Automated detection and prediction of suicidal behavior from clinical notes using deep learning
We demonstrated that leveraging EHRs with a well-defined set of ISH ICD codes to train deep learning models to detect and predict ISH using clinical note text is feasible and replicable at more than one institution. Future work will examine this approach across multiple sites under less controlled settings using both structured and unstructured EHR data.
Authors
- Jihad S. Obeid (ORCID: https://orcid.org/0000-0002-7193-7779)
- Elizabeth Szwast
- Sarah Cool
- Athanasios Tsalatsanis (ORCID: https://orcid.org/0000-0003-3818-8283)
- Paul M. Heider (ORCID: https://orcid.org/0000-0002-1589-4567)
- Brian E. Bunnell (ORCID: https://orcid.org/0000-0002-4964-0688)
- Sara Robinson
- Sierra Klein
- Bethany J. Wolf (ORCID: https://orcid.org/0000-0002-7124-5158)
- Chaitanya Chaphalkar (ORCID: https://orcid.org/0009-0003-5166-7606)
Institutions
- Medical University of South Carolina (US)
- University of South Florida (US)
Publication Details
- Journal
- PLoS ONE
- Published
- 2025-09-15
- DOI
- https://doi.org/10.1371/journal.pone.0331459
- Citations
- 2
- Primary Topic
- Mental Health via Writing
- Type
- article
- Field-Weighted Citation Impact
- 4.88