Insights into building a hypertension predictor leveraging genotypes, phenotypes, ancestral and family history
As with many diseases, hypertension is influenced by both genetic and non-genetic risk factors. We combine genetic-epidemiological approaches with machine learning to develop an understanding of the roles of genetic and non-genetic risk factors. By examining not just genetics, but also fine-scale ancestry, family history, and other risk factors such as age, sex, and lifestyle, we can begin to paint a data-driven understanding of hypertension disease risk and actionability.
Ahna Girshick is fascinated by the creative intersection of humans and technology. She has been an innovator in applying computational and machine learning methods to understanding neuroscience, health care, genetics and music. Ahna holds a Ph.D. from UC Berkeley in Vision Science, and performed her postdoctoral research at New York University as an NIH Fellow.