Grant supports speedy sorting of health records by phenotypeFeb. 11, 2021, 9:01 AM
by Paul Govern
Wei-Qi Wei, MD, PhD, assistant professor of Biomedical Informatics and scientific director of the Precision Phenotyping Core at the Center for Precision Medicine, has been awarded a four-year, $1.7 million grant from the National Institutes of Health (grant GM139891) to continue development of high-throughput software for quickly identifying traits of interest, or phenotypes, in electronic health records (EHRs).
EHRs, in the aggregate, are increasingly a resource for biomedical discovery. As a common starting point of observational studies, researchers search for records that reflect a phenotype of interest, typically a disease. Unfortunately, these searches aren’t straightforward in the least. For a given disease of interest, it takes time and effort for experts to devise, test and refine electronic selection algorithms. These elaborate preliminaries are seen as slowing discovery.
To dramatically pick up the pace, in May 2020 Vanderbilt University Medical Center began offering researchers everywhere, as a free download, the prototype of a tool devised by Wei and colleagues, called PheMAP, or Phenotyping by Measured, Automated Profile.
With some 1,400 phenotypes currently in its quiver, in one quick scan of an EHR data base, PheMAP can tell researchers each record’s probability of having a given phenotype, and this can easily be transferred into case or control status for an observational study. In prototype testing, PheMAP’s accuracy has already proved comparable to or better than that of bespoke algorithms.
“For research teams around the world, with this project we want to improve efficiency and help make research on the EHR more nimble,” Wei said. “We are grateful to the NIH for this generous support for the continued refinement of PheMAP.”