Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 11, 2025

Digital Phenotyping of Individuals with Suicide Attempts: Comparison and Classification with Healthy Controls Using passive-sensing Smartphone Data (Preprint)

View Full Paper
Ask AI
Bookmark
Share

Authors

CHChristoph HörmannMBMateo de BardeciABAnna Bankwitz

Discussion

Loading...

Member takes

Overview

This observational analysis identifies behavioral differences and classifies individuals with suicide attempts using digital phenotyping data.

Key Points

  • Participants with suicide attempts showed reduced mobility and increased smartphone usage compared to controls.
  • The machine learning model achieved a classification accuracy of 62% and an ROC-AUC of 0.68 for predicting group membership.
  • Analysis revealed significant behavioral differences, particularly in physical activity and smartphone interactions.
  • Findings highlight the potential of digital markers for assessing suicide risk but indicate the need for larger samples and longer observation periods.

Cite This Study

Hörmann et al. (2025) studied this question.

synapsesocial.com/papers/68d41711713b0b5dfea62c25https://doi.org/10.2196/preprints.83848
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A Scoping Review of Smartphone-Based Digital Phenotyping (Preprint)2025
  2. 2Using smartphone-tracked behavioural markers to recognize depression and anxiety symptoms: Digital phenotyping in the Netherlands Study of Depression and Anxiety (Preprint)2025
  3. 3Machine Learning Prediction of Suicidal Ideation in Community-Based Older Adults using Deep Phenotypes2025
  4. 4Digital Phenotyping for Real-Time Monitoring of Nonsuicidal Self-Injury Thoughts2025
  5. 5Phenotyping suicidal behaviour : what could we learn from digital and experimental studies2025