Deep graph neural network-based prediction of acute suicidal ideation in young adults

Abstract Precise remote evaluation of both suicide risk and psychiatric disorders is critical for suicide prevention as well as for psychiatric well-being. Using questionnaires is an alternative to labor-intensive diagnostic interviews in a large general population, but previous models for predictin...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Kyu Sung Choi, Sunghwan Kim, Byung-Hoon Kim, Hong Jin Jeon, Jong-Hoon Kim, Joon Hwan Jang, Bumseok Jeong
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/517429c33258464db81d66a2d972bb07
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:517429c33258464db81d66a2d972bb07
record_format dspace
spelling oai:doaj.org-article:517429c33258464db81d66a2d972bb072021-12-02T14:53:35ZDeep graph neural network-based prediction of acute suicidal ideation in young adults10.1038/s41598-021-95102-72045-2322https://doaj.org/article/517429c33258464db81d66a2d972bb072021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-95102-7https://doaj.org/toc/2045-2322Abstract Precise remote evaluation of both suicide risk and psychiatric disorders is critical for suicide prevention as well as for psychiatric well-being. Using questionnaires is an alternative to labor-intensive diagnostic interviews in a large general population, but previous models for predicting suicide attempts suffered from low sensitivity. We developed and validated a deep graph neural network model that increased the prediction sensitivity of suicide risk in young adults (n = 17,482 for training; n = 14,238 for testing) using multi-dimensional questionnaires and suicidal ideation within 2 weeks as the prediction target. The best model achieved a sensitivity of 76.3%, specificity of 83.4%, and an area under curve of 0.878 (95% confidence interval, 0.855–0.899). We demonstrated that multi-dimensional deep features covering depression, anxiety, resilience, self-esteem, and clinico-demographic information contribute to the prediction of suicidal ideation. Our model might be useful for the remote evaluation of suicide risk in the general population of young adults for specific situations such as the COVID-19 pandemic.Kyu Sung ChoiSunghwan KimByung-Hoon KimHong Jin JeonJong-Hoon KimJoon Hwan JangBumseok JeongNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Kyu Sung Choi
Sunghwan Kim
Byung-Hoon Kim
Hong Jin Jeon
Jong-Hoon Kim
Joon Hwan Jang
Bumseok Jeong
Deep graph neural network-based prediction of acute suicidal ideation in young adults
description Abstract Precise remote evaluation of both suicide risk and psychiatric disorders is critical for suicide prevention as well as for psychiatric well-being. Using questionnaires is an alternative to labor-intensive diagnostic interviews in a large general population, but previous models for predicting suicide attempts suffered from low sensitivity. We developed and validated a deep graph neural network model that increased the prediction sensitivity of suicide risk in young adults (n = 17,482 for training; n = 14,238 for testing) using multi-dimensional questionnaires and suicidal ideation within 2 weeks as the prediction target. The best model achieved a sensitivity of 76.3%, specificity of 83.4%, and an area under curve of 0.878 (95% confidence interval, 0.855–0.899). We demonstrated that multi-dimensional deep features covering depression, anxiety, resilience, self-esteem, and clinico-demographic information contribute to the prediction of suicidal ideation. Our model might be useful for the remote evaluation of suicide risk in the general population of young adults for specific situations such as the COVID-19 pandemic.
format article
author Kyu Sung Choi
Sunghwan Kim
Byung-Hoon Kim
Hong Jin Jeon
Jong-Hoon Kim
Joon Hwan Jang
Bumseok Jeong
author_facet Kyu Sung Choi
Sunghwan Kim
Byung-Hoon Kim
Hong Jin Jeon
Jong-Hoon Kim
Joon Hwan Jang
Bumseok Jeong
author_sort Kyu Sung Choi
title Deep graph neural network-based prediction of acute suicidal ideation in young adults
title_short Deep graph neural network-based prediction of acute suicidal ideation in young adults
title_full Deep graph neural network-based prediction of acute suicidal ideation in young adults
title_fullStr Deep graph neural network-based prediction of acute suicidal ideation in young adults
title_full_unstemmed Deep graph neural network-based prediction of acute suicidal ideation in young adults
title_sort deep graph neural network-based prediction of acute suicidal ideation in young adults
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/517429c33258464db81d66a2d972bb07
work_keys_str_mv AT kyusungchoi deepgraphneuralnetworkbasedpredictionofacutesuicidalideationinyoungadults
AT sunghwankim deepgraphneuralnetworkbasedpredictionofacutesuicidalideationinyoungadults
AT byunghoonkim deepgraphneuralnetworkbasedpredictionofacutesuicidalideationinyoungadults
AT hongjinjeon deepgraphneuralnetworkbasedpredictionofacutesuicidalideationinyoungadults
AT jonghoonkim deepgraphneuralnetworkbasedpredictionofacutesuicidalideationinyoungadults
AT joonhwanjang deepgraphneuralnetworkbasedpredictionofacutesuicidalideationinyoungadults
AT bumseokjeong deepgraphneuralnetworkbasedpredictionofacutesuicidalideationinyoungadults
_version_ 1718389445126782976