Epic sepsis model’s ability to predict depends on hospital factors

The model performed worse in centers with more cases of sepsis, more patients with multiple health conditions and more oncology patients.

11:17 AM

Author | Kelly Malcom

hospital bed coloring blue yellow
Jacob Dwyer/Justine Ross/Michigan Medicine

In the fight against sepsis, one of the leading causes of death in hospitalized patients, clinicians are increasingly reliant on prediction tools trained on massive amounts of data stored in electronic health records. One of the most popular tools comes from Epic Systems and is used in more than half of United States hospitals. However, research has shown that its performance varies depending on the hospital in which it’s being used.

In a recent research letter published in JAMA Internal Medicine, researchers from U-M, Oregon Health and Sciences University, and Washington University looked for a possible explanation for this variation. Using more than 800,000 patient encounters across 9 hospitals between January 1, 2020 and June 30, 2022, they determined the performance of the model at each hospital: how likely it was to accurately predict the onset of sepsis compared to chance.

They found that the sepsis model performed worse in hospitals with more incidence of sepsis, more patients with multiple health conditions and more patients with cancer. One possible explanation, noted the authors, is sepsis may be difficult to distinguish from other signs and symptoms in sicker patients. “Our findings suggest [sepsis prediction models] may be most useful at lower-acuity hospitals, where sepsis rates may be lower,” they stated.

Paper cited: "Factors associated with variability in the performance of a proprietary sepsis prediction model across 9 networked hospitals in the US," JAMA Internal Medicine. DOI: 10.1001/jamainternmed.2022.7182

More Articles About: Sepsis infectious disease Preventative health and wellness Future Think Emerging Technologies
Health Lab word mark overlaying blue cells
Health Lab

Explore a variety of healthcare news & stories by visiting the Health Lab home page for more articles.

Media Contact Public Relations

Department of Communication at Michigan Medicine

[email protected]


Stay Informed

Want top health & research news weekly? Sign up for Health Lab’s newsletters today!

Featured News & Stories Illustration of scientists and doctors playing basketball in white coats and scrubs
News Release
Four U-M teams selected for virtual tournament of science
U-M researchers' work made the bracket in the 2024 STAT Madness tournament of science, and need public support to advance
Health care provider loads syringe with measles vaccine
Health Lab
Measles: 10 things to know about immunization and prevention
Measles: 10 things to know about immunization and prevention
Drawing of parent trying to get child's attention who is listening to music on headphones
Health Lab
Are headphones and earbuds exposing your children to noise health risks?
2 in 3 parents in national poll say their child ages 5-12 use personal audio devices; pediatrician offers 4 tips to reduce noise exposure risks
colorful illustration with human figure and highlighted lungs
Health Lab
Multimodal AI model may guide personalized treatments for tuberculosis
AI approach helps researchers interpret large biomedical data sets to accurately predict tuberculosis treatment prognosis
Hallie Prescott talking while sitting at a panel table with two individuals.
Health Lab
How do we reduce sepsis nationwide?
Hallie Prescott of the Michigan Medicine Division of Pulmonary & Critical Care Medicine is providing guidance at the state and national level to reduce the burden of sepsis in hospitalized patients.
Medical gloved hand holding test tube sample for HIV testing.
Health Lab
Inequities in HIV testing, diagnosis and care for people with intellectual and developmental disabilities
People with disabilities are often at higher risk for exposure to HIV due to barriers in engaging healthcare and other systemic factors and are thus considered a priority for prevention and testing efforts. However, these efforts don’t always extend to people with intellectual disabilities due to the perception that people with intellectual disabilities are mostly asexual.