EUVIMEDDescoperă EUVIMED
Open access

Prediction of early‐onset bipolar using electronic health records

Bo Wang, Yi-Han Sheu, Hyunjoon Lee, Robert G Mealer, Victor M Castro, Jordan W Smoller

Journal of Child Psychology and Psychiatry · 2025-08 · 66 (8) · 1141-1154

DOI: 10.1111/jcpp.14131 ↗

At a glance

Journal article in Journal of Child Psychology and Psychiatry, published online on 2025-02-18. Written by Bo Wang and 5 co-authors. Institution: Center for Precision Psychiatry, Massachusetts General Hospital, Boston, MA, USA. Major MEDLINE topics: Bipolar Disorder, Electronic Health Records, Machine Learning, Attention Deficit Disorder with Hyperactivity. Cited 10 times so far (Crossref); 51 references. The full text is freely available in PubMed Central. Funded by: NIMH NIH HHS, Ryan Licht Sang Bipolar Foundation, National Institute of Mental Health.

RezumatSubjectsDate bibliograficeCiteRelated studies

Abstract (original language)

Background

Early identification of bipolar disorder (BD) provides an important opportunity for timely intervention. In this study, we aimed to develop machine learning models using large‐scale electronic health record (EHR) data including clinical notes for predicting early‐onset BD.

Methods

Structured and unstructured data were extracted from the longitudinal EHR of the Mass General Brigham health system. We defined three cohorts aged 10–25 years: (1) the full youth cohort ( N = 300,398); (2) a subcohort defined by having a mental health visit ( N = 105,461); and (3) a subcohort defined by having a diagnosis of mood disorder or ADHD ( N = 35,213). By adopting a prospective landmark modeling approach that aligns with clinical practice, we developed and validated a range of machine learning models, across different cohorts and prediction windows.

Results

We found the two tree‐based models, random forests (RF) and light gradient‐boosting machine (LGBM), achieving good discriminative performance across different clinical settings (area under the receiver operating characteristic curve 0.76–0.88 for RF and 0.74–0.89 for LGBM). In addition, we showed comparable performance can be achieved with a greatly reduced set of features, demonstrating computational efficiency can be attained without significant compromise of model accuracy.

Conclusions

Good discriminative performance for models predicting early‐onset BD can be achieved utilizing large‐scale EHR data. Our study offers a scalable and accurate method for identifying youth at risk for BD that could help inform clinical decision‐making and facilitate early intervention. Future work includes evaluating the portability of our approach to other healthcare systems and exploring considerations regarding possible implementation.

Subjects

MeSH terms (MEDLINE)

Bipolar DisorderElectronic Health RecordsMachine LearningAttention Deficit Disorder with HyperactivityHumansAdolescentChildYoung AdultFemaleMaleAdultLongitudinal Studies

Author keywords

Early‐onset bipolar disorderelectronic health recordmachine learningmood disordersrisk prediction

Authors and institutions

  • Center for Precision Psychiatry, Massachusetts General Hospital, Boston, MA, USA.
  • Psychiatric and Neurodevelopmental Genetics Unit, Massachusetts General Hospital, Boston, MA, USA.
  • Department of Psychiatry, Harvard Medical School, Boston, MA, USA.
  • Stanley Center for Psychiatric Research, Broad Institute of MIT and Harvard, Cambridge, MA, USA.
  • Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA.
  • Department of Psychiatry, Oregon Health & Science University, Portland, OR, USA.

Funding

  • NIMH NIH HHS
  • Ryan Licht Sang Bipolar Foundation
  • National Institute of Mental Health

Cite

APA

Wang, B., Sheu, Y. H., Lee, H., Mealer, R. G., Castro, V. M., & Smoller, J. W. (2025). Prediction of early‐onset bipolar using electronic health records. Journal of Child Psychology and Psychiatry, 66(8), 1141-1154. https://doi.org/10.1111/jcpp.14131

Vancouver

Wang B, Sheu YH, Lee H, Mealer RG, Castro VM, Smoller JW. Prediction of early‐onset bipolar using electronic health records. Journal of Child Psychology and Psychiatry. 2025;66(8):1141-1154. doi:10.1111/jcpp.14131

BibTeX
@article{Wang2025,
  author = {Wang, Bo and Sheu, Yi-Han and Lee, Hyunjoon and Mealer, Robert G and Castro, Victor M and Smoller, Jordan W},
  title = {Prediction of early‐onset bipolar using electronic health records},
  journal = {Journal of Child Psychology and Psychiatry},
  year = {2025},
  volume = {66},
  number = {8},
  pages = {1141--1154},
  doi = {10.1111/jcpp.14131}
}
Start for free →