Improving health outcomes for underserved transgender and gender non-conforming populations

Symbols of man and woman cast shadow in the form of transgender on blue

A team led by Yi Guo, Ph.D. and Jiang Bian, Ph.D., will present their research on developing computable phenotype algorithms for identifying transgender and gender non-conforming individuals in electronic health records at the 2020 American Medical Informatics Association (AMIA) Annual Symposium in November.

Yi Guo
Yi Guo, Ph.D.

According to Guo, an assistant professor of biomedical informatics at HOBI, the phenotyping algorithms enable scientists to access and use electrontic health records to study health conditions unique to transgender and gender non-conforming individuals, which could lead to improved health outcomes for this underserved population.

The  research team included co-authors Xing He, a Ph.D. candidate in biomedical informatics at HOBI, and HOBI researchers Yonghui Wu, Ph.D., François Modave, Ph.D., William Hogan, M.D., Christopher Harle, Ph.D., and Elizabeth Shenkman, Ph.D. Other members of the team include Merry Jennifer Markham, M.D., from UF Health’s Division of Hematology and Oncology, and Mengjun Xie, Ph.D., from the University of Tennessee at Chattanooga.

Their paper was among a handful selected from more than 1,350 submissions across all categories for publication in AMIA’s 2020 Annual Symposium Proceedings.