Identifying and characterizing suicide decedent subtypes using deep embedded clustering

Abstract Subtypes of suicide decedents have not been studied at a population level using linked clinical and public health surveillance records. Identifying suicide subtypes can help facilitate the development and deployment of population-level prevention strategies. This retrospective study uses th...

Full description

Saved in:
Bibliographic Details
Main Authors: Anas Belouali, Christopher Kitchen, Ayah Zirikly, Paul Nestadt, Holly C Wilcox, Hadi Kharrazi
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-07007-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849768653888684032
author Anas Belouali
Christopher Kitchen
Ayah Zirikly
Paul Nestadt
Holly C Wilcox
Hadi Kharrazi
author_facet Anas Belouali
Christopher Kitchen
Ayah Zirikly
Paul Nestadt
Holly C Wilcox
Hadi Kharrazi
author_sort Anas Belouali
collection DOAJ
description Abstract Subtypes of suicide decedents have not been studied at a population level using linked clinical and public health surveillance records. Identifying suicide subtypes can help facilitate the development and deployment of population-level prevention strategies. This retrospective study uses the Maryland Suicide Data Warehouse (MSDW). The analyses included 848 individuals who died by suicide as well as 4,161 individuals who died by accident in the state of Maryland between January 1st, 2016, and December 31st, 2019. These individuals had electronic health records from Johns Hopkins Medical Institutes and statewide hospital discharge data. We employed deep embedded clustering and evaluated its performance against traditional clustering approaches. We evaluated different numbers of clusters (k = 2 to 10) and assessed clustering performance using stability metrics, achieving a cross-validated prediction strength of 0.94. We then performed cluster characterization and assessed cluster stability up to 1 year before suicide death. We identified four distinct suicide profiles. Profile 1 (23.2% of suicide cases) included older individuals with high comorbid conditions. Profile 2 (19.2%) was characterized by psychiatric illness, the highest healthcare utilization, and significant social needs. Profile 3 (25.4%) consisted of younger individuals with psychiatric illness, no recorded social needs, and the highest percentage of Medicaid patients. Profile 4 (32.2%) included less clinically engaged individuals with the fewest healthcare visits. Our findings show the effective use of clustering methods to identify meaningful and stable suicide decedent profiles, revealing significant demographic and clinical differences. The identified subtypes can inform population-level suicide prevention strategies.
format Article
id doaj-art-5ad5b4ddface4d01931d333d80879b6e
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-5ad5b4ddface4d01931d333d80879b6e2025-08-20T03:03:42ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-07007-4Identifying and characterizing suicide decedent subtypes using deep embedded clusteringAnas Belouali0Christopher Kitchen1Ayah Zirikly2Paul Nestadt3Holly C Wilcox4Hadi Kharrazi5Division of General Internal Medicine, Biomedical Informatics and Data Science (BIDS), Johns Hopkins School of MedicineDepartment of Health Policy and Management, Center for Population Health Information Technology, Johns Hopkins Bloomberg School of Public HealthCenter for Language and Speech Processing, Johns Hopkins Whiting School of EngineeringDepartment of Mental Health, Johns Hopkins Bloomberg School of Public HealthDepartment of Mental Health, Johns Hopkins Bloomberg School of Public HealthDivision of General Internal Medicine, Biomedical Informatics and Data Science (BIDS), Johns Hopkins School of MedicineAbstract Subtypes of suicide decedents have not been studied at a population level using linked clinical and public health surveillance records. Identifying suicide subtypes can help facilitate the development and deployment of population-level prevention strategies. This retrospective study uses the Maryland Suicide Data Warehouse (MSDW). The analyses included 848 individuals who died by suicide as well as 4,161 individuals who died by accident in the state of Maryland between January 1st, 2016, and December 31st, 2019. These individuals had electronic health records from Johns Hopkins Medical Institutes and statewide hospital discharge data. We employed deep embedded clustering and evaluated its performance against traditional clustering approaches. We evaluated different numbers of clusters (k = 2 to 10) and assessed clustering performance using stability metrics, achieving a cross-validated prediction strength of 0.94. We then performed cluster characterization and assessed cluster stability up to 1 year before suicide death. We identified four distinct suicide profiles. Profile 1 (23.2% of suicide cases) included older individuals with high comorbid conditions. Profile 2 (19.2%) was characterized by psychiatric illness, the highest healthcare utilization, and significant social needs. Profile 3 (25.4%) consisted of younger individuals with psychiatric illness, no recorded social needs, and the highest percentage of Medicaid patients. Profile 4 (32.2%) included less clinically engaged individuals with the fewest healthcare visits. Our findings show the effective use of clustering methods to identify meaningful and stable suicide decedent profiles, revealing significant demographic and clinical differences. The identified subtypes can inform population-level suicide prevention strategies.https://doi.org/10.1038/s41598-025-07007-4
spellingShingle Anas Belouali
Christopher Kitchen
Ayah Zirikly
Paul Nestadt
Holly C Wilcox
Hadi Kharrazi
Identifying and characterizing suicide decedent subtypes using deep embedded clustering
Scientific Reports
title Identifying and characterizing suicide decedent subtypes using deep embedded clustering
title_full Identifying and characterizing suicide decedent subtypes using deep embedded clustering
title_fullStr Identifying and characterizing suicide decedent subtypes using deep embedded clustering
title_full_unstemmed Identifying and characterizing suicide decedent subtypes using deep embedded clustering
title_short Identifying and characterizing suicide decedent subtypes using deep embedded clustering
title_sort identifying and characterizing suicide decedent subtypes using deep embedded clustering
url https://doi.org/10.1038/s41598-025-07007-4
work_keys_str_mv AT anasbelouali identifyingandcharacterizingsuicidedecedentsubtypesusingdeepembeddedclustering
AT christopherkitchen identifyingandcharacterizingsuicidedecedentsubtypesusingdeepembeddedclustering
AT ayahzirikly identifyingandcharacterizingsuicidedecedentsubtypesusingdeepembeddedclustering
AT paulnestadt identifyingandcharacterizingsuicidedecedentsubtypesusingdeepembeddedclustering
AT hollycwilcox identifyingandcharacterizingsuicidedecedentsubtypesusingdeepembeddedclustering
AT hadikharrazi identifyingandcharacterizingsuicidedecedentsubtypesusingdeepembeddedclustering