Jalen Brown

National Institutes of Health (NIH)

1 active project

Gender Identity Algorithm

Previous investigations into the use of diagnosis codes for identifying non-binary gender identities used large databases like Kaiser Permanente or Medicare. However, these researchers did not have access to the gold standard where the patient’s self-reported gender identity is known.…

Scientific Questions Being Studied

Previous investigations into the use of diagnosis codes for identifying non-binary gender identities used large databases like Kaiser Permanente or Medicare. However, these researchers did not have access to the gold standard where the patient’s self-reported gender identity is known. We aim to build an algorithm using socio-demographics, diagnosis, procedure, and medication codes from electronic health records that can identify transgender identity in large medical records datasets. Comparing this algorithmic method to the gold standard of self reported gender identity in All of Us will allow us to create a robust algorithm for application in datasets where self-reported gender identity is not collected. Additional strengths of this pilot project include building an algorithm in a dataset with patients across multiple health systems.

Project Purpose(s)

  • Population Health

Scientific Approaches

We propose to create an algorithm with diagnostic, procedure, and medication codes from electronic health records to identify transgender individuals using a gold standard for gender identity. Predictors of transgender status will be selected based on consultations with clinicians with expertise in transgender healthcare. These variables include sociodemographic (age, race/ethnicity), ICD-9/10 diagnosis codes (gender dysphoria), procedure codes for gender-affirming procedures (e.g. hysterectomy), and prescribed medications. We will use machine learning techniques to classify participants as transmen, transwomen or non-binary, including 400 transgender and 520 non-binary participants, in All of Us.

Anticipated Findings

We anticipate that our findings will inform future identification measures of transgender and gender non-conforming/non binary individuals in electronic medical health record systems and/or large epidemiological datasets. This initial assessment will establish a basis for future work to identify health outcomes and risk factors within sexual gender minority populations.

Demographic Categories of Interest

  • Gender Identity

Research Team

Owner:

  • Jalen Brown - Other, National Institutes of Health (NIH)
1 - 1 of 1
<
>
Request a Review of this Research Project

You can request that the All of Us Resource Access Board (RAB) review a research purpose description if you have concerns that this research project may stigmatize All of Us participants or violate the Data User Code of Conduct in some other way. To request a review, you must fill in a form, which you can access by selecting ‘request a review’ below.