Date
2023-04-24Subject
150 Psychology 360 Social problems and social services SuizidversuchPrognoseJugendRisikofaktorMaschinelles LernenMetadata
Show full item record
Aufsatz
Predicting Lifetime Suicide Attempts in a Community Sample of Adolescents Using Machine Learning Algorithms
Abstract
Suicide is a major global health concern and a prominent cause of death in adolescents. Previous research on suicide prediction has mainly focused on clinical or adult samples. To prevent suicides at an early stage, however, it is important to screen for risk factors in a community sample of adolescents. We compared the accuracy of logistic regressions, elastic net regressions, and gradient boosting machines in predicting suicide attempts by 17-year-olds in the Millennium Cohort Study (N = 7,347), combining a large set of self- and other-reported variables from different categories. Both machine learning algorithms outperformed logistic regressions and achieved similar balanced accuracies (.76 when using data 3 years before the self-reported lifetime suicide attempts and .85 when using data from the same measurement wave). We identified essential variables that should be considered when screening for suicidal behavior. Finally, we discuss the usefulness of complex machine learning models in suicide prediction.
Citation
In: Assessment Volume 31 / Issue 3 (2023-04-24) , S. 557-573 ; eissn:1552-3489Sponsorship
Gefördert im Rahmen eines Open-Access-Transformationsvertrags mit dem VerlagCitation
@article{doi:10.17170/kobra-202403149777,
author={Jankowsky, Kristin and Steger, Diana and Schroeders, Ulrich},
title={Predicting Lifetime Suicide Attempts in a Community Sample of Adolescents Using Machine Learning Algorithms},
journal={Assessment},
year={2023}
}
0500 Oax 0501 Text $btxt$2rdacontent 0502 Computermedien $bc$2rdacarrier 1100 2023$n2023 1500 1/eng 2050 ##0##http://hdl.handle.net/123456789/15617 3000 Jankowsky, Kristin 3010 Steger, Diana 3010 Schroeders, Ulrich 4000 Predicting Lifetime Suicide Attempts in a Community Sample of Adolescents Using Machine Learning Algorithms / Jankowsky, Kristin 4030 4060 Online-Ressource 4085 ##0##=u http://nbn-resolving.de/http://hdl.handle.net/123456789/15617=x R 4204 \$dAufsatz 4170 5550 {{Suizidversuch}} 5550 {{Prognose}} 5550 {{Jugend}} 5550 {{Risikofaktor}} 5550 {{Maschinelles Lernen}} 7136 ##0##http://hdl.handle.net/123456789/15617
2024-04-05T11:24:05Z 2024-04-05T11:24:05Z 2023-04-24 doi:10.17170/kobra-202403149777 http://hdl.handle.net/123456789/15617 Gefördert im Rahmen eines Open-Access-Transformationsvertrags mit dem Verlag eng Namensnennung 4.0 International http://creativecommons.org/licenses/by/4.0/ suicide prediction suicide risk screening adolescents machine learning 150 360 Predicting Lifetime Suicide Attempts in a Community Sample of Adolescents Using Machine Learning Algorithms Aufsatz Suicide is a major global health concern and a prominent cause of death in adolescents. Previous research on suicide prediction has mainly focused on clinical or adult samples. To prevent suicides at an early stage, however, it is important to screen for risk factors in a community sample of adolescents. We compared the accuracy of logistic regressions, elastic net regressions, and gradient boosting machines in predicting suicide attempts by 17-year-olds in the Millennium Cohort Study (N = 7,347), combining a large set of self- and other-reported variables from different categories. Both machine learning algorithms outperformed logistic regressions and achieved similar balanced accuracies (.76 when using data 3 years before the self-reported lifetime suicide attempts and .85 when using data from the same measurement wave). We identified essential variables that should be considered when screening for suicidal behavior. Finally, we discuss the usefulness of complex machine learning models in suicide prediction. open access Jankowsky, Kristin Steger, Diana Schroeders, Ulrich doi:10.1177/10731911231167490 Suizidversuch Prognose Jugend Risikofaktor Maschinelles Lernen publishedVersion eissn:1552-3489 Issue 3 Assessment 557-573 Volume 31 false
The following license files are associated with this item: