Development of a natural language processing algorithm to identify and evaluate transgender patients in electronic health record systems

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.