Abstract
Objective: To identify and compare predictors of nonfatal and fatal suicidal events within 180 days of emergency department (ED) visits for mental health disorders.
Methods: This longitudinal cohort analysis assessed risk of nonfatal and fatal suicide events among a national sample of 511,559 patients presenting to an ED between 2015 and 2022 with 1 or more mental health disorder. Machine learning models were used to predict events incorporating demographic and clinical characteristics, incremental value of clinical feature sets, feature importance rankings across models, and accuracy with which a model trained to predict nonfatal outcomes predicted suicide deaths. Nonfatal attempts within 6 months of an ED visit were identified using electronic health records (n=4,525), while fatal events were identified from the National Death Index (n=434).
Results: The final sample of 872,627 ED episodes represented 511,559 individuals. The full model with 143 features achieved stronger performance for nonfatal events (area under the curve [AUC]=0.874) than for suicide deaths (AUC=0.787). The relative importance of features was highly correlated across models (r=0.82), with 73% of overlap between the top 15 predictors for nonfatal and fatal events. When the nonfatal model was applied to fatal outcomes on the same sample, performance declined (AUC=0.724), indicating limited generalizability despite similar predictors (sensitivity=78.1%, specificity=67.3%).
Conclusions: Although nonfatal and fatal suicidal events share predictors, their predictive strength and function differ. These differences underscore challenges in using models trained on nonfatal outcomes to identify risk of suicide death and contribute to the ongoing debate over whether suicidal thoughts and behaviors reflect a continuum of severity or distinct clinical pathways.
J Clin Psychiatry 2026;87(2):25m16070
Author affiliations are listed at the end of this article.
Members Only Content
This full article is available exclusively to Professional tier members. Subscribe now to unlock the HTML version and gain unlimited access to our entire library plus all PDFs. If you're already a subscriber, please log in below to continue reading.
References (44)
- Ahmedani B, Westphal J, Autio K, et al. Variation in patterns of health care before suicide: a population case-control study. Prev Med. 2019;127:105796. PubMed CrossRef
- Ahmedani B, Simon G, Stewart C, et al. Health care contacts in the year before suicide death. J Gen Intern Med. 2014;29(6):870–877. PubMed CrossRef
- Owens PL, Fingar KR, Heslin KC, et al. Emergency Department Visits Related to Suicidal Ideation, 2006–2013. In: Healthcare Cost and Utilization Project (HCUP) Statistical Briefs [Internet]. Agency for Healthcare Research and Quality (US; 2006.
- Olfson M, Gao Y, Xie M, et al. Suicide risk among adults with mental health emergency department visits with and without suicidal symptoms. J Clin Psychiatry. 2021;82(6):20m13833. PubMed CrossRef
- Marcus S, Cullen S, Schmutte T, et al. A cohort study of predictors of short-term nonfatal suicidal and self-harm events among individuals with mental health disorders treated in the emergency department. J Psych Res. 2025;186:458–468. https://doi.org/10.1016/j.jpsychires.2025.04.035 PubMed CrossRef
- Nock M, Hwang I, Sampson N, et al. Mental disorders, comorbidity and suicidal behavior: results from the National Comorbidity Survey Replication. Mol Psychiatr. 2010;15(8):868–876. PubMed CrossRef
- Nordentoft M, Mortensen P, Pedersen C. Absolute risk of suicide after first hospital contact in mental disorder. Archives Gen Psychiatry. 2011;68(10):1058–1064. PubMed CrossRef
- Hoertel N, Franco S, Wall M, et al. Mental disorders and risk of suicide attempt: a national prospective study. Mol Psychiatr. 2015;20(6):718–726. PubMed CrossRef
- Tran T, Luo W, Phung D, et al. Risk stratification using data from electronic medical records better predicts suicide risks than clinician assessments. BMC Psychiatry. 2014;14(1):76. PubMed CrossRef
- McCarthy J, Bossarte R, Katz I, et al. Predictive modeling and concentration of the risk of suicide: implications for preventive interventions in the US Department of Veterans Affairs. Am J Public Health. 2015;105(9):1935–1942. PubMed CrossRef
- Barak-Corren Y, Castro V, Javitt S, et al. Predicting suicidal behavior from longitudinal electronic health records. Am J Psychiatr. 2017;174(2):154–162. PubMed CrossRef
- Kessler R, Warner C, Ivany C, et al. Predicting suicides after psychiatric hospitalization in US Army soldiers: the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS). JAMA Psychiatry. 2015;72(1):49–57. PubMed CrossRef
- Burke T, Ammerman B, Jacobucci R. The use of machine learning in the study of suicidal and non-suicidal self-injurious thoughts and behaviors: a systematic review. J Affect Disord. 2019;245:869–884. PubMed CrossRef
- Nordin N, Zainol Z, Noor M, et al. Suicidal behaviour prediction models using machine learning techniques: a systematic review. Artif Intell Med. 2022;132. https://doi.org/10.1016/j.artmed.2022.102395
- Simon G, Johnson E, Shortreed S, et al. Predicting suicide death after emergency department visits with mental health or self-harm diagnoses. Gen Hosp Psychiatry. 2024;87:13–19. PubMed CrossRef
- Nielsen S, Christensen R, Madsen T, et al. Prediction models of suicide and non-fatal suicide attempt after discharge from a psychiatric inpatient stay: a machine learning approach on nationwide Danish registers. Acta Psychiatr Scand. 2023;148(6):525–537. PubMed CrossRef
- Klonsky E, May A, Saffer B. Suicide, suicide attempts, and suicide ideation. Ann Rev Psychol. 2016;12:307–330. PubMed CrossRef
- Ribeiro J, Franklin J, Fox K, et al. Self-injurious thoughts and behaviors as risk factors for future suicide ideation, attempts, and death: a meta-analysis of longitudinal studies. Psychol Med. 2016;46(2):225–236. PubMed CrossRef
- Optum Labs. Optum labs and Optum Labs Data Warehouse (OLDW) descriptions and citation.
- Wojcik N, Huebner W, Jorgensen G. Strategies for using the National Death Index and the Social Security Administration for death ascertainment in large occupational cohort mortality studies. Am J Epidemiol. 2010;172(4):469–477. PubMed CrossRef
- Ivey-Stephenson A, Crosby A, Jack S, et al. Suicide trends among and within urbanization levels by sex, race/ethnicity, age group, and mechanism of death—United States, 2001–2015. MMWR Surveill Summ. 2017;66(18):1–16. PubMed CrossRef
- Gili M, Castellvi P, Vives M, et al. Mental disorders as risk factors for suicidal behavior in young people: a meta-analysis and systematic review of longitudinal studies. J Affect Disord. 2019;245:152–162. PubMed CrossRef
- Agency for Healthcare Research and Quality. DXCSSR Reference File. 2024. https://hcup-us.ahrq.gov/toolssoftware/ccsr/DXCCSR-Reference-File-v2024-1.xlsx Accessed June 11, 2024
- Ahmedani BK, Peterson EL, Hu Y, et al. Major physical health conditions and risk of suicide. Am J Prev Med. 2017;53(3):308–315. PubMed CrossRef
- Scott K, Hwang I, Chiu W-TA, et al. Chronic physical conditions and their association with first onset of suicidal behavior in the world mental health surveys. Psychosom Med. 2010;72(7):712–719. PubMed CrossRef
- Qato D, Ozenberger K, Olfson M. Prevalence of prescription medications with depression as a potential adverse effect among adults in the United States. JAMA. 2018;319(22):2289–2298. PubMed CrossRef
- Liu T, Ungar L. Towards Cotenable and Causal Shapley Feature Explanations. In: AAAI 2021 Workshop: Trustworthy AI for Healthcare; 2021.
- Youden W. Index for rating diagnostic tests. Cancer. 1950;3(1):32–35. PubMed CrossRef
- Wang C, Wu Q, Weimer M, et al. FLAML: a fast and lightweight AutoML Library. In: 4th MLSys Conference; 2021. https://www.microsoft.com/en-us/research/wp-content/uploads/2021/03/MLSys21FLAML.pdf
- Bernert R, Kim J, Iwata N, et al. Sleep disturbances as an evidence-based suicide risk factor. Curr Psychiatry Rep. 2015;17(3):554–569. PubMed CrossRef
- Pigeon W, Pinquart M, Conner K. Meta-analysis of sleep disturbance and suicidal thoughts and behaviors. J Clin Psychiatry. 2012;73(9):e1160–e1167. PubMed CrossRef
- Drapeau C, Nadorff M. Suicidality in sleep disorders: prevalence, impact, and management strategies. Nat Sci Sleep. 2017;9:213–226. PubMed CrossRef
- Morin C, Belleville G, Bélanger L, et al. The Insomnia Severity Index: psychometric indicators to detect cases and evaluate treatment response. Sleep. 2011;34(5):601–608. PubMed CrossRef
- Larney S, Train L, Leung J, et al. All cause and cause-specific mortality among people using extra medical opioids: a systematic review and meta-analysis. JAMA Psychiatry. 2019;77(5):1–10.
- Miller T, Swedler D, Lawrence B, et al. Incidence and lethality of suicidal overdoses by drug class. JAMA Netw Open. 2020;3(3):e200607. PubMed CrossRef
- Mergl R, Koburger N, Heinrichs K, et al. What are reasons for the large gender differences in the lethality of suicidal acts? An epidemiological analysis in four European countries. PLoS One. 2015;10(7):e0129062. PubMed CrossRef
- Nguyen B, Lyons B, Forsberg K, et al. Surveillance for violent deaths — National Violent Death Reporting System, 48 states, the District of Columbia, and Puerto Rico, 2021. MMWR Surveill Summ. 2024;73(5):1–44. PubMed CrossRef
- Bostwick J, Pabbati C, Geske J, et al. Suicide attempt as a risk factor for completed suicide: even more lethal than we knew. Am J Psychiatry. 2016;173(11):1094–1100. PubMed CrossRef
- Haroz E, Kitche C, Nestadt P, et al. Comparing the predictive value of screening to the use of electronic health record data for detecting future suicidal thoughts and behavior in an urban pediatric emergency department: a preliminary analysis. Sui Life Threaten Behav. 2021;51:1189–1202.
- Nock M, Millner A, Ross E, et al. Prediction of suicide attempts using clinician assessment, patient self-report, and electronic health records. JAMA Netw Open. 2022;5(1):e2144373. PubMed CrossRef
- Oquendo M, Wall M, Wang S, et al. Lifetime suicide attempts in healthy volunteers: results from a national epidemiological study. JAMA Psychiatry. 2024;81(6):572–578. PubMed CrossRef
- Posner K, Brown G, Stanley B, et al. The Columbia-Suicide Severity Rating Scale: initial validity and internal consistency findings from three multisite studies with adolescents and adults. Am J Psychiatry. 2011;168(12):1266–1277. PubMed CrossRef
- Joiner T, Van Orden K, Witte T, et al. Main predictions of the interpersonal–psychological theory of suicidal behavior: empirical tests in two samples of young adults. J Abnorm Psychol. 2009;118(3):634–646. PubMed CrossRef
- Klonsky E, May A. The Three Step Theory (3ST): a new theory of suicide rooted in the “ideation to action” framework. Int J Cog Ther. 2015;2(8):114–129. CrossRef
