Life events extraction from healthcare notes for veteran acute suicide risk prediction
Journal of the American Medical Informatics Association · 01.04.2026 · 33 (4) · 812-820
DOI: 10.1093/jamia/ocaf197 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 16.03.2026. Verfasst von Destinee Morrow und 7 weiteren Autor:innen. Beteiligte Einrichtung: Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, United States. Hauptthemen laut MEDLINE: Electronic Health Records, Machine Learning, Natural Language Processing, Suicide. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: BLRD VA, Million Veteran Program, Office of Research and Development, Veterans Health Administration.
Abstract (Originalsprache)
Objective
Predictive models of suicide risk have focused on features extracted from structured data found in electronic health records, with limited consideration of predisposing life events (LE) expressed in unstructured clinical text such as housing instability and marital troubles. This study aims to expand upon previous research, demonstrating how high-performance computing (HPC) and machine learning methodologies can be used to extract and annotate 8 LE across all Veterans Health Administration (VHA) unstructured clinical text data with enriched performance metrics. Integration of the 8 LE with the structured features using different statistical and machine learning (ML) methods is also discussed. Materials/Methods VHA-wide clinical text from January 2000 to January 2022 was pre-processed and analyzed using HPC. Data-driven lexicon curation enabled a rule-based annotator to extract LE, followed by machine learning for improved positive predictive value (PPV). NLP results were analyzed longitudinally and then integrated and compared to a baseline statistical model predicting risk for a combined outcome (suicide death, suicide attempt and overdose).
Results
First-time LE mentions showed a significant temporal correlation to suicide-related events (SRE) (suicide ideation, attempt and/or death) and are not associated with administrative bias. Predictive linear regression (LR) models integrating NLP-derived LE show an improved AUC of 0.81 and novel patient identification of up to 18%.
Discussion
Our analysis shows that these methodologies helped improve performance metrics significantly from previous work, while outperforming related works. These results demonstrated that NLP-derived LE served as acute predictors for SRE.
Conclusion
NLP integration into predictive models may help improve clinician decision support. Future work is necessary to better define and integrate these and other potential LE.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, United States.
- Los Alamos National Laboratory, Los Alamos, NM 87545, United States.
- VA Mid-Atlantic Mental Illness Research, Education, and Clinical Center, Durham Veterans Affairs Health Care System, Durham, NC 27705, United States.
- Department of Psychiatry and Behavioral Sciences, Duke University School of Medicine, Durham, NC 27705, United States.
ORCID-Profile: Destinee Morrow
Förderung
- BLRD VA
- Million Veteran Program, Office of Research and Development
- Veterans Health Administration
- VA Research Career Scientist
- Million Veteran Program
- VA Senior RCS
- CSRD VA
- Office of Research and Development
Zitieren
APA
Morrow, D., Zamora-Resendiz, R., Dhaubhadel, S., Beckham, J. C., Kimbrel, N. A., McMahon, B. H., VA Million Veteran Program, & Crivelli, S. (2026). Life events extraction from healthcare notes for veteran acute suicide risk prediction. Journal of the American Medical Informatics Association, 33(4), 812-820. https://doi.org/10.1093/jamia/ocaf197
Vancouver
Morrow D, Zamora-Resendiz R, Dhaubhadel S, Beckham JC, Kimbrel NA, McMahon BH, et al. Life events extraction from healthcare notes for veteran acute suicide risk prediction. Journal of the American Medical Informatics Association. 2026;33(4):812-820. doi:10.1093/jamia/ocaf197
BibTeX
@article{Morrow2026,
author = {Morrow, Destinee and Zamora-Resendiz, Rafael and Dhaubhadel, Sayera and Beckham, Jean C and Kimbrel, Nathan A and McMahon, Benjamin H and VA Million Veteran Program, VA Million Veteran Program and Crivelli, Silvia},
title = {Life events extraction from healthcare notes for veteran acute suicide risk prediction},
journal = {Journal of the American Medical Informatics Association},
year = {2026},
volume = {33},
number = {4},
pages = {812--820},
doi = {10.1093/jamia/ocaf197}
}
EUVIMED