PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
June 5, 2026Scientific Reports0 citationsOpen Access

A causal discovery framework for digital phenotyping

AIAhmed Ibrahim

Key Points

  • To develop a framework that shifts from predictive classification to causal modeling in digital phenotyping for mental health.
  • Utilized CNN-based encoder to learn behavioral embeddings from multimodal sensor data.
  • Applied neuro-symbolic causal discovery to infer directed graphs of behavioral-psychological dynamics.
  • Conducted dimensionality reduction via PCA to retain five principal components explaining 85% of variance.
  • Causal approach identified time-lagged associations, with lower sleep activity (p<0.01) and reduced mobility (p<0.05) preceding stress episodes.
  • Deep embedding models showed limited improvement over chance in stress prediction, with best AUC of 0.532.
  • Causal biomarkers defined potential lagged behavior-stress relationships rather than confirmed causal effects.

Abstract

Digital phenotyping, the moment-by-moment quantification of human behavior using data from personal devices and sensors, has shown great promise in predicting mental health outcomes. However, the field is reaching a ’predictive plateau,’ where models, while accurate, are often opaque black boxes that offer limited insight into underlying mechanisms of well-being. This paper proposes a fundamental paradigm shift from predictive classification to structural causal modeling. We introduce a two-stage computational framework that first learns unified daily behavioral embeddings from multimodal sensor data using a CNN-based encoder, and then applies neuro-symbolic causal discovery to infer interpretable directed graphs of behavioral–psychological dynamics. In our evaluation, we observed clear signs of this predictive plateau: even deep embedding models performed only slightly better than chance in stress prediction (best AUC = 0.532). By comparison, the causal approach identified candidate time-lagged associations; for example, lower levels of sleep activity ( \(p<0.01\) ) and reduced mobility ( \(p<0.05\) ) often appeared as preceding indicators of stress episodes. Dimensionality reduction via PCA retained five principal components explaining approximately 85% of the variance, enabling post-hoc interpretation of candidate behavioral components such as “Stationary Social Engagement.” We define these components and their associated edge weights as candidate causal biomarkers: hypothesis-generating indicators of possible lagged behavior–stress relationships, rather than confirmed interventional causal effects.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Ahmed Ibrahim (2026) studied this question.

synapsesocial.com/papers/6a22692e763171746d547cd8https://doi.org/10.1038/s41598-026-55866-2
Ask AI
Helpful
Bookmark
Share
View Full Paper