Identifying most important predictors for suicidal thoughts and behaviours among healthcare workers active during the Spain COVID-19 pandemic: a machine-learning approach

Aims: Studies conducted during the COVID-19 pandemic found high occurrence of suicidal thoughts and behaviours (STBs) among healthcare workers (HCWs). The current study aimed to (1) develop a machine learning-based prediction model for future STBs using data from a large prospective cohort of Spanis...

Descripción completa

Detalles Bibliográficos
Autores: Alayo, Itxaso, Alonso Caballero, Jordi, Ferrer Forés, Maria Montserrat, Amigo, Franco, Portillo-Van Diest, Ana, Sanz, Ferran, Serra, Consol, Pérez Solà, Víctor, Mortier, Philippe, Vilagut Saiz, Gemma, 1975-, MINDCOVID Working group
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Institución:Universitat Pompeu Fabra
Repositorio:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/70676
Acceso en línea:http://hdl.handle.net/10230/70676
http://dx.doi.org/10.1017/S2045796025000198
Access Level:acceso abierto
Palabra clave:Attempted suicide
Interpretability
Machine learning
Mental health
Suicidal ideation
id ES_ee675e7022d4e2449e21f1beed07d66e
oai_identifier_str oai:repositori.upf.edu:10230/70676
network_acronym_str ES
network_name_str España
repository_id_str
spelling Identifying most important predictors for suicidal thoughts and behaviours among healthcare workers active during the Spain COVID-19 pandemic: a machine-learning approachAlayo, ItxasoAlonso Caballero, JordiFerrer Forés, Maria MontserratAmigo, FrancoPortillo-Van Diest, AnaSanz, FerranSerra, ConsolPérez Solà, VíctorMortier, PhilippeVilagut Saiz, Gemma, 1975-MINDCOVID Working groupAttempted suicideInterpretabilityMachine learningMental healthSuicidal ideationAims: Studies conducted during the COVID-19 pandemic found high occurrence of suicidal thoughts and behaviours (STBs) among healthcare workers (HCWs). The current study aimed to (1) develop a machine learning-based prediction model for future STBs using data from a large prospective cohort of Spanish HCWs and (2) identify the most important variables in terms of contribution to the model's predictive accuracy. Methods: This is a prospective, multicentre cohort study of Spanish HCWs active during the COVID-19 pandemic. A total of 8,996 HCWs participated in the web-based baseline survey (May-July 2020) and 4,809 in the 4-month follow-up survey. A total of 219 predictor variables were derived from the baseline survey. The outcome variable was any STB at the 4-month follow-up. Variable selection was done using an L1 regularized linear Support Vector Classifier (SVC). A random forest model with 5-fold cross-validation was developed, in which the Synthetic Minority Oversampling Technique (SMOTE) and undersampling of the majority class balancing techniques were tested. The model was evaluated by the area under the Receiver Operating Characteristic (AUROC) curve and the area under the precision-recall curve. Shapley's additive explanatory values (SHAP values) were used to evaluate the overall contribution of each variable to the prediction of future STBs. Results were obtained separately by gender. Results: The prevalence of STBs in HCWs at the 4-month follow-up was 7.9% (women = 7.8%, men = 8.2%). Thirty-four variables were selected by the L1 regularized linear SVC. The best results were obtained without data balancing techniques: AUROC = 0.87 (0.86 for women and 0.87 for men) and area under the precision-recall curve = 0.50 (0.55 for women and 0.45 for men). Based on SHAP values, the most important baseline predictors for any STB at the 4-month follow-up were the presence of passive suicidal ideation, the number of days in the past 30 days with passive or active suicidal ideation, the number of days in the past 30 days with binge eating episodes, the number of panic attacks (women only) and the frequency of intrusive thoughts (men only). Conclusions: Machine learning-based prediction models for STBs in HCWs during the COVID-19 pandemic trained on web-based survey data present high discrimination and classification capacity. Future clinical implementations of this model could enable the early detection of HCWs at the highest risk for developing adverse mental health outcomes. Study registration: NCT04556565.Cambridge University Press202520252025info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/70676http://dx.doi.org/10.1017/S2045796025000198reponame:Repositorio Digital de la UPFinstname:Universitat Pompeu FabraInglésEpidemiol Psychiatr Sci. 2025 May 8;34:e28© The Author(s), 2025. Published by Cambridge University Press. This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.http://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessoai:repositori.upf.edu:10230/706762026-06-12T07:21:37Z
dc.title.none.fl_str_mv Identifying most important predictors for suicidal thoughts and behaviours among healthcare workers active during the Spain COVID-19 pandemic: a machine-learning approach
title Identifying most important predictors for suicidal thoughts and behaviours among healthcare workers active during the Spain COVID-19 pandemic: a machine-learning approach
spellingShingle Identifying most important predictors for suicidal thoughts and behaviours among healthcare workers active during the Spain COVID-19 pandemic: a machine-learning approach
Alayo, Itxaso
Attempted suicide
Interpretability
Machine learning
Mental health
Suicidal ideation
title_short Identifying most important predictors for suicidal thoughts and behaviours among healthcare workers active during the Spain COVID-19 pandemic: a machine-learning approach
title_full Identifying most important predictors for suicidal thoughts and behaviours among healthcare workers active during the Spain COVID-19 pandemic: a machine-learning approach
title_fullStr Identifying most important predictors for suicidal thoughts and behaviours among healthcare workers active during the Spain COVID-19 pandemic: a machine-learning approach
title_full_unstemmed Identifying most important predictors for suicidal thoughts and behaviours among healthcare workers active during the Spain COVID-19 pandemic: a machine-learning approach
title_sort Identifying most important predictors for suicidal thoughts and behaviours among healthcare workers active during the Spain COVID-19 pandemic: a machine-learning approach
dc.creator.none.fl_str_mv Alayo, Itxaso
Alonso Caballero, Jordi
Ferrer Forés, Maria Montserrat
Amigo, Franco
Portillo-Van Diest, Ana
Sanz, Ferran
Serra, Consol
Pérez Solà, Víctor
Mortier, Philippe
Vilagut Saiz, Gemma, 1975-
MINDCOVID Working group
author Alayo, Itxaso
author_facet Alayo, Itxaso
Alonso Caballero, Jordi
Ferrer Forés, Maria Montserrat
Amigo, Franco
Portillo-Van Diest, Ana
Sanz, Ferran
Serra, Consol
Pérez Solà, Víctor
Mortier, Philippe
Vilagut Saiz, Gemma, 1975-
MINDCOVID Working group
author_role author
author2 Alonso Caballero, Jordi
Ferrer Forés, Maria Montserrat
Amigo, Franco
Portillo-Van Diest, Ana
Sanz, Ferran
Serra, Consol
Pérez Solà, Víctor
Mortier, Philippe
Vilagut Saiz, Gemma, 1975-
MINDCOVID Working group
author2_role author
author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Attempted suicide
Interpretability
Machine learning
Mental health
Suicidal ideation
topic Attempted suicide
Interpretability
Machine learning
Mental health
Suicidal ideation
description Aims: Studies conducted during the COVID-19 pandemic found high occurrence of suicidal thoughts and behaviours (STBs) among healthcare workers (HCWs). The current study aimed to (1) develop a machine learning-based prediction model for future STBs using data from a large prospective cohort of Spanish HCWs and (2) identify the most important variables in terms of contribution to the model's predictive accuracy. Methods: This is a prospective, multicentre cohort study of Spanish HCWs active during the COVID-19 pandemic. A total of 8,996 HCWs participated in the web-based baseline survey (May-July 2020) and 4,809 in the 4-month follow-up survey. A total of 219 predictor variables were derived from the baseline survey. The outcome variable was any STB at the 4-month follow-up. Variable selection was done using an L1 regularized linear Support Vector Classifier (SVC). A random forest model with 5-fold cross-validation was developed, in which the Synthetic Minority Oversampling Technique (SMOTE) and undersampling of the majority class balancing techniques were tested. The model was evaluated by the area under the Receiver Operating Characteristic (AUROC) curve and the area under the precision-recall curve. Shapley's additive explanatory values (SHAP values) were used to evaluate the overall contribution of each variable to the prediction of future STBs. Results were obtained separately by gender. Results: The prevalence of STBs in HCWs at the 4-month follow-up was 7.9% (women = 7.8%, men = 8.2%). Thirty-four variables were selected by the L1 regularized linear SVC. The best results were obtained without data balancing techniques: AUROC = 0.87 (0.86 for women and 0.87 for men) and area under the precision-recall curve = 0.50 (0.55 for women and 0.45 for men). Based on SHAP values, the most important baseline predictors for any STB at the 4-month follow-up were the presence of passive suicidal ideation, the number of days in the past 30 days with passive or active suicidal ideation, the number of days in the past 30 days with binge eating episodes, the number of panic attacks (women only) and the frequency of intrusive thoughts (men only). Conclusions: Machine learning-based prediction models for STBs in HCWs during the COVID-19 pandemic trained on web-based survey data present high discrimination and classification capacity. Future clinical implementations of this model could enable the early detection of HCWs at the highest risk for developing adverse mental health outcomes. Study registration: NCT04556565.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/70676
http://dx.doi.org/10.1017/S2045796025000198
url http://hdl.handle.net/10230/70676
http://dx.doi.org/10.1017/S2045796025000198
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Epidemiol Psychiatr Sci. 2025 May 8;34:e28
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by/4.0
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Cambridge University Press
publisher.none.fl_str_mv Cambridge University Press
dc.source.none.fl_str_mv reponame:Repositorio Digital de la UPF
instname:Universitat Pompeu Fabra
instname_str Universitat Pompeu Fabra
reponame_str Repositorio Digital de la UPF
collection Repositorio Digital de la UPF
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869423642686783488
score 15,812455

Similares en LA Referencia