Computing 3‐Step Theory of Suicide Factor Scores From Veterans Health Administration Clinical Progress Notes
Suicide and Life-Threatening Behavior · 2025
DOI: 10.1111/sltb.70004 ↗Kurz gefasst
Fachartikel in der Zeitschrift Suicide and Life-Threatening Behavior, 2025. Verfasst von Esther L Meerwijk und 6 weiteren Autor:innen. Beteiligte Einrichtung: VA Health Systems Research, Center for Innovation to Implementation (Ci2i), VA Palo Alto Health Care System, Menlo Park, California, USA. Hauptthemen laut MEDLINE: Suicide, Natural Language Processing, Veterans. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: HSRD VA, U.S. Veterans Health Administration Research & Development.
Abstract (Originalsprache)
Background
Literature on how to translate information extracted from clinical progress notes into numeric scores for 3‐step theory of suicide (3ST) factors is nonexistent. We determined which scoring option would best discriminate between patients who will attempt or die by suicide and patients with neither suicidal ideation nor attempts, and we tested hypotheses related to the 3ST.
Methods
We used terminology‐driven natural language processing (NLP) to extract information from Veterans Health Administration (VHA) clinical progress notes. Counts of those extractions served as input to evaluate candidate scoring options for each 3ST factor (psychological pain, hopelessness, connectedness, capability for suicide). Logistic regression models adjusted for common demographic characteristics were used to test the 3ST hypotheses.
Results
Optimal contrasts between groups were obtained with P − A for psychological pain, hopelessness, and capability for suicide, and for connectedness, where P and A , respectively, indicate the patient‐level number of extractions indicating presence and absence of the factor.
Limitations
Additional research is necessary to verify whether our conclusions hold in a cohort that is more reflective of the general VHA population.
Conclusion
Terminology‐driven 3ST factor scores discriminate patients who attempt or die by suicide from patients without suicidal ideation or attempts. Our results corroborate the validity of the 3ST for VHA patients.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- VA Health Systems Research, Center for Innovation to Implementation (Ci2i), VA Palo Alto Health Care System, Menlo Park, California, USA.
- VA National Center on Homelessness Among Veterans, USA.
- Division of Health Systems Science, Department of Medicine, UMass Chan Medical School, Worcester, Massachusetts, USA.
- VA Tennessee Valley Healthcare System, Nashville, Tennessee, USA.
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
- Department of Medicine, Stanford University, Stanford, California, USA.
ORCID-Profile: Esther L Meerwijk
Förderung
- HSRD VA
- U.S. Veterans Health Administration Research & Development
Zitieren
APA
Meerwijk, E. L., Shotqara, A. S., Finlay, A. K., Reeves, R. M., Tamang, S. R., Ilgen, M. A., & Harris, A. H. S. (2025). Computing 3‐Step Theory of Suicide Factor Scores From Veterans Health Administration Clinical Progress Notes. Suicide and Life-Threatening Behavior. https://doi.org/10.1111/sltb.70004
Vancouver
Meerwijk EL, Shotqara AS, Finlay AK, Reeves RM, Tamang SR, Ilgen MA, et al. Computing 3‐Step Theory of Suicide Factor Scores From Veterans Health Administration Clinical Progress Notes. Suicide and Life-Threatening Behavior. 2025. doi:10.1111/sltb.70004
BibTeX
@article{Meerwijk2025,
author = {Meerwijk, Esther L and Shotqara, Asqar S and Finlay, Andrea K and Reeves, Ruth M and Tamang, Suzanne R and Ilgen, Mark A and Harris, Alex H S},
title = {Computing 3‐Step Theory of Suicide Factor Scores From Veterans Health Administration Clinical Progress Notes},
journal = {Suicide and Life-Threatening Behavior},
year = {2025},
doi = {10.1111/sltb.70004}
}
EUVIMED