No Cover Image

Journal article 482 views 127 downloads

Identification of Suicidal Ideation in the Canadian Community Health Survey—Mental Health Component Using Deep Learning

Sneha Desai, Myriam Tanguay-Sela, David Benrimoh, Robert Fratila, Eleanor Brown, Kelly Perlman, Ann John Orcid Logo, Marcos del Pozo Banos Orcid Logo, Nancy Low, Sonia Israel, Lisa Palladini, Gustavo Turecki

Frontiers in Artificial Intelligence, Volume: 4

Swansea University Authors: Ann John Orcid Logo, Marcos del Pozo Banos Orcid Logo

  • 56968.pdf

    PDF | Version of Record

    © 2021 Desai, Tanguay-Sela, Benrimoh, Fratila, Brown, Perlman, John, DelPozo-Banos, Low, Israel, Palladini and Turecki. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY).

    Download (839.08KB)

Check full text

DOI (Published version): 10.3389/frai.2021.561528

Abstract

Introduction: Suicidal ideation (SI) is prevalent in the general population, and is a risk factor for suicide. Predicting which patients are likely to have SI remains challenging. Deep Learning (DL) may be a useful tool in this context, as it can be used to find patterns in complex, heterogeneous, a...

Full description

Published in: Frontiers in Artificial Intelligence
ISSN: 2624-8212
Published: Frontiers Media SA 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa56968
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-05-26T09:39:24Z
last_indexed 2023-01-11T14:36:33Z
id cronfa56968
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2022-12-02T14:12:08.2915157</datestamp><bib-version>v2</bib-version><id>56968</id><entry>2021-05-26</entry><title>Identification of Suicidal Ideation in the Canadian Community Health Survey&#x2014;Mental Health Component Using Deep Learning</title><swanseaauthors><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><author><sid>f141785b1c0ab9efe45665d35c081b84</sid><ORCID>0000-0003-1502-389X</ORCID><firstname>Marcos</firstname><surname>del Pozo Banos</surname><name>Marcos del Pozo Banos</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-05-26</date><deptcode>HDAT</deptcode><abstract>Introduction: Suicidal ideation (SI) is prevalent in the general population, and is a risk factor for suicide. Predicting which patients are likely to have SI remains challenging. Deep Learning (DL) may be a useful tool in this context, as it can be used to find patterns in complex, heterogeneous, and incomplete datasets. An automated screening system for SI could help prompt clinicians to be moreattentive to patients at risk for suicide.Methods: Using the Canadian Community Health Survey - Mental Health Component, we trained a DL model based on 23,859 survey responses to classify patients with and without SI. Models were created to classify both lifetime and last 12 month SI. From 582 possible parameters we produced 96 and 21 feature versions of the models. Models were trained using an undersampling procedure that balanced the training set between SI and non-SI; validation was done on held-out data.Results: For lifetime SI, the 96 feature model had an AUC of 0.79 and the 21 feature model had an AUC of 0.77. For SI in the last 12 months the 96 feature model had an AUC of 0.71 and the 21 feature model had an AUC of 0.68. In addition, sensitivity analyses demonstrated feature relationships in line with existing literature. Discussion: Although requiring further study to ensure clinical relevance and sample generalizability, this study is an initial proof of concept for the use of DL to improve identification of SI. Sensitivity analyses can help improve the interpretability of DL models. This kind of model would help start conversations with patients which could lead to improved care and a reduction in suicidal behavior.</abstract><type>Journal Article</type><journal>Frontiers in Artificial Intelligence</journal><volume>4</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>Frontiers Media SA</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2624-8212</issnElectronic><keywords>deep learning, suicidal ideation, risk assessment, predictors, machine learning, artificial intelligence,Canadian community health survey, Canadian community health survey&#x2014;mental health 2012</keywords><publishedDay>24</publishedDay><publishedMonth>6</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-06-24</publishedDate><doi>10.3389/frai.2021.561528</doi><url/><notes/><college>COLLEGE NANME</college><department>Health Data Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>HDAT</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2022-12-02T14:12:08.2915157</lastEdited><Created>2021-05-26T10:29:16.2992648</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>Sneha</firstname><surname>Desai</surname><order>1</order></author><author><firstname>Myriam</firstname><surname>Tanguay-Sela</surname><order>2</order></author><author><firstname>David</firstname><surname>Benrimoh</surname><order>3</order></author><author><firstname>Robert</firstname><surname>Fratila</surname><order>4</order></author><author><firstname>Eleanor</firstname><surname>Brown</surname><order>5</order></author><author><firstname>Kelly</firstname><surname>Perlman</surname><order>6</order></author><author><firstname>Ann</firstname><surname>John</surname><orcid>0000-0002-5657-6995</orcid><order>7</order></author><author><firstname>Marcos</firstname><surname>del Pozo Banos</surname><orcid>0000-0003-1502-389X</orcid><order>8</order></author><author><firstname>Nancy</firstname><surname>Low</surname><order>9</order></author><author><firstname>Sonia</firstname><surname>Israel</surname><order>10</order></author><author><firstname>Lisa</firstname><surname>Palladini</surname><order>11</order></author><author><firstname>Gustavo</firstname><surname>Turecki</surname><order>12</order></author></authors><documents><document><filename>56968__20604__4caebcf1fd3745dda4795290c99c94d1.pdf</filename><originalFilename>56968.pdf</originalFilename><uploaded>2021-08-10T16:50:07.0977511</uploaded><type>Output</type><contentLength>859216</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2021 Desai, Tanguay-Sela, Benrimoh, Fratila, Brown, Perlman, John, DelPozo-Banos, Low, Israel, Palladini and Turecki. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2022-12-02T14:12:08.2915157 v2 56968 2021-05-26 Identification of Suicidal Ideation in the Canadian Community Health Survey—Mental Health Component Using Deep Learning ed8a9c37bd7b7235b762d941ef18ee55 0000-0002-5657-6995 Ann John Ann John true false f141785b1c0ab9efe45665d35c081b84 0000-0003-1502-389X Marcos del Pozo Banos Marcos del Pozo Banos true false 2021-05-26 HDAT Introduction: Suicidal ideation (SI) is prevalent in the general population, and is a risk factor for suicide. Predicting which patients are likely to have SI remains challenging. Deep Learning (DL) may be a useful tool in this context, as it can be used to find patterns in complex, heterogeneous, and incomplete datasets. An automated screening system for SI could help prompt clinicians to be moreattentive to patients at risk for suicide.Methods: Using the Canadian Community Health Survey - Mental Health Component, we trained a DL model based on 23,859 survey responses to classify patients with and without SI. Models were created to classify both lifetime and last 12 month SI. From 582 possible parameters we produced 96 and 21 feature versions of the models. Models were trained using an undersampling procedure that balanced the training set between SI and non-SI; validation was done on held-out data.Results: For lifetime SI, the 96 feature model had an AUC of 0.79 and the 21 feature model had an AUC of 0.77. For SI in the last 12 months the 96 feature model had an AUC of 0.71 and the 21 feature model had an AUC of 0.68. In addition, sensitivity analyses demonstrated feature relationships in line with existing literature. Discussion: Although requiring further study to ensure clinical relevance and sample generalizability, this study is an initial proof of concept for the use of DL to improve identification of SI. Sensitivity analyses can help improve the interpretability of DL models. This kind of model would help start conversations with patients which could lead to improved care and a reduction in suicidal behavior. Journal Article Frontiers in Artificial Intelligence 4 Frontiers Media SA 2624-8212 deep learning, suicidal ideation, risk assessment, predictors, machine learning, artificial intelligence,Canadian community health survey, Canadian community health survey—mental health 2012 24 6 2021 2021-06-24 10.3389/frai.2021.561528 COLLEGE NANME Health Data Science COLLEGE CODE HDAT Swansea University 2022-12-02T14:12:08.2915157 2021-05-26T10:29:16.2992648 Faculty of Medicine, Health and Life Sciences Swansea University Medical School - Medicine Sneha Desai 1 Myriam Tanguay-Sela 2 David Benrimoh 3 Robert Fratila 4 Eleanor Brown 5 Kelly Perlman 6 Ann John 0000-0002-5657-6995 7 Marcos del Pozo Banos 0000-0003-1502-389X 8 Nancy Low 9 Sonia Israel 10 Lisa Palladini 11 Gustavo Turecki 12 56968__20604__4caebcf1fd3745dda4795290c99c94d1.pdf 56968.pdf 2021-08-10T16:50:07.0977511 Output 859216 application/pdf Version of Record true © 2021 Desai, Tanguay-Sela, Benrimoh, Fratila, Brown, Perlman, John, DelPozo-Banos, Low, Israel, Palladini and Turecki. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). true eng http://creativecommons.org/licenses/by/4.0/
title Identification of Suicidal Ideation in the Canadian Community Health Survey—Mental Health Component Using Deep Learning
spellingShingle Identification of Suicidal Ideation in the Canadian Community Health Survey—Mental Health Component Using Deep Learning
Ann John
Marcos del Pozo Banos
title_short Identification of Suicidal Ideation in the Canadian Community Health Survey—Mental Health Component Using Deep Learning
title_full Identification of Suicidal Ideation in the Canadian Community Health Survey—Mental Health Component Using Deep Learning
title_fullStr Identification of Suicidal Ideation in the Canadian Community Health Survey—Mental Health Component Using Deep Learning
title_full_unstemmed Identification of Suicidal Ideation in the Canadian Community Health Survey—Mental Health Component Using Deep Learning
title_sort Identification of Suicidal Ideation in the Canadian Community Health Survey—Mental Health Component Using Deep Learning
author_id_str_mv ed8a9c37bd7b7235b762d941ef18ee55
f141785b1c0ab9efe45665d35c081b84
author_id_fullname_str_mv ed8a9c37bd7b7235b762d941ef18ee55_***_Ann John
f141785b1c0ab9efe45665d35c081b84_***_Marcos del Pozo Banos
author Ann John
Marcos del Pozo Banos
author2 Sneha Desai
Myriam Tanguay-Sela
David Benrimoh
Robert Fratila
Eleanor Brown
Kelly Perlman
Ann John
Marcos del Pozo Banos
Nancy Low
Sonia Israel
Lisa Palladini
Gustavo Turecki
format Journal article
container_title Frontiers in Artificial Intelligence
container_volume 4
publishDate 2021
institution Swansea University
issn 2624-8212
doi_str_mv 10.3389/frai.2021.561528
publisher Frontiers Media SA
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 Introduction: Suicidal ideation (SI) is prevalent in the general population, and is a risk factor for suicide. Predicting which patients are likely to have SI remains challenging. Deep Learning (DL) may be a useful tool in this context, as it can be used to find patterns in complex, heterogeneous, and incomplete datasets. An automated screening system for SI could help prompt clinicians to be moreattentive to patients at risk for suicide.Methods: Using the Canadian Community Health Survey - Mental Health Component, we trained a DL model based on 23,859 survey responses to classify patients with and without SI. Models were created to classify both lifetime and last 12 month SI. From 582 possible parameters we produced 96 and 21 feature versions of the models. Models were trained using an undersampling procedure that balanced the training set between SI and non-SI; validation was done on held-out data.Results: For lifetime SI, the 96 feature model had an AUC of 0.79 and the 21 feature model had an AUC of 0.77. For SI in the last 12 months the 96 feature model had an AUC of 0.71 and the 21 feature model had an AUC of 0.68. In addition, sensitivity analyses demonstrated feature relationships in line with existing literature. Discussion: Although requiring further study to ensure clinical relevance and sample generalizability, this study is an initial proof of concept for the use of DL to improve identification of SI. Sensitivity analyses can help improve the interpretability of DL models. This kind of model would help start conversations with patients which could lead to improved care and a reduction in suicidal behavior.
published_date 2021-06-24T04:12:20Z
_version_ 1763753842960236544
score 11.037603

Similar Items