A Review of Suicide-Related Risks through Propensity Score Methods using the Maryland Suicide Data Warehouse
- 1Johns Hopkins University, School of Public Health
Abstract
ObjectiveA diversity of approaches and cohorts have been published in research literature for suicide risk estimation, leading to some uncertainty around which factors and conditions are most strongly contributing to risk. Methods exist for weighting estimates by propensity score, removing simplifying the interpretation of model effects. Few studies have explored the use of these tools to assess when the effect of certain factors is uncertain or inconsistent.
MethodA mix of 1,001,737 suicide decedents and living patients were evaluated for suicide risk, relying on a subset of commonly identified factors: demographics, psychiatric conditions, substance use disorders, and social needs. Care utilization patterns were then assessed controlling for these factors in a hospital care setting. Four methods were considered for controlling multivariate confounding of odds predicting death by suicide: multivariate logistic regression, 1-to-1 sample matching, inverse propensity weighting (IPTW), and entropy balancing (EBAL).
ResultsTest statistics showed suicide decedents were much more likely to have various psychiatric and substance use diagnoses, social needs and more likely to heightened care utilization across sampling intervals. Greater utilization was found close to date of death. Effect sizes after IPTW and EBAL weighting were also generally greater than would have been documented by regression alone.
ConclusionsPropensity weighting is a useful alternative to exploring nuanced effects, especially when the direction and strength of an association differ from traditional statistics. By weighting, the overall imbalance of cases remains consistent and effect terms might reflect more nuanced associations than regression or sample matching alone.
Related
- Suicide-Related Responses From AI Chatbots Through Application Programming Interfaces and Consumer-Facing Apps: Observational Cross-Sectional Comparative Study.
- Low-threshold secondary and tertiary suicide prevention measures for individuals with suicid-related thoughts and behaviors: a scoping review
- Suicide‐Related Medical Claims, Downstream Healthcare Costs, and the Economic Impact of Enhanced Outpatient Services
- Gambling-related suicide and serious suicide attempts in the United Kingdom: a psychological autopsy and qualitative investigation
- Characterizing Use of the Internet and Social Media to Access Suicide-Related Content among Adolescents with Suicidal Ideation
BibTeX
@misc{kitchen2026review,
title = {{A Review of Suicide-Related Risks through Propensity Score Methods using the Maryland Suicide Data Warehouse}},
author = {C. Kitchen and J. Kush and A. Zirikly and A. Belouali and P. Nestadt and H. Wilcox and H. Kharrazi},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.19.26364526},
url = {https://www.medrxiv.org/content/10.64898/2026.10.19.26364526v1},
note = {CC0},
}
RIS
TY - UNPB
TI - A Review of Suicide-Related Risks through Propensity Score Methods using the Maryland Suicide Data Warehouse
AU - C. Kitchen
AU - J. Kush
AU - A. Zirikly
AU - A. Belouali
AU - P. Nestadt
AU - H. Wilcox
AU - H. Kharrazi
PY - 2026
DA - 2026/10/19
PB - medRxiv
DO - 10.64898/2026.10.19.26364526
UR - https://www.medrxiv.org/content/10.64898/2026.10.19.26364526v1
AB - ObjectiveA diversity of approaches and cohorts have been published in research literature for suicide risk estimation, leading to some uncertainty around which factors and conditions are most strongly contributing to risk. Methods exist for weighting estimates by propensity score, removing simplifying the interpretation of model effects. Few studies have explored the use of these tools to assess when the effect of certain factors is uncertain or inconsistent. MethodA mix of 1,001,737 suicide decedents and living patients were evaluated for suicide risk, relying on a subset of commonly identified factors: demographics, psychiatric conditions, substance use disorders, and social needs. Care utilization patterns were then assessed controlling for these factors in a hospital care setting. Four methods were considered for controlling multivariate confounding of odds predicting death by suicide: multivariate logistic regression, 1-to-1 sample matching, inverse propensity weighting (IPTW), and entropy balancing (EBAL). ResultsTest statistics showed suicide decedents were much more likely to have various psychiatric and substance use diagnoses, social needs and more likely to heightened care utilization across sampling intervals. Greater utilization was found close to date of death. Effect sizes after IPTW and EBAL weighting were also generally greater than would have been documented by regression alone. ConclusionsPropensity weighting is a useful alternative to exploring nuanced effects, especially when the direction and strength of an association differ from traditional statistics. By weighting, the overall imbalance of cases remains consistent and effect terms might reflect more nuanced associations than regression or sample matching alone.
ER -