Automated detection and prediction of suicidal behavior from clinical notes using deep learning
PLOS One · 2025
DOI: 10.1371/journal.pone.0331459 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Brian E Bunnell und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry and Behavioral Neurosciences, Morsani College of Medicine, University of South Florida, Tampa, Florida, United States of Ame…. Hauptthemen laut MEDLINE: Deep Learning, Self-Injurious Behavior, Suicide. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institute of Mental Health and Neurosciences, National Center for Advancing Translational Sciences.
Abstract (Originalsprache)
Background
Deep learning approaches have tremendous potential to improve the predictive power of traditional suicide prediction models to detect and predict intentional self-harm (ISH). Existing research is limited by a general lack of consistent performance and replicability across sites. We aimed to validate a deep learning approach used in previous research to detect and predict ISH using clinical note text and evaluate its generalizability to other academic medical centers.
Methods
We extracted clinical notes from electronic health records (EHRs) of 1,538 patients with International Classification of Diseases codes for ISH and 3,012 matched controls without ISH codes. We evaluated the performance of two traditional bag-of-words models (i.e., Naïve Bayes, Random Forest) and two convolutional neural network (CNN) models including randomly initialized (CNNr) and pre-trained Word2Vec initialized (CNNw) weights to detect ISH within 24 hours of and predict ISH from clinical notes 1–6 months before the first ISH event.
Results
In detecting concurrent ISH, both CNN models outperformed bag-of-words models with AUCs of.99 and F1 scores of 0.94. In predicting future ISH, the CNN models outperformed Naïve Bayes models with AUCs of 0.81–0.82 and F1 scores of 0.61−.64.
Conclusions
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Psychiatry and Behavioral Neurosciences, Morsani College of Medicine, University of South Florida, Tampa, Florida, United States of America.
- Research Methodology and Biostatistics Core, Office of Research, Morsani College of Medicine, University of South Florida, Tampa, Florida, United States of America.
- Biomedical Informatics Center, Medical University of South Carolina, Charleston, South Carolina, United States of America.
- Department of Public Health Sciences, Medical University of South Carolina, Charleston, South Carolina, United States of America.
ORCID-Profile: Athanasios Tsalatsanis, Chaitanya Chaphalkar, Jihad S Obeid
Förderung
- National Institute of Mental Health and Neurosciences
- National Center for Advancing Translational Sciences
Zitieren
APA
Bunnell, B. E., Tsalatsanis, A., Chaphalkar, C., Robinson, S., Klein, S., Cool, S., Szwast, E., Heider, P. M., Wolf, B. J., & Obeid, J. S. (2025). Automated detection and prediction of suicidal behavior from clinical notes using deep learning. PLOS One. https://doi.org/10.1371/journal.pone.0331459
Vancouver
Bunnell BE, Tsalatsanis A, Chaphalkar C, Robinson S, Klein S, Cool S, et al. Automated detection and prediction of suicidal behavior from clinical notes using deep learning. PLOS One. 2025. doi:10.1371/journal.pone.0331459
BibTeX
@article{Bunnell2025,
author = {Bunnell, Brian E and Tsalatsanis, Athanasios and Chaphalkar, Chaitanya and Robinson, Sara and Klein, Sierra and Cool, Sarah and Szwast, Elizabeth and Heider, Paul M and Wolf, Bethany J and Obeid, Jihad S},
title = {Automated detection and prediction of suicidal behavior from clinical notes using deep learning},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0331459}
}
EUVIMED