Prediction of Sex-Specific Suicide Risk Using Machine Learning and Single-Payer Health Care Registry Data from Denmark

Jaimie L. Gradus, Anthony J. Rosellini, Erzsébet Horváth-Puhó, Amy E. Street, Isaac Galatzer-Levy, Tammy Jiang, Timothy L. Lash, Henrik T. Sørensen

Research output: Article

1 Citation (Scopus)

Abstract

Importance: Suicide is a public health problem, with multiple causes that are poorly understood. The increased focus on combining health care data with machine-learning approaches in psychiatry may help advance the understanding of suicide risk. Objective: To examine sex-specific risk profiles for death from suicide using machine-learning methods and data from the population of Denmark. Design, Setting, and Participants: A case-cohort study nested within 8 national Danish health and social registries was conducted from January 1, 1995, through December 31, 2015. The source population was all persons born or residing in Denmark as of January 1, 1995. Data were analyzed from November 5, 2018, through May 13, 2019. Exposures: Exposures included 1339 variables spanning domains of suicide risk factors. Main Outcomes and Measures: Death from suicide from the Danish cause of death registry. Results: A total of 14103 individuals died by suicide between 1995 and 2015 (10 152 men [72.0%]; mean [SD] age, 43.5 [18.8] years and 3951 women [28.0%]; age, 47.6 [18.8] years). The comparison subcohort was a 5% random sample (n = 265183) of living individuals in Denmark on January 1, 1995 (130 591 men [49.2%]; age, 37.4 [21.8] years and 134 592 women [50.8%]; age, 39.9 [23.4] years). With use of classification trees and random forests, sex-specific differences were noted in risk for suicide, with physical health more important to men's suicide risk than women's suicide risk. Psychiatric disorders and possibly associated medications were important to suicide risk, with specific results that may increase clarity in the literature. For example, stress disorders among unmarried men older than 30 years were important factors for suicide risk in the presence of depression (risk, 0.54). Generally, diagnoses and medications measured 48 months before suicide were more important indicators of suicide risk than when measured 6 months earlier. Individuals in the top 5% of predicted suicide risk appeared to account for 32.0% of all suicide cases in men and 53.4% of all cases in women. Conclusions and Relevance: Despite decades of research on suicide risk factors, understanding of suicide remains poor. In this study, the first to date to develop risk profiles for suicide based on data from a full population, apparent consistency with what is known about suicide risk was noted, as well as potentially important, understudied risk factors with evidence of unique suicide risk profiles among specific subpopulations..

Original languageEnglish
JournalJAMA Psychiatry
DOIs
Publication statusAccepted/In press - jan. 1 2019

Fingerprint

Denmark
Suicide
Registries
Delivery of Health Care
Machine Learning
Psychiatry
Population
Health

ASJC Scopus subject areas

  • Psychiatry and Mental health

Cite this

Prediction of Sex-Specific Suicide Risk Using Machine Learning and Single-Payer Health Care Registry Data from Denmark. / Gradus, Jaimie L.; Rosellini, Anthony J.; Horváth-Puhó, Erzsébet; Street, Amy E.; Galatzer-Levy, Isaac; Jiang, Tammy; Lash, Timothy L.; Sørensen, Henrik T.

In: JAMA Psychiatry, 01.01.2019.

Research output: Article

Gradus, Jaimie L. ; Rosellini, Anthony J. ; Horváth-Puhó, Erzsébet ; Street, Amy E. ; Galatzer-Levy, Isaac ; Jiang, Tammy ; Lash, Timothy L. ; Sørensen, Henrik T. / Prediction of Sex-Specific Suicide Risk Using Machine Learning and Single-Payer Health Care Registry Data from Denmark. In: JAMA Psychiatry. 2019.
@article{6b329fd02a9d4fa29ada32b7f4efc181,
title = "Prediction of Sex-Specific Suicide Risk Using Machine Learning and Single-Payer Health Care Registry Data from Denmark",
abstract = "Importance: Suicide is a public health problem, with multiple causes that are poorly understood. The increased focus on combining health care data with machine-learning approaches in psychiatry may help advance the understanding of suicide risk. Objective: To examine sex-specific risk profiles for death from suicide using machine-learning methods and data from the population of Denmark. Design, Setting, and Participants: A case-cohort study nested within 8 national Danish health and social registries was conducted from January 1, 1995, through December 31, 2015. The source population was all persons born or residing in Denmark as of January 1, 1995. Data were analyzed from November 5, 2018, through May 13, 2019. Exposures: Exposures included 1339 variables spanning domains of suicide risk factors. Main Outcomes and Measures: Death from suicide from the Danish cause of death registry. Results: A total of 14103 individuals died by suicide between 1995 and 2015 (10 152 men [72.0{\%}]; mean [SD] age, 43.5 [18.8] years and 3951 women [28.0{\%}]; age, 47.6 [18.8] years). The comparison subcohort was a 5{\%} random sample (n = 265183) of living individuals in Denmark on January 1, 1995 (130 591 men [49.2{\%}]; age, 37.4 [21.8] years and 134 592 women [50.8{\%}]; age, 39.9 [23.4] years). With use of classification trees and random forests, sex-specific differences were noted in risk for suicide, with physical health more important to men's suicide risk than women's suicide risk. Psychiatric disorders and possibly associated medications were important to suicide risk, with specific results that may increase clarity in the literature. For example, stress disorders among unmarried men older than 30 years were important factors for suicide risk in the presence of depression (risk, 0.54). Generally, diagnoses and medications measured 48 months before suicide were more important indicators of suicide risk than when measured 6 months earlier. Individuals in the top 5{\%} of predicted suicide risk appeared to account for 32.0{\%} of all suicide cases in men and 53.4{\%} of all cases in women. Conclusions and Relevance: Despite decades of research on suicide risk factors, understanding of suicide remains poor. In this study, the first to date to develop risk profiles for suicide based on data from a full population, apparent consistency with what is known about suicide risk was noted, as well as potentially important, understudied risk factors with evidence of unique suicide risk profiles among specific subpopulations..",
author = "Gradus, {Jaimie L.} and Rosellini, {Anthony J.} and Erzs{\'e}bet Horv{\'a}th-Puh{\'o} and Street, {Amy E.} and Isaac Galatzer-Levy and Tammy Jiang and Lash, {Timothy L.} and S{\o}rensen, {Henrik T.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1001/jamapsychiatry.2019.2905",
language = "English",
journal = "JAMA Psychiatry",
issn = "2168-622X",
publisher = "American Medical Association",

}

TY - JOUR

T1 - Prediction of Sex-Specific Suicide Risk Using Machine Learning and Single-Payer Health Care Registry Data from Denmark

AU - Gradus, Jaimie L.

AU - Rosellini, Anthony J.

AU - Horváth-Puhó, Erzsébet

AU - Street, Amy E.

AU - Galatzer-Levy, Isaac

AU - Jiang, Tammy

AU - Lash, Timothy L.

AU - Sørensen, Henrik T.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Importance: Suicide is a public health problem, with multiple causes that are poorly understood. The increased focus on combining health care data with machine-learning approaches in psychiatry may help advance the understanding of suicide risk. Objective: To examine sex-specific risk profiles for death from suicide using machine-learning methods and data from the population of Denmark. Design, Setting, and Participants: A case-cohort study nested within 8 national Danish health and social registries was conducted from January 1, 1995, through December 31, 2015. The source population was all persons born or residing in Denmark as of January 1, 1995. Data were analyzed from November 5, 2018, through May 13, 2019. Exposures: Exposures included 1339 variables spanning domains of suicide risk factors. Main Outcomes and Measures: Death from suicide from the Danish cause of death registry. Results: A total of 14103 individuals died by suicide between 1995 and 2015 (10 152 men [72.0%]; mean [SD] age, 43.5 [18.8] years and 3951 women [28.0%]; age, 47.6 [18.8] years). The comparison subcohort was a 5% random sample (n = 265183) of living individuals in Denmark on January 1, 1995 (130 591 men [49.2%]; age, 37.4 [21.8] years and 134 592 women [50.8%]; age, 39.9 [23.4] years). With use of classification trees and random forests, sex-specific differences were noted in risk for suicide, with physical health more important to men's suicide risk than women's suicide risk. Psychiatric disorders and possibly associated medications were important to suicide risk, with specific results that may increase clarity in the literature. For example, stress disorders among unmarried men older than 30 years were important factors for suicide risk in the presence of depression (risk, 0.54). Generally, diagnoses and medications measured 48 months before suicide were more important indicators of suicide risk than when measured 6 months earlier. Individuals in the top 5% of predicted suicide risk appeared to account for 32.0% of all suicide cases in men and 53.4% of all cases in women. Conclusions and Relevance: Despite decades of research on suicide risk factors, understanding of suicide remains poor. In this study, the first to date to develop risk profiles for suicide based on data from a full population, apparent consistency with what is known about suicide risk was noted, as well as potentially important, understudied risk factors with evidence of unique suicide risk profiles among specific subpopulations..

AB - Importance: Suicide is a public health problem, with multiple causes that are poorly understood. The increased focus on combining health care data with machine-learning approaches in psychiatry may help advance the understanding of suicide risk. Objective: To examine sex-specific risk profiles for death from suicide using machine-learning methods and data from the population of Denmark. Design, Setting, and Participants: A case-cohort study nested within 8 national Danish health and social registries was conducted from January 1, 1995, through December 31, 2015. The source population was all persons born or residing in Denmark as of January 1, 1995. Data were analyzed from November 5, 2018, through May 13, 2019. Exposures: Exposures included 1339 variables spanning domains of suicide risk factors. Main Outcomes and Measures: Death from suicide from the Danish cause of death registry. Results: A total of 14103 individuals died by suicide between 1995 and 2015 (10 152 men [72.0%]; mean [SD] age, 43.5 [18.8] years and 3951 women [28.0%]; age, 47.6 [18.8] years). The comparison subcohort was a 5% random sample (n = 265183) of living individuals in Denmark on January 1, 1995 (130 591 men [49.2%]; age, 37.4 [21.8] years and 134 592 women [50.8%]; age, 39.9 [23.4] years). With use of classification trees and random forests, sex-specific differences were noted in risk for suicide, with physical health more important to men's suicide risk than women's suicide risk. Psychiatric disorders and possibly associated medications were important to suicide risk, with specific results that may increase clarity in the literature. For example, stress disorders among unmarried men older than 30 years were important factors for suicide risk in the presence of depression (risk, 0.54). Generally, diagnoses and medications measured 48 months before suicide were more important indicators of suicide risk than when measured 6 months earlier. Individuals in the top 5% of predicted suicide risk appeared to account for 32.0% of all suicide cases in men and 53.4% of all cases in women. Conclusions and Relevance: Despite decades of research on suicide risk factors, understanding of suicide remains poor. In this study, the first to date to develop risk profiles for suicide based on data from a full population, apparent consistency with what is known about suicide risk was noted, as well as potentially important, understudied risk factors with evidence of unique suicide risk profiles among specific subpopulations..

UR - http://www.scopus.com/inward/record.url?scp=85074196487&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074196487&partnerID=8YFLogxK

U2 - 10.1001/jamapsychiatry.2019.2905

DO - 10.1001/jamapsychiatry.2019.2905

M3 - Article

C2 - 31642880

AN - SCOPUS:85074196487

JO - JAMA Psychiatry

JF - JAMA Psychiatry

SN - 2168-622X

ER -