A.I. predicts how patients with viral infections, like COVID-19, will fare
SAN DIEGO (KUSI) – Researchers at U.C. San Diego School of Medicine have discovered a way to figure out how the immune system will respond to a viral infection.
This research could provide vital information for the current pandemic, and future pandemics.
Debashish Sahoo, Ph.D., Assistant Professor at UC San Diego School of Medicine, and one of the lead authors of the study, joined KUSI’s Ginger Jeffries to discuss the study’s findings.
Sahoo wanted to use his computer science background to find something that all viral pandemics have in common so that the knowledge could be used as a guide.
Specifically, researchers used an A.I. algorithm to look through terabytes of gene expression data, noticing which genes are “on” or “off” while infected, and point out shared patterns in patients with past pandemic viral infections, such as SARS, MERS and swine flu.
Publicly available sources of patient gene expression data were used to test and train the algorithm.