A genetically informed prediction model for suicidal and aggressive behaviour in teens
Abstract Suicidal and aggressive behaviours cause significant personal and societal burden. As risk factors associated with these behaviours frequently overlap, combined approaches in predicting the behaviours may be useful in identifying those at risk for either. The current study aimed to create a...
Main Authors: | , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2022-11-01
|
Series: | Translational Psychiatry |
Online Access: | https://doi.org/10.1038/s41398-022-02245-w |
_version_ | 1811303880057683968 |
---|---|
author | Ashley E. Tate Wonuola A. Akingbuwa Robert Karlsson Jouke-Jan Hottenga René Pool Magnus Boman Henrik Larsson Sebastian Lundström Paul Lichtenstein Christel M. Middeldorp Meike Bartels Ralf Kuja-Halkola |
author_facet | Ashley E. Tate Wonuola A. Akingbuwa Robert Karlsson Jouke-Jan Hottenga René Pool Magnus Boman Henrik Larsson Sebastian Lundström Paul Lichtenstein Christel M. Middeldorp Meike Bartels Ralf Kuja-Halkola |
author_sort | Ashley E. Tate |
collection | DOAJ |
description | Abstract Suicidal and aggressive behaviours cause significant personal and societal burden. As risk factors associated with these behaviours frequently overlap, combined approaches in predicting the behaviours may be useful in identifying those at risk for either. The current study aimed to create a model that predicted if individuals will exhibit suicidal behaviour, aggressive behaviour, both, or neither in late adolescence. A sample of 5,974 twins from the Child and Adolescent Twin Study in Sweden (CATSS) was broken down into a training (80%), tune (10%) and test (10%) set. The Netherlands Twin Register (NTR; N = 2702) was used for external validation. Our longitudinal data featured genetic, environmental, and psychosocial predictors derived from parental and self-report data. A stacked ensemble model was created which contained a gradient boosted machine, random forest, elastic net, and neural network. Model performance was transferable between CATSS and NTR (macro area under the receiver operating characteristic curve (AUC) [95% CI] AUCCATSS(test set) = 0.709 (0.671–0.747); AUCNTR = 0.685 (0.656–0.715), suggesting model generalisability across Northern Europe. The notable exception is suicidal behaviours in the NTR, which was no better than chance. The 25 highest scoring variable importance scores for the gradient boosted machines and random forest models included self-reported psychiatric symptoms in mid-adolescence, sex, and polygenic scores for psychiatric traits. The model’s performance is comparable to current prediction models that use clinical interviews and is not yet suitable for clinical use. Moreover, genetic variables may have a role to play in predictive models of adolescent psychopathology. |
first_indexed | 2024-04-13T07:57:13Z |
format | Article |
id | doaj.art-c194d48465434855818b9651cbe00c79 |
institution | Directory Open Access Journal |
issn | 2158-3188 |
language | English |
last_indexed | 2024-04-13T07:57:13Z |
publishDate | 2022-11-01 |
publisher | Nature Publishing Group |
record_format | Article |
series | Translational Psychiatry |
spelling | doaj.art-c194d48465434855818b9651cbe00c792022-12-22T02:55:23ZengNature Publishing GroupTranslational Psychiatry2158-31882022-11-011211910.1038/s41398-022-02245-wA genetically informed prediction model for suicidal and aggressive behaviour in teensAshley E. Tate0Wonuola A. Akingbuwa1Robert Karlsson2Jouke-Jan Hottenga3René Pool4Magnus Boman5Henrik Larsson6Sebastian Lundström7Paul Lichtenstein8Christel M. Middeldorp9Meike Bartels10Ralf Kuja-Halkola11Department of Medical Epidemiology and Biostatistics, Karolinska InstitutetDepartment of Biological Psychology, Vrije Universiteit AmsterdamDepartment of Medical Epidemiology and Biostatistics, Karolinska InstitutetDepartment of Biological Psychology, Vrije Universiteit AmsterdamDepartment of Biological Psychology, Vrije Universiteit AmsterdamDivision of Software and Computer Systems, School of Electrical Engineering and Computer Science KTHDepartment of Medical Epidemiology and Biostatistics, Karolinska InstitutetCentre for Ethics, Law and Mental Health (CELAM), University of GothenburgDepartment of Medical Epidemiology and Biostatistics, Karolinska InstitutetDepartment of Biological Psychology, Vrije Universiteit AmsterdamDepartment of Biological Psychology, Vrije Universiteit AmsterdamDepartment of Medical Epidemiology and Biostatistics, Karolinska InstitutetAbstract Suicidal and aggressive behaviours cause significant personal and societal burden. As risk factors associated with these behaviours frequently overlap, combined approaches in predicting the behaviours may be useful in identifying those at risk for either. The current study aimed to create a model that predicted if individuals will exhibit suicidal behaviour, aggressive behaviour, both, or neither in late adolescence. A sample of 5,974 twins from the Child and Adolescent Twin Study in Sweden (CATSS) was broken down into a training (80%), tune (10%) and test (10%) set. The Netherlands Twin Register (NTR; N = 2702) was used for external validation. Our longitudinal data featured genetic, environmental, and psychosocial predictors derived from parental and self-report data. A stacked ensemble model was created which contained a gradient boosted machine, random forest, elastic net, and neural network. Model performance was transferable between CATSS and NTR (macro area under the receiver operating characteristic curve (AUC) [95% CI] AUCCATSS(test set) = 0.709 (0.671–0.747); AUCNTR = 0.685 (0.656–0.715), suggesting model generalisability across Northern Europe. The notable exception is suicidal behaviours in the NTR, which was no better than chance. The 25 highest scoring variable importance scores for the gradient boosted machines and random forest models included self-reported psychiatric symptoms in mid-adolescence, sex, and polygenic scores for psychiatric traits. The model’s performance is comparable to current prediction models that use clinical interviews and is not yet suitable for clinical use. Moreover, genetic variables may have a role to play in predictive models of adolescent psychopathology.https://doi.org/10.1038/s41398-022-02245-w |
spellingShingle | Ashley E. Tate Wonuola A. Akingbuwa Robert Karlsson Jouke-Jan Hottenga René Pool Magnus Boman Henrik Larsson Sebastian Lundström Paul Lichtenstein Christel M. Middeldorp Meike Bartels Ralf Kuja-Halkola A genetically informed prediction model for suicidal and aggressive behaviour in teens Translational Psychiatry |
title | A genetically informed prediction model for suicidal and aggressive behaviour in teens |
title_full | A genetically informed prediction model for suicidal and aggressive behaviour in teens |
title_fullStr | A genetically informed prediction model for suicidal and aggressive behaviour in teens |
title_full_unstemmed | A genetically informed prediction model for suicidal and aggressive behaviour in teens |
title_short | A genetically informed prediction model for suicidal and aggressive behaviour in teens |
title_sort | genetically informed prediction model for suicidal and aggressive behaviour in teens |
url | https://doi.org/10.1038/s41398-022-02245-w |
work_keys_str_mv | AT ashleyetate ageneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT wonuolaaakingbuwa ageneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT robertkarlsson ageneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT joukejanhottenga ageneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT renepool ageneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT magnusboman ageneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT henriklarsson ageneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT sebastianlundstrom ageneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT paullichtenstein ageneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT christelmmiddeldorp ageneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT meikebartels ageneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT ralfkujahalkola ageneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT ashleyetate geneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT wonuolaaakingbuwa geneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT robertkarlsson geneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT joukejanhottenga geneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT renepool geneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT magnusboman geneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT henriklarsson geneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT sebastianlundstrom geneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT paullichtenstein geneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT christelmmiddeldorp geneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT meikebartels geneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens AT ralfkujahalkola geneticallyinformedpredictionmodelforsuicidalandaggressivebehaviourinteens |