Communications of the ACM
Amid a Pandemic, a Health Care Algorithm Shows Promise and Peril
Introducing machine learning into the triage process has the potential to improve inpatient care by highlighting new links between clinical data and outcomes, but it could also over-sensitize young physicians to the specific tests and health factors that
Vishal Khetpal, M.D., MSc is an internal medicine resident physician training in the Brown University Internal Medicine Program. Nishant R. Shah, M.D., MPH is an assistant professor of medicine at the Alpert Medical School of Brown University and an assistant professor of health services, practice, and policy at the Brown University School of Public Health.
In the midst of 2020's pandemic uncertainty, private electronic health record giant Epic accelerated the deployment of a clinical prediction tool called the Deterioration Index (DI) to help physicians decide when to move a patient into or out of intensive care. The DI is poised to upend a key cultural practice in medicine—triage—augmenting, or perhaps entirely replacing it with machine learning and big data.
The authors contend, however, that the DI remains proprietary and was not independently validated or peer-reviewed before it was rapidly deployed to America’s largest health care systems, raising a host of issues.
From Undark
View Full Article
No entries found