Predicting cardiovascular disease in patients with mental illness using machine learning

Abstract Background Cardiovascular disease (CVD) is twice as prevalent among individuals with mental illness compared to the general population. Prevention strategies exist but require accurate risk prediction. This study aimed to develop and validate a machine learning model for predicting incide...

Full description

Saved in:
Bibliographic Details
Main Authors: Martin Bernstorff, Lasse Hansen, Kevin Kris Warnakula Olesen, Andreas Aalkjær Danielsen, Søren Dinesen Østergaard
Format: Article
Language:English
Published: Cambridge University Press 2025-01-01
Series:European Psychiatry
Subjects:
Online Access:https://www.cambridge.org/core/product/identifier/S092493382500001X/type/journal_article
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850182994682183680
author Martin Bernstorff
Lasse Hansen
Kevin Kris Warnakula Olesen
Andreas Aalkjær Danielsen
Søren Dinesen Østergaard
author_facet Martin Bernstorff
Lasse Hansen
Kevin Kris Warnakula Olesen
Andreas Aalkjær Danielsen
Søren Dinesen Østergaard
author_sort Martin Bernstorff
collection DOAJ
description Abstract Background Cardiovascular disease (CVD) is twice as prevalent among individuals with mental illness compared to the general population. Prevention strategies exist but require accurate risk prediction. This study aimed to develop and validate a machine learning model for predicting incident CVD among patients with mental illness using routine clinical data from electronic health records. Methods A cohort study was conducted using data from 74,880 patients with 1.6 million psychiatric service contacts in the Central Denmark Region from 2013 to 2021. Two machine learning models (XGBoost and regularised logistic regression) were trained on 85% of the data from six hospitals using 234 potential predictors. The best-performing model was externally validated on the remaining 15% of patients from another three hospitals. CVD was defined as myocardial infarction, stroke, or peripheral arterial disease. Results The best-performing model (hyperparameter-tuned XGBoost) demonstrated acceptable discrimination, with an area under the receiver operating characteristic curve of 0.84 on the training set and 0.74 on the validation set. It identified high-risk individuals 2.5 years before CVD events. For the psychiatric service contacts in the top 5% of predicted risk, the positive predictive value was 5%, and the negative predictive value was 99%. The model issued at least one positive prediction for 39% of patients who developed CVD. Conclusions A machine learning model can accurately predict CVD risk among patients with mental illness using routinely collected electronic health record data. A decision support system building on this approach may aid primary CVD prevention in this high-risk population.
format Article
id doaj-art-4ebed6f348e146189be40f1201fc824f
institution OA Journals
issn 0924-9338
1778-3585
language English
publishDate 2025-01-01
publisher Cambridge University Press
record_format Article
series European Psychiatry
spelling doaj-art-4ebed6f348e146189be40f1201fc824f2025-08-20T02:17:28ZengCambridge University PressEuropean Psychiatry0924-93381778-35852025-01-016810.1192/j.eurpsy.2025.1Predicting cardiovascular disease in patients with mental illness using machine learningMartin Bernstorff0https://orcid.org/0000-0002-0234-5390Lasse Hansen1https://orcid.org/0000-0003-1113-4779Kevin Kris Warnakula Olesen2https://orcid.org/0000-0002-0560-3615Andreas Aalkjær Danielsen3https://orcid.org/0000-0002-6585-3616Søren Dinesen Østergaard4https://orcid.org/0000-0002-8032-6208Department of Affective Disorders, Aarhus University Hospital – Psychiatry, Aarhus, Denmark Department of Clinical Medicine, Aarhus University, Aarhus, Denmark Center for Humanities Computing, Aarhus University, Aarhus, DenmarkDepartment of Affective Disorders, Aarhus University Hospital – Psychiatry, Aarhus, Denmark Department of Clinical Medicine, Aarhus University, Aarhus, Denmark Center for Humanities Computing, Aarhus University, Aarhus, DenmarkDepartment of Cardiology, Aarhus University Hospital, Aarhus, DenmarkDepartment of Affective Disorders, Aarhus University Hospital – Psychiatry, Aarhus, Denmark Department of Clinical Medicine, Aarhus University, Aarhus, DenmarkDepartment of Affective Disorders, Aarhus University Hospital – Psychiatry, Aarhus, Denmark Department of Clinical Medicine, Aarhus University, Aarhus, Denmark Abstract Background Cardiovascular disease (CVD) is twice as prevalent among individuals with mental illness compared to the general population. Prevention strategies exist but require accurate risk prediction. This study aimed to develop and validate a machine learning model for predicting incident CVD among patients with mental illness using routine clinical data from electronic health records. Methods A cohort study was conducted using data from 74,880 patients with 1.6 million psychiatric service contacts in the Central Denmark Region from 2013 to 2021. Two machine learning models (XGBoost and regularised logistic regression) were trained on 85% of the data from six hospitals using 234 potential predictors. The best-performing model was externally validated on the remaining 15% of patients from another three hospitals. CVD was defined as myocardial infarction, stroke, or peripheral arterial disease. Results The best-performing model (hyperparameter-tuned XGBoost) demonstrated acceptable discrimination, with an area under the receiver operating characteristic curve of 0.84 on the training set and 0.74 on the validation set. It identified high-risk individuals 2.5 years before CVD events. For the psychiatric service contacts in the top 5% of predicted risk, the positive predictive value was 5%, and the negative predictive value was 99%. The model issued at least one positive prediction for 39% of patients who developed CVD. Conclusions A machine learning model can accurately predict CVD risk among patients with mental illness using routinely collected electronic health record data. A decision support system building on this approach may aid primary CVD prevention in this high-risk population. https://www.cambridge.org/core/product/identifier/S092493382500001X/type/journal_articleartificial intelligencecardiovascular diseasespsychiatryprecision medicine
spellingShingle Martin Bernstorff
Lasse Hansen
Kevin Kris Warnakula Olesen
Andreas Aalkjær Danielsen
Søren Dinesen Østergaard
Predicting cardiovascular disease in patients with mental illness using machine learning
European Psychiatry
artificial intelligence
cardiovascular diseases
psychiatry
precision medicine
title Predicting cardiovascular disease in patients with mental illness using machine learning
title_full Predicting cardiovascular disease in patients with mental illness using machine learning
title_fullStr Predicting cardiovascular disease in patients with mental illness using machine learning
title_full_unstemmed Predicting cardiovascular disease in patients with mental illness using machine learning
title_short Predicting cardiovascular disease in patients with mental illness using machine learning
title_sort predicting cardiovascular disease in patients with mental illness using machine learning
topic artificial intelligence
cardiovascular diseases
psychiatry
precision medicine
url https://www.cambridge.org/core/product/identifier/S092493382500001X/type/journal_article
work_keys_str_mv AT martinbernstorff predictingcardiovasculardiseaseinpatientswithmentalillnessusingmachinelearning
AT lassehansen predictingcardiovasculardiseaseinpatientswithmentalillnessusingmachinelearning
AT kevinkriswarnakulaolesen predictingcardiovasculardiseaseinpatientswithmentalillnessusingmachinelearning
AT andreasaalkjærdanielsen predictingcardiovasculardiseaseinpatientswithmentalillnessusingmachinelearning
AT sørendinesenøstergaard predictingcardiovasculardiseaseinpatientswithmentalillnessusingmachinelearning