Temporal and Geographic Patterns of Documentation of Sexual Orientation and Gender Identity Keywords in Clinical Notes

Abstract

Objective: Disclosure of sexual orientation and gender identity correlates with better outcomes, yet data may not be available in structured fields in electronic health record data. To gain greater insight into the care of sexual and gender-diverse patients in the Veterans Health Administration (VHA), we examined the documentation patterns of sexual orientation and gender identity through extraction and analyses of data contained in unstructured electronic health record clinical notes. Methods: Salient terms were identified through authoritative vocabularies, the research team’s expertise, and frequencies, and the use of consistency in VHA clinical notes. Term frequencies were extracted from VHA clinical notes recorded from 2000 to 2018. Temporal analyses assessed usage changes in normalized frequencies as compared with nonclinical use, relative growth rates, and geographic variations. Results: Over time most terms increased in use, similar to Google ngram data, especially after the repeal of the “Don’t Ask Don’t Tell” military policy in 2010. For most terms, the usage adoption consistency also increased by the study’s end. Aggregated use of all terms increased throughout the United States. Conclusion: Term usage trends may provide a view of evolving care in a temporal continuum of changing policy. These findings may be useful for policies and interventions geared toward sexual and gender-diverse individuals. Despite the lack of structured data, the documentation of sexual orientation and gender identity terms is increasing in clinical notes.

Clinical documentation of patient identities in the electronic health record: Ethical principles to consider.

“…The second area of research to consider is the use of large administrative data sets, which can be used to examine identity language. Studies using natural language processing suggest documentation practices have changed as providers have begun to document patient sexual orientation (Lynch et al, 2021) and gender identity (Workman et al, 2023) more frequently over time. These methods can be used to examine the speed with which providers adopt new terms or discard less preferred terms, as well as any systemic level differences in health care outcomes that may vary based on whether a particular organization or clinic uses updated identity language in its documentation.…”

Sexual and Gender Minority Status and Suicide Mortality: An Explainable Artificial Intelligence Analysis

“…Second, we did not assume that people without disclosed LGBT status are not LGBT. Third, LGBT documentation is increasing over time [ 46 ] and the social pressure associated with LGBT is decreasing. Consequently, this study can be viewed as a second-generation disparities study [ 47 ], in that it identifies several risk factors that account for group differences in prevalence of the outcome.…”

Relationship Between Pain and LGBT Status Among Veterans in Care in a Retrospective Cross-Sectional Cohort

“…Using data from the Corporate Data Warehouse, a national repository of data of over 9 million Veterans in care that contains all clinical, administrative, laboratory, and pharmacy data for every Veteran in the VHA nationwide, patients were classified as LGBT or non-LGBT from Fiscal year (FY) 2010 to 2019 (ie, October 1, 2010 to September 30, 2019), using natural language processing. 12 , 13 Fifteen established key terms (Lesbian, Gay, Bisexual, Transgender, Trans woman, Transwoman, Trans man, Transman, Cisgender, Homosexual, LGBT, LGBTQ, LGBTQI, Queer, and Intersex) were used to capture LGBT status. 12 The natural language processing method had 88.2% sensitivity and 91.5% specificity to identify LGBT status.…”

“… 12 , 13 Fifteen established key terms (Lesbian, Gay, Bisexual, Transgender, Trans woman, Transwoman, Trans man, Transman, Cisgender, Homosexual, LGBT, LGBTQ, LGBTQI, Queer, and Intersex) were used to capture LGBT status. 12 The natural language processing method had 88.2% sensitivity and 91.5% specificity to identify LGBT status. 12 All VHA patients with one or more visits to primary care, defined by clinic stop codes (27, 301, 310, 318, 319, 322, 323, 348, 350, and 404), in the observation period were eligible, and the cohort entry (ie, enrollment date) was the first primary care visit.…”