A Machine-Learning Model for Optimal Allocation of Limited Medical Resources to Covid-19 Patients

*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************

Contact

Laurie Haigh
Communications Manager

Sidebar Content
No sidebar content submitted.
Summaries

Summary Sentence:

GT researchers built a predictive model based on patient data to anticipate the course of the disease on an individual basis.

Full Summary:

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.

Media
  • Healthcare workers assisting COVID-19 patient Healthcare workers assisting COVID-19 patient
    (image/jpeg)
  • Harold E. Smalley Professor Chuck Zhang Harold E. Smalley Professor Chuck Zhang
    (image/jpeg)
  • Gwaltney Chair in Manufacturing Systems and Professor Ben Wang Gwaltney Chair in Manufacturing Systems and Professor Ben Wang
    (image/jpeg)

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.

Additional Information

Groups

The Supply Chain and Logistics Institute (SCL)

Categories
Research
Related Core Research Areas
Data Engineering and Science, Systems
Newsroom Topics
No newsroom topics were selected.
Keywords
covid-19, machine learning, predictive health
Status
  • Created By: Andy Haleblian
  • Workflow Status: Published
  • Created On: Dec 10, 2020 - 5:13pm
  • Last Updated: Dec 11, 2020 - 8:28am