No Cover Image

Journal article 565 views 98 downloads

Identifying long-term and imminent suicide predictors in a general population and a clinical sample with machine learning

Lloyd Balbuena Orcid Logo, Marilyn Baetz, Joseph Andrew Sexton, Douglas Harder, Cindy Xin Feng, Kerstina Boctor, Candace LaPointe, Elizabeth Letwiniuk, Arash Shamloo, Hemant Ishwaran, Ann John Orcid Logo, Anne Lise Brantsæter

BMC Psychiatry, Volume: 22, Issue: 1, Start page: 120

Swansea University Authors: Lloyd Balbuena Orcid Logo, Ann John Orcid Logo

  • 12888_2022_Article_3702.pdf

    PDF | Version of Record

    © The Author(s) 2022. This article is licensed under a Creative Commons Attribution 4.0 International License

    Download (637.79KB)

Check full text

DOI (Published version): 10.1186/s12888-022-03702-y

Abstract

Background: Machine learning (ML) is increasingly used to predict suicide deaths but their value for suicide prevention has not been established. Our first objective was to identify risk and protective factors in a general population. Our second objective was to identify factors indicating imminent...

Full description

Published in: BMC Psychiatry
ISSN: 1471-244X
Published: Springer Science and Business Media LLC 2022
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa59416
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2022-02-16T16:10:06Z
last_indexed 2022-02-17T04:26:44Z
id cronfa59416
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2022-02-16T16:13:08.1856404</datestamp><bib-version>v2</bib-version><id>59416</id><entry>2022-02-16</entry><title>Identifying long-term and imminent suicide predictors in a general population and a clinical sample with machine learning</title><swanseaauthors><author><sid>6058e9a7895980ea8671e8f8c3f85c45</sid><ORCID>0000-0002-3745-5426</ORCID><firstname>Lloyd</firstname><surname>Balbuena</surname><name>Lloyd Balbuena</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>ed8a9c37bd7b7235b762d941ef18ee55</sid><ORCID>0000-0002-5657-6995</ORCID><firstname>Ann</firstname><surname>John</surname><name>Ann John</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-02-16</date><deptcode>PMSC</deptcode><abstract>Background: Machine learning (ML) is increasingly used to predict suicide deaths but their value for suicide prevention has not been established. Our first objective was to identify risk and protective factors in a general population. Our second objective was to identify factors indicating imminent suicide risk. Methods: We used survival and ML models to identify lifetime predictors using the Cohort of Norway (n=173,275) and hospital diagnoses in a Saskatoon clinical sample (n=12,614). The mean follow-up times were 17 years and 3 years for the Cohort of Norway and Saskatoon respectively. People in the clinical sample had a longitudinal record of hospital visits grouped in six-month intervals. We developed models in a training set and these models predicted survival probabilities in held-out test data. Results: In the general population, we found that a higher proportion of low-income residents in a county, mood symptoms, and daily smoking increased the risk of dying from suicide in both genders. In the clinical sample, the only predictors identified were male gender and older age. Conclusion: Suicide prevention probably requires individual actions with governmental incentives. The prediction of imminent suicide remains highly challenging, but machine learning can identify early prevention targets.</abstract><type>Journal Article</type><journal>BMC Psychiatry</journal><volume>22</volume><journalNumber>1</journalNumber><paginationStart>120</paginationStart><paginationEnd/><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>1471-244X</issnElectronic><keywords>suicide; machine learning; prediction; primary prevention; secondary prevention</keywords><publishedDay>15</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2022</publishedYear><publishedDate>2022-02-15</publishedDate><doi>10.1186/s12888-022-03702-y</doi><url/><notes/><college>COLLEGE NANME</college><department>Medicine</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>PMSC</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This research was supported by grants to the first author from the Department of Psychiatry, University of Saskatchewan, the Saskatchewan Health Research Foundation, the Royal University Hospital Foundation Community Mental Health Fund, the Google Cloud Platform, and Compute Canada.</funders><lastEdited>2022-02-16T16:13:08.1856404</lastEdited><Created>2022-02-16T16:06:34.9426191</Created><path><level id="1">Faculty of Medicine, Health and Life Sciences</level><level id="2">Swansea University Medical School - Medicine</level></path><authors><author><firstname>Lloyd</firstname><surname>Balbuena</surname><orcid>0000-0002-3745-5426</orcid><order>1</order></author><author><firstname>Marilyn</firstname><surname>Baetz</surname><order>2</order></author><author><firstname>Joseph Andrew</firstname><surname>Sexton</surname><order>3</order></author><author><firstname>Douglas</firstname><surname>Harder</surname><order>4</order></author><author><firstname>Cindy Xin</firstname><surname>Feng</surname><order>5</order></author><author><firstname>Kerstina</firstname><surname>Boctor</surname><order>6</order></author><author><firstname>Candace</firstname><surname>LaPointe</surname><order>7</order></author><author><firstname>Elizabeth</firstname><surname>Letwiniuk</surname><order>8</order></author><author><firstname>Arash</firstname><surname>Shamloo</surname><order>9</order></author><author><firstname>Hemant</firstname><surname>Ishwaran</surname><order>10</order></author><author><firstname>Ann</firstname><surname>John</surname><orcid>0000-0002-5657-6995</orcid><order>11</order></author><author><firstname>Anne Lise</firstname><surname>Brants&#xE6;ter</surname><order>12</order></author></authors><documents><document><filename>59416__22389__69b8dfa1d9a54bffa9971975e6464011.pdf</filename><originalFilename>12888_2022_Article_3702.pdf</originalFilename><uploaded>2022-02-16T16:06:34.9424211</uploaded><type>Output</type><contentLength>653097</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; The Author(s) 2022. This article is licensed under a Creative Commons Attribution 4.0 International License</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2022-02-16T16:13:08.1856404 v2 59416 2022-02-16 Identifying long-term and imminent suicide predictors in a general population and a clinical sample with machine learning 6058e9a7895980ea8671e8f8c3f85c45 0000-0002-3745-5426 Lloyd Balbuena Lloyd Balbuena true false ed8a9c37bd7b7235b762d941ef18ee55 0000-0002-5657-6995 Ann John Ann John true false 2022-02-16 PMSC Background: Machine learning (ML) is increasingly used to predict suicide deaths but their value for suicide prevention has not been established. Our first objective was to identify risk and protective factors in a general population. Our second objective was to identify factors indicating imminent suicide risk. Methods: We used survival and ML models to identify lifetime predictors using the Cohort of Norway (n=173,275) and hospital diagnoses in a Saskatoon clinical sample (n=12,614). The mean follow-up times were 17 years and 3 years for the Cohort of Norway and Saskatoon respectively. People in the clinical sample had a longitudinal record of hospital visits grouped in six-month intervals. We developed models in a training set and these models predicted survival probabilities in held-out test data. Results: In the general population, we found that a higher proportion of low-income residents in a county, mood symptoms, and daily smoking increased the risk of dying from suicide in both genders. In the clinical sample, the only predictors identified were male gender and older age. Conclusion: Suicide prevention probably requires individual actions with governmental incentives. The prediction of imminent suicide remains highly challenging, but machine learning can identify early prevention targets. Journal Article BMC Psychiatry 22 1 120 Springer Science and Business Media LLC 1471-244X suicide; machine learning; prediction; primary prevention; secondary prevention 15 2 2022 2022-02-15 10.1186/s12888-022-03702-y COLLEGE NANME Medicine COLLEGE CODE PMSC Swansea University This research was supported by grants to the first author from the Department of Psychiatry, University of Saskatchewan, the Saskatchewan Health Research Foundation, the Royal University Hospital Foundation Community Mental Health Fund, the Google Cloud Platform, and Compute Canada. 2022-02-16T16:13:08.1856404 2022-02-16T16:06:34.9426191 Faculty of Medicine, Health and Life Sciences Swansea University Medical School - Medicine Lloyd Balbuena 0000-0002-3745-5426 1 Marilyn Baetz 2 Joseph Andrew Sexton 3 Douglas Harder 4 Cindy Xin Feng 5 Kerstina Boctor 6 Candace LaPointe 7 Elizabeth Letwiniuk 8 Arash Shamloo 9 Hemant Ishwaran 10 Ann John 0000-0002-5657-6995 11 Anne Lise Brantsæter 12 59416__22389__69b8dfa1d9a54bffa9971975e6464011.pdf 12888_2022_Article_3702.pdf 2022-02-16T16:06:34.9424211 Output 653097 application/pdf Version of Record true © The Author(s) 2022. This article is licensed under a Creative Commons Attribution 4.0 International License true eng http://creativecommons.org/licenses/by/4.0/
title Identifying long-term and imminent suicide predictors in a general population and a clinical sample with machine learning
spellingShingle Identifying long-term and imminent suicide predictors in a general population and a clinical sample with machine learning
Lloyd Balbuena
Ann John
title_short Identifying long-term and imminent suicide predictors in a general population and a clinical sample with machine learning
title_full Identifying long-term and imminent suicide predictors in a general population and a clinical sample with machine learning
title_fullStr Identifying long-term and imminent suicide predictors in a general population and a clinical sample with machine learning
title_full_unstemmed Identifying long-term and imminent suicide predictors in a general population and a clinical sample with machine learning
title_sort Identifying long-term and imminent suicide predictors in a general population and a clinical sample with machine learning
author_id_str_mv 6058e9a7895980ea8671e8f8c3f85c45
ed8a9c37bd7b7235b762d941ef18ee55
author_id_fullname_str_mv 6058e9a7895980ea8671e8f8c3f85c45_***_Lloyd Balbuena
ed8a9c37bd7b7235b762d941ef18ee55_***_Ann John
author Lloyd Balbuena
Ann John
author2 Lloyd Balbuena
Marilyn Baetz
Joseph Andrew Sexton
Douglas Harder
Cindy Xin Feng
Kerstina Boctor
Candace LaPointe
Elizabeth Letwiniuk
Arash Shamloo
Hemant Ishwaran
Ann John
Anne Lise Brantsæter
format Journal article
container_title BMC Psychiatry
container_volume 22
container_issue 1
container_start_page 120
publishDate 2022
institution Swansea University
issn 1471-244X
doi_str_mv 10.1186/s12888-022-03702-y
publisher Springer Science and Business Media LLC
college_str Faculty of Medicine, Health and Life Sciences
hierarchytype
hierarchy_top_id facultyofmedicinehealthandlifesciences
hierarchy_top_title Faculty of Medicine, Health and Life Sciences
hierarchy_parent_id facultyofmedicinehealthandlifesciences
hierarchy_parent_title Faculty of Medicine, Health and Life Sciences
department_str Swansea University Medical School - Medicine{{{_:::_}}}Faculty of Medicine, Health and Life Sciences{{{_:::_}}}Swansea University Medical School - Medicine
document_store_str 1
active_str 0
description Background: Machine learning (ML) is increasingly used to predict suicide deaths but their value for suicide prevention has not been established. Our first objective was to identify risk and protective factors in a general population. Our second objective was to identify factors indicating imminent suicide risk. Methods: We used survival and ML models to identify lifetime predictors using the Cohort of Norway (n=173,275) and hospital diagnoses in a Saskatoon clinical sample (n=12,614). The mean follow-up times were 17 years and 3 years for the Cohort of Norway and Saskatoon respectively. People in the clinical sample had a longitudinal record of hospital visits grouped in six-month intervals. We developed models in a training set and these models predicted survival probabilities in held-out test data. Results: In the general population, we found that a higher proportion of low-income residents in a county, mood symptoms, and daily smoking increased the risk of dying from suicide in both genders. In the clinical sample, the only predictors identified were male gender and older age. Conclusion: Suicide prevention probably requires individual actions with governmental incentives. The prediction of imminent suicide remains highly challenging, but machine learning can identify early prevention targets.
published_date 2022-02-15T04:16:42Z
_version_ 1763754117896863744
score 11.037056

Similar Items