About:
I’m a data scientist and 3rd year medical student at the University of New Mexico.
I have an MS (admitted as PhD) in
Biomedical Data Science from Stanford University.
My interdisciplinary BA is in Mathematics,
Statistics, and Physical, Natural & Social Sciences with minors in Navajo
Language & Linguistics and Chicana & Chicano Studies in 2015. I
worked as research assistant in the Dept. of Economics at Harvard University
and was a fellow at the
Washington University School of Medicine Mallinckrodt Institute of
Radiology.
Research:
Missing data is a fundamental problem for research and applications that
leverage real world data. It is often addressed by simply dropping observations
with missing features, a frequent offender in the limitations paragraph(s) of
published research.
My research sought to create a method that could accept arbitrary feature set
inputs for neural network based modeling tasks, which would allow use
of observations that would have otherwise have been dropped. I then sought
to demonstrate how the method could be used to represent human sex as a
continuous variable that captured known physiologic variation due to age,
genetics, and environmental exposures.
I also developed a computer vision method to isolate and featurize
autofluorescent signals in megapixel resolution, multiplexed immunofluorescence
imaging studies. I also studied multi-class segmentation algorithms in the
context of high-grade, gliomas and I have published work on natural language
processing methods used in the setting of patient-provider messages as well as
policy research regarding disparity in insurance coverage and stoke treatment.
Publications: