Tech

Researchers develop automated tool to anticipate hospital disease outbreaks

A CDC-funded trial showed the tool successfully reduced outbreaks prior to the Covid-19 pandemic.
article cover

Eugene Mymrin/Getty Images

· 3 min read

Navigate the healthcare industry

Healthcare Brew covers pharmaceutical developments, health startups, the latest tech, and how it impacts hospitals and providers to keep administrators and providers informed.

Researchers have developed an automated tool that serves as a crystal ball of sorts for hospital disease outbreaks.

The tool—designed by researchers from the CDC, Harvard Pilgrim Health Care Institute, HCA Healthcare, and the University of California, Irvine Health—can help medical professionals anticipate outbreaks of hundreds of pathogens and is meant to be an “early warning system” for hospitals, according to a CDC-funded study published in April. The researchers found that the tool had helped achieve a 64% reduction in the size of potential outbreaks in a pre-pandemic clinical trial (dubbed the Cluster trial) involving 82 HCA-owned hospitals across 16 states.

Outbreaks at hospitals are a common and costly issue—an estimated one in every 31 hospitalized patients in the US has at least one hospital-acquired infection at any given time, costing healthcare systems “billions of dollars” annually, according to the US Department of Health and Human Services.

“Despite significant progress in reducing healthcare-associated infection outbreaks…they remain an industry challenge and can present as clusters that signal potential for transmission to patients,” Joseph Perz, quality standards and safety team leader for the Division of Healthcare Quality Promotion at the CDC, said in a statement. “The Cluster trial provides evidence that early detection powered by automation tools and quick action can prevent outbreaks from growing.”

How it works: The automated tool uses an algorithm powered with data about organisms grown from patient clinical cultures.

The tool automatically reviews that data and uses statistical analysis to see if there’s an increase in more than 100 different bacterial and fungal species that could indicate an increased pathogen spread. If an increase is detected, the tool sets off an alert to notify staff, who can then take steps to mitigate further spread.

The tool notified hospitals about possible outbreaks roughly three times per year per hospital in the clinical trial, according to the researchers.

The trial took place between 2019 and 2022. The 64% reduction in outbreak size occurred from 2019 to the start of the Covid-19 pandemic, and researchers noted that once the pandemic hit, the tool did not effectively help prevent the spread of other outbreaks, as clinicians weren’t able to respond to the automated alerts.

“Outbreaks in hospitals are often missed or detected late, after preventable infections have occurred,” Meghan Baker, an assistant professor of population medicine at Harvard Medical School and Harvard Pilgrim Health Care Institute and lead investigator of the study, said in a statement. “This study provides a practical and standardized approach to identify early transmission and halt events that could become an outbreak in hospitals.”

Navigate the healthcare industry

Healthcare Brew covers pharmaceutical developments, health startups, the latest tech, and how it impacts hospitals and providers to keep administrators and providers informed.