeling and counterfactual regression to estimate heterogeneous and dose-dependent behavioral effects, enabling intervention-oriented reasoning under different circadian contexts. Experiments on the China Health and Retirement Longitudinal Study (CHARLS, n=15,233), demonstrate robust screening performance (ROC-AUC=0.825) and identify actionable behavioral thresholds, including a minimum effective exercise dose of approximately 300 MET-min/week and an optimal restorative nap duration of approximately 65 minutes for sleep-deprived individuals. By bridging supervised representation learning and interpretable modeling, this work provides a scalable framework for depression screening and intervention-aware healthcare data mining.