A deep learning approach for transgender and gender diverse patient identification in electronic health records

Yining Hua; Liqin Wang; Vi Nguyen; Meghan Rieu-Werden; Alex McDowell; David W Bates; Dinah Foer; Li Zhou

doi:10.1016/j.jbi.2023.104507

A deep learning approach for transgender and gender diverse patient identification in electronic health records

J Biomed Inform. 2023 Nov:147:104507. doi: 10.1016/j.jbi.2023.104507. Epub 2023 Sep 29.

Authors

Yining Hua¹, Liqin Wang², Vi Nguyen³, Meghan Rieu-Werden⁴, Alex McDowell⁵, David W Bates⁶, Dinah Foer⁷, Li Zhou⁸

Affiliations

¹ Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA; Department of Epidemiology, Harvard T.H Chan School of Public Health, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA. Electronic address: yininghua@g.harvard.edu.
² Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA. Electronic address: lwang@bwh.harvard.edu.
³ Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA. Electronic address: vnguyen31@bwh.harvard.edu.
⁴ Division of General Medicine, Massachusetts General Hospital, Boston, MA, USA. Electronic address: mrieuwerden@mgh.harvard.edu.
⁵ Health Policy Research Institute, Mongan Institute, Massachusetts General Hospital, Boston, MA, USA; Department of Health Care Policy, Harvard Medical School, Boston, MA, USA. Electronic address: amcdowell4@mgh.harvard.edu.
⁶ Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA. Electronic address: dbates@bwh.harvard.edu.
⁷ Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA; Division of Allergy and Clinical Immunology, Department of Medicine, Brigham and Women's Hospital, USA. Electronic address: dfoer@bwh.harvard.edu.
⁸ Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA. Electronic address: lzhou@bwh.harvard.edu.

PMID: 37778672
PMCID: PMC10687838 (available on 2024-11-01)
DOI: 10.1016/j.jbi.2023.104507

Abstract

Background: Although accurate identification of gender identity in the electronic health record (EHR) is crucial for providing equitable health care, particularly for transgender and gender diverse (TGD) populations, it remains a challenging task due to incomplete gender information in structured EHR fields.

Objective: Using TGD identification as a case study, this research uses NLP and deep learning to build an accurate patient gender identity predictive model, aiming to tackle the challenges of identifying relevant patient-level information from EHR data and reducing annotation work.

Methods: This study included adult patients in a large healthcare system in Boston, MA, between 4/1/2017 to 4/1/2022. To identify relevant information from massive clinical notes, we compiled a list of gender-related keywords through expert curation, literature review, and expansion via a fine-tuned BioWordVec model. This keyword list was used to pre-screen potential TGD individuals and create two datasets for model training, testing, and validation. Dataset I was a balanced dataset that contained clinician-confirmed TGD patients and cases without keywords. Dataset II contained cases with keywords. The performance of the deep learning model was compared to traditional machine learning and rule-based algorithms.

Results: The final keyword list consists of 109 keywords, of which 58 (53.2%) were expanded by the BioWordVec model. Dataset I contained 3,150 patients (50% TGD) while Dataset II contained 200 patients (90% TGD). On Dataset I the deep learning model achieved a F1 score of 0.917, sensitivity of 0.854, and a precision of 0.980; and on Dataset II a F1 score of 0.969, sensitivity of 0.967, and precision of 0.972. The deep learning model significantly outperformed rule-based algorithms.

Conclusion: This is the first study to show that deep learning-integrated NLP algorithms can accurately identify gender identity using EHR data. Future work should leverage and evaluate additional diverse data sources to generate more generalizable algorithms.

Keywords: Electronic health records; Gender identity; Machine learning; Natural language processing; Sexual and gender minorities; Transgender persons.

Publication types

Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, P.H.S.
Research Support, N.I.H., Extramural

MeSH terms

Adult
Algorithms
Deep Learning*
Electronic Health Records
Female
Gender Identity
Humans
Male
Transgender Persons*

Abstract

Publication types

MeSH terms

Grants and funding