The escalating number of Covid-19 cases in the U.S. led to a critical shortage of medical supplies, including medicine, equipment, and personnel to treat infected patients. To make the best use of available resources, a team led by Harold E. Smalley Professor Chuck Zhang and Gwaltney Chair in Manufacturing Systems and Professor Ben Wang developed a machine-learning model to inform clinical decisions and optimize resource allocation.

Specifically, the team built a predictive model based on patient data collected by Georgia hospitals — medical history, symptoms, and test results — to anticipate the course of the disease for each individual. The goal? Identify which patients would recover and could be safely sent home; determine which patients would deteriorate quickly and require hospitalization and/or life support; and predict the outcome of patients requiring life support.

Phase one of the project was a success. “We achieved our goal by creating the predictive model that can help medical professionals and hospitals optimize treatment plans and resource utilization, which has been confirmed by our collaborators in the hospitals,” Zhang said.

During the second phase of the project, the team will develop a comprehensive model to help healthcare systems optimize operations and resource allocation for future Covid-19 outbreaks or other pandemics.