Robert Becker

Graduate Trainee, Vanderbilt University

2 active projects

Transgender Identification Model

Trying to develop an inter-institutional NLP model to help identify transgender cohorts using EHR data for retrospective studies. AoU has the gold-standard of self-identification. I want to fine-tune a model on AoU data and see how well it performs on…

Scientific Questions Being Studied

Trying to develop an inter-institutional NLP model to help identify transgender cohorts using EHR data for retrospective studies. AoU has the gold-standard of self-identification. I want to fine-tune a model on AoU data and see how well it performs on VUMC's de-identified dataset.

Project Purpose(s)

  • Methods Development

Scientific Approaches

AoU data, VUMC Synthetic derivative data. NLP and structured queries for ICD9/10 codes, CPT, RxNorm, and other terminologies that coincide with transgender identity. Much Like Guo et. al.'s work on developing a computable phenotype for transgender population.

Anticipated Findings

I hope to see if, by using a gold standard for identification, we can develop a standardized approach to transgender cohort identification across institutions. This could be especially helpful for smaller/rural institutions without the resources or knowledge to develop their own model.

Demographic Categories of Interest

  • Gender Identity

Research Team

Owner:

Duplicate of AMIA Genomics Walkthrough - My Copy

This workspace is intended to provide basic instruction for using genomics data in All of Us, including cohort identification, covariate extraction, analysis, and display of results.

Scientific Questions Being Studied

This workspace is intended to provide basic instruction for using genomics data in All of Us, including cohort identification, covariate extraction, analysis, and display of results.

Project Purpose(s)

  • Educational

Scientific Approaches

We use OMOP, the cohort builder, and Hail for genomics analysis. The approach will be a simple rule based algorithm along with some open access genomic data to simulate a GWAS.

Anticipated Findings

We do not anticipate any findings as the analysis will not be real. Therefore this will not contribute to scientific knowledge, but hopefully will contribute to individual user's knowledge.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Research Team

Owner:

1 - 2 of 2
<
>
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.