Within-person prediction of depressive symptom change using year-long Screenome data and CES-D assessments

2026-04-24

AI Summary

This study addresses the prospective prediction of individual trajectories—worsening, stability, or improvement—of depressive symptoms over a two-week horizon to enable early, precise intervention. Leveraging a one-year longitudinal dataset comprising biweekly CES-D assessments and over 100 million high-frequency screenshots collected via the Stanford Screenomics platform, the work formulates intra-individual depression trajectory prediction as a three-class classification task for the first time. Using an XGBoost model with temporal holdout validation, the approach achieves an AUC of 0.906 in predicting transitions across clinical severity thresholds, an AUC of 0.755 for within-person symptom change, and generalizes effectively to new individuals (AUC = 0.821). The analysis identifies personalized behavioral precursors such as surges in social media use and fragmented device interactions, underscoring the critical role of baseline symptom severity in detecting imminent worsening episodes.

Technology Category

• Application Domains: Humanities & Computational Social Science
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Predicting whether an individual's depressive symptoms will worsen, remain stable, or improve over the coming weeks can enable earlier and more targeted care, yet prospective within-person trajectory prediction remains largely unaddressed in digital phenotyping. We combine fortnightly CES-D assessments with over 100 million screenshots captured every five seconds via the Stanford Screenomics platform from 96 adults followed for approximately one year (M = 20.9, SD = 3.9 assessments per participant, 2,002 total observations). We frame prediction as a within-person classification task: whether symptoms will worsen, remain stable, or improve over the subsequent fortnight, operationalized in three ways to capture clinically meaningful change. Under temporal holdout, XGBoost achieves an AUC of 0.906 for crossings of established CES-D severity bands and 0.755 for change relative to each participant's own within-person variability, generalizing to unseen individuals (AUC = 0.821). Each person's typical symptom level was the only statistically significant predictor above the most recent CES-D score; without it, the most consequential worsening transitions go undetected. Screenome-derived behavioral features revealed prodromal patterns of worsening, including escalating social media use, fragmented device engagement, and changes in overnight activity, with substantial individual heterogeneity. These findings establish a proof-of-concept foundation for monitoring systems that could identify individuals approaching clinical deterioration before symptoms reach a crisis point.

Problem

• within-person prediction
• depressive symptoms
• digital phenotyping
• trajectory prediction
• early intervention

Innovation

• within-person prediction
• digital phenotyping
• Screenome
• depression trajectory
• behavioral biomarkers