Unveiling Adolescent Suicidality: Holistic Analysis of Protective and Risk Factors Using Multiple Machine Learning Algorithms.
Adolescent suicide attempts are on the rise, presenting a significant public health concern. Recent research aimed at improving risk assessment for adolescent suicide attempts has turned to machine learning. But no studies to date have examined the performance of stacked ensemble algorithms, which a...
| Publicado en: | Journal of Youth & Adolescence Vol. 53; no. 3; pp. 507 - 526 |
|---|---|
| Autores principales: | , , , , , , , |
| Formato: | Artículo |
| Publicado: |
Springer Nature
Mar2024
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=175233696&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 175233696 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 00472891 JYA jtl: Journal of Youth & Adolescence issn: 00472891 maglogo: N pubinfo: dt: Mar2024 vid: 53 iid: 3 pid: 237 pub: Springer Nature artinfo: ui: 175233696 10.1007/s10964-023-01892-6 ppf: 507 ppct: 19 formats: fmt: – @attributes: type: T – @attributes: type: P size: 1022KB tig: atl: Unveiling Adolescent Suicidality: Holistic Analysis of Protective and Risk Factors Using Multiple Machine Learning Algorithms. aug: au: Haghish, E. F. Nes, Ragnhild Bang Obaidi, Milan Qin, Ping Stänicke, Line Indrevoll Bekkhus, Mona Laeng, Bruno Czajkowski, Nikolai affil: https://ror.org/01xtthb56 Department of Psychology, University of Oslo, Oslo, Norway https://ror.org/046nvst19 Department of Mental Health and Suicide, Norwegian Institute of Public Health, Oslo, Norway https://ror.org/01xtthb56 Promenta Research Center, Department of Psychology, University of Oslo, Oslo, Norway https://ror.org/035b05819 Department of Psychology, Copenhagen University, Copenhagen, Denmark https://ror.org/01xtthb56 National Centre for Suicide Research and Prevention, Institute for Clinical Medicine, University of Oslo, Oslo, Norway Nic Waals Institute, Lovisenberg hospital, Oslo, Norway https://ror.org/01xtthb56 RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Oslo, Norway su: Norway Suicide risk factors Holistic medicine Suicidal ideation Suicidal behavior Teenagers' conduct of life Self-mutilation Eating disorders Well-being Adolescence Risk assessment Research funding Receiver operating characteristic curves Research methodology evaluation Norwegians Descriptive statistics Research Factor analysis Sleep disorders sug: subj: Suicide risk factors Holistic medicine Suicidal ideation Suicidal behavior Teenagers' conduct of life Self-mutilation Eating disorders Well-being Adolescence Norway Risk assessment Research funding Receiver operating characteristic curves Research methodology evaluation Norwegians Descriptive statistics Research Factor analysis Sleep disorders keyword: Adolescent suicide attempt Eating and sleep problems Optimism and well-being Risk and protective factors Self-harm Adolescent suicide attempt Eating and sleep problems Optimism and well-being Risk and protective factors Self-harm ab: Adolescent suicide attempts are on the rise, presenting a significant public health concern. Recent research aimed at improving risk assessment for adolescent suicide attempts has turned to machine learning. But no studies to date have examined the performance of stacked ensemble algorithms, which are more suitable for low-prevalence conditions. The existing machine learning-based research also lacks population-representative samples, overlooks protective factors and their interplay with risk factors, and neglects established theories on suicidal behavior in favor of purely algorithmic risk estimation. The present study overcomes these shortcomings by comparing the performance of a stacked ensemble algorithm with a diverse set of algorithms, performing a holistic item analysis to identify both risk and protective factors on a comprehensive data, and addressing the compatibility of these factors with two competing theories of suicide, namely, The Interpersonal Theory of Suicide and The Strain Theory of Suicide. A population-representative dataset of 173,664 Norwegian adolescents aged 13 to 18 years (mean = 15.14, SD = 1.58, 50.5% female) with a 4.65% rate of reported suicide attempt during the past 12 months was analyzed. Five machine learning algorithms were trained for suicide attempt risk assessment. The stacked ensemble model significantly outperformed other algorithms, achieving equal sensitivity and a specificity of 90.1%, AUC of 96.4%, and AUCPR of 67.5%. All algorithms found recent self-harm to be the most important indicator of adolescent suicide attempt. Exploratory factor analysis suggested five additional risk domains, which we labeled internalizing problems, sleep disturbance, disordered eating, lack of optimism regarding future education and career, and victimization. The identified factors provided stronger support for The Interpersonal Theory of Suicide than for The Strain Theory of Suicide. An enhancement to The Interpersonal Theory based on the risk and protective factors identified by holistic item analysis is presented. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|