An automated algorithm using free-text clinical notes to improve identification of transgender people.

Accurate identification of transgender persons is a critical first step in conducting transgender health studies. To develop an automated algorithm for identifying transgender individuals from electronic medical records (EMR) using free-text clinical notes. The development and validation of the algorithm was based on data from an integrated healthcare system that served as a participating site in the multicenter Study of Transition Outcomes and Gender. The training and test datasets each contained a total of 300 individuals identified between 2006 and 2014. Both datasets underwent a full medical record review by experienced research abstractors. The validated algorithm was then implemented to identify transgender individuals in the EMR using all clinical notes of patients that received care between January 1, 2015 and June 30, 2018. Validation of the algorithm against the full chart review demonstrated a high degree of accuracy with 97% sensitivity, 95% specificity, 94% positive predictive value, and 97% negative predictive value. The algorithm classified 7,409 individuals (3.5%) as "Definitely transgender" and 679 individuals (0.3%) as "Probably transgender" out of 212,138 candidates with a total of 378,641 clinical notes. The computerized NLP algorithm can support essential efforts to improve the health of transgender people.

Cross-sex Hormones and Acute Cardiovascular Events in Transgender Persons: A Cohort Study.

Background: Venous thromboembolism (VTE), ischemic stroke, and myocardial infarction in transgender persons may be related to hormone use. Objective: To examine the incidence of these events in a cohort of transgender persons. Design: Electronic medical record-based cohort study of transgender members of integrated health care systems who had an index date (first evidence of transgender status) from 2006 through 2014. Ten male and 10 female cisgender enrollees were matched to each transgender participant by year of birth, race/ethnicity, study site, and index date enrollment. Setting: Kaiser Permanente in Georgia and northern and southern California. Patients: 2842 transfeminine and 2118 transmasculine members with a mean follow-up of 4.0 and 3.6 years, respectively, matched to 48 686 cisgender men and 48 775 cisgender women. Measurements: VTE, ischemic stroke, and myocardial infarction events ascertained from diagnostic codes through the end of 2016 in transgender and reference cohorts. Results: Transfeminine participants had a higher incidence of VTE, with 2- and 8-year risk differences of 4.1 (95% CI, 1.6 to 6.7) and 16.7 (CI, 6.4 to 27.5) per 1000 persons relative to cisgender men and 3.4 (CI, 1.1 to 5.6) and 13.7 (CI, 4.1 to 22.7) relative to cisgender women. The overall analyses for ischemic stroke and myocardial infarction demonstrated similar incidence across groups. More pronounced differences for VTE and ischemic stroke were observed among transfeminine participants who initiated hormone therapy during follow-up. The evidence was insufficient to allow conclusions regarding risk among transmasculine participants. Limitation: Inability to determine which transgender members received hormones elsewhere. Conclusion: The patterns of increases in VTE and ischemic stroke rates among transfeminine persons are not consistent with those observed in cisgender women. These results may indicate the need for long-term vigilance in identifying vascular side effects of cross-sex estrogen. Primary Funding Source: Patient-Centered Outcomes Research Institute and Eunice Kennedy Shriver National Institute of Child Health and Human Development.