https://github.com/alexanderquispe/passivesensing-symptoms-networkanalysis

Combining Passive Sensing and Self-Reported Symptoms with Network Analysis to Predict Suicidal Ideation in Medical Residents

https://github.com/alexanderquispe/passivesensing-symptoms-networkanalysis

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (4.3%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Combining Passive Sensing and Self-Reported Symptoms with Network Analysis to Predict Suicidal Ideation in Medical Residents

Basic Info
  • Host: GitHub
  • Owner: alexanderquispe
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 25.9 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme License

README.md

PassiveSensing-Symptoms-NetworkAnalysis

Combining Passive Sensing and Self-Reported Symptoms with Network Analysis to Predict Suicidal Ideation in Medical Residents

Medical residents experience high levels of occupational stress, which elevates their vulnerability to mental health challenges, including suicidal ideation. This study aims to develop a predictive framework for identifying suicide risk in this population by constructing networks from passive sensing data (e.g., step count, sleep metrics) and self-reported mental health assessments (e.g., daily mood ratings, PHQ-9, GAD-7). Using data from the Intern Health Study conducted in 2018–2019, we will employ graph-based machine learning to capture complex, temporal relationships among these behavioral and psychological variables. Key network-derived topological features, such as degree centrality and clustering coefficients, will be extracted and used to train machine learning classifiers. Comparative evaluations of traditional classifiers and advanced graph neural network (GNN) architectures will be conducted to assess both predictive accuracy and interpretability. By using graph-based ML to preserve the networked nature of mental health and behavioral data, this project aims to develop a predictive tool for detecting suicide risk among medical residents, supporting targeted intervention strategies in high-stress professional environments.

Owner

  • Name: Alexander Quispe
  • Login: alexanderquispe
  • Kind: user

GitHub Events

Total
  • Member event: 1
  • Push event: 20
  • Pull request event: 16
  • Create event: 8
Last Year
  • Member event: 1
  • Push event: 20
  • Pull request event: 16
  • Create event: 8