Machine Learning Finds Personalized Combos to Prevent COVID-19 Recurrence

A machine-learning study has found the best drug combinations to prevent COVID-19 recurrence, which affects as many as one-third of patients. The researchers found these drug combos are not the same for every patient. Individual characteristics, including age, weight, and additional illness determine which combinations most effectively reduce recurrence. Using real-world data from a hospital in China, the UC Riverside-led study has been published in the journal Frontiers in Artificial Intelligence. The lead author is Song Zhai, senior researcher at Merck, in Rahway. The study project began in April 2020, about a month into the pandemic. At the time, most studies were focused on death rates. However, doctors in Shenzhen, near Hong Kong, were more concerned about recurrence rates because fewer people there were dying. For this study, we pioneered a technique to attack the challenge of confounding factors by virtually matching people with similar characteristics who were undergoing different treatment combinations.