Format

Send to

Choose Destination
Ethn Dis. 2019 Jun 13;29(Suppl 2):441-450. doi: 10.18865/ed.29.S2.441. eCollection 2019.

Development of a Natural Language Processing Algorithm to Identify and Evaluate Transgender Patients in Electronic Health Record Systems.

Author information

1
Vanderbilt University, Departments of Anesthesiology, Surgery, Biomedical Informatics, Health Policy; Nashville, Tennessee.
2
Vanderbilt University Medical Center, Program for LGBTQ Health; Nashville, Tennessee.
3
Northwestern University, Institute for Sexual and Gender Minority Health & Wellbeing, Chicago, Illinois.
4
Western Kentucky University, Department of Psychology; Bowling Green, Kentucky.
5
Vanderbilt University, Departments of Biomedical Informatics & Computer Science; Nashville, Tennessee.

Abstract

Objective:

To create a natural language processing (NLP) algorithm to identify transgender patients in electronic health records.

Design:

We developed an NLP algorithm to identify patients (keyword + billing codes). Patients were manually reviewed, and their health care services categorized by billing code.

Setting:

Vanderbilt University Medical Center.

Participants:

234 adult and pediatric transgender patients.

Main Outcome Measures:

Number of transgender patients correctly identified and categorization of health services utilized.

Results:

We identified 234 transgender patients of whom 50% had a diagnosed mental health condition, 14% were living with HIV, and 7% had diabetes. Largely driven by hormone use, nearly half of patients attended the Endocrinology/Diabetes/Metabolism clinic. Many patients also attended the Psychiatry, HIV, and/or Obstetrics/Gynecology clinics. The false positive rate of our algorithm was 3%.

Conclusions:

Our novel algorithm correctly identified transgender patients and provided important insights into health care utilization among this marginalized population.

KEYWORDS:

Electronic Health Records; Natural Language Processing; Transgender; Utilization

PMID:
31308617
PMCID:
PMC6604788
[Available on 2019-12-13]
DOI:
10.18865/ed.29.S2.441

Supplemental Content

Loading ...
Support Center