Predicting suicide attempts among Norwegian adolescents without using suicide-related items: a machine learning approach
IntroductionResearch on the classification models of suicide attempts has predominantly depended on the collection of sensitive data related to suicide. Gathering this type of information at the population level can be challenging, especially when it pertains to adolescents. We addressed two main ob...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-09-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1216791/full |
| _version_ | 1797672696330321920 |
|---|---|
| author | E. F. Haghish Nikolai O. Czajkowski Nikolai O. Czajkowski Tilmann von Soest Tilmann von Soest |
| author_facet | E. F. Haghish Nikolai O. Czajkowski Nikolai O. Czajkowski Tilmann von Soest Tilmann von Soest |
| author_sort | E. F. Haghish |
| collection | DOAJ |
| description | IntroductionResearch on the classification models of suicide attempts has predominantly depended on the collection of sensitive data related to suicide. Gathering this type of information at the population level can be challenging, especially when it pertains to adolescents. We addressed two main objectives: (1) the feasibility of classifying adolescents at high risk of attempting suicide without relying on specific suicide-related survey items such as history of suicide attempts, suicide plan, or suicide ideation, and (2) identifying the most important predictors of suicide attempts among adolescents.MethodsNationwide survey data from 173,664 Norwegian adolescents (ages 13–18) were utilized to train a binary classification model, using 169 questionnaire items. The Extreme Gradient Boosting (XGBoost) algorithm was fine-tuned to classify adolescent suicide attempts, and the most important predictors were identified.ResultsXGBoost achieved a sensitivity of 77% with a specificity of 90%, and an AUC of 92.1% and an AUPRC of 47.1%. A coherent set of predictors in the domains of internalizing problems, substance use, interpersonal relationships, and victimization were pinpointed as the most important items related to recent suicide attempts.ConclusionThis study underscores the potential of machine learning for screening adolescent suicide attempts on a population scale without requiring sensitive suicide-related survey items. Future research investigating the etiology of suicidal behavior may direct particular attention to internalizing problems, interpersonal relationships, victimization, and substance use. |
| first_indexed | 2024-03-11T21:33:57Z |
| format | Article |
| id | doaj.art-830b71dc96c549c0ad4a60c674387154 |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-03-11T21:33:57Z |
| publishDate | 2023-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-830b71dc96c549c0ad4a60c6743871542023-09-27T05:05:56ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402023-09-011410.3389/fpsyt.2023.12167911216791Predicting suicide attempts among Norwegian adolescents without using suicide-related items: a machine learning approachE. F. Haghish0Nikolai O. Czajkowski1Nikolai O. Czajkowski2Tilmann von Soest3Tilmann von Soest4Department of Psychology, Faculty of Social Sciences, University of Oslo, Oslo, NorwayDepartment of Psychology, Faculty of Social Sciences, University of Oslo, Oslo, NorwayDepartment of Mental Disorders, Division of Mental and Physical Health, Norwegian Institute of Public Health (NIPH), Oslo, NorwayDepartment of Psychology, Faculty of Social Sciences, University of Oslo, Oslo, NorwayNorwegian Social Research (NOVA), Oslo Metropolitan University, Oslo, NorwayIntroductionResearch on the classification models of suicide attempts has predominantly depended on the collection of sensitive data related to suicide. Gathering this type of information at the population level can be challenging, especially when it pertains to adolescents. We addressed two main objectives: (1) the feasibility of classifying adolescents at high risk of attempting suicide without relying on specific suicide-related survey items such as history of suicide attempts, suicide plan, or suicide ideation, and (2) identifying the most important predictors of suicide attempts among adolescents.MethodsNationwide survey data from 173,664 Norwegian adolescents (ages 13–18) were utilized to train a binary classification model, using 169 questionnaire items. The Extreme Gradient Boosting (XGBoost) algorithm was fine-tuned to classify adolescent suicide attempts, and the most important predictors were identified.ResultsXGBoost achieved a sensitivity of 77% with a specificity of 90%, and an AUC of 92.1% and an AUPRC of 47.1%. A coherent set of predictors in the domains of internalizing problems, substance use, interpersonal relationships, and victimization were pinpointed as the most important items related to recent suicide attempts.ConclusionThis study underscores the potential of machine learning for screening adolescent suicide attempts on a population scale without requiring sensitive suicide-related survey items. Future research investigating the etiology of suicidal behavior may direct particular attention to internalizing problems, interpersonal relationships, victimization, and substance use.https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1216791/fullsuicide attempt classificationrisk factorssupervised machine learningadolescentssurvey |
| spellingShingle | E. F. Haghish Nikolai O. Czajkowski Nikolai O. Czajkowski Tilmann von Soest Tilmann von Soest Predicting suicide attempts among Norwegian adolescents without using suicide-related items: a machine learning approach Frontiers in Psychiatry suicide attempt classification risk factors supervised machine learning adolescents survey |
| title | Predicting suicide attempts among Norwegian adolescents without using suicide-related items: a machine learning approach |
| title_full | Predicting suicide attempts among Norwegian adolescents without using suicide-related items: a machine learning approach |
| title_fullStr | Predicting suicide attempts among Norwegian adolescents without using suicide-related items: a machine learning approach |
| title_full_unstemmed | Predicting suicide attempts among Norwegian adolescents without using suicide-related items: a machine learning approach |
| title_short | Predicting suicide attempts among Norwegian adolescents without using suicide-related items: a machine learning approach |
| title_sort | predicting suicide attempts among norwegian adolescents without using suicide related items a machine learning approach |
| topic | suicide attempt classification risk factors supervised machine learning adolescents survey |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1216791/full |
| work_keys_str_mv | AT efhaghish predictingsuicideattemptsamongnorwegianadolescentswithoutusingsuiciderelateditemsamachinelearningapproach AT nikolaioczajkowski predictingsuicideattemptsamongnorwegianadolescentswithoutusingsuiciderelateditemsamachinelearningapproach AT nikolaioczajkowski predictingsuicideattemptsamongnorwegianadolescentswithoutusingsuiciderelateditemsamachinelearningapproach AT tilmannvonsoest predictingsuicideattemptsamongnorwegianadolescentswithoutusingsuiciderelateditemsamachinelearningapproach AT tilmannvonsoest predictingsuicideattemptsamongnorwegianadolescentswithoutusingsuiciderelateditemsamachinelearningapproach |