Popular sepsis prediction tool less accurate than claimed

The algorithm is currently implemented at hundreds of U.S. hospitals.

11:41 AM

Author | Kelly Malcom

doctor holding tablet hospital room with stethoscope
Getty Images

One in three patients who dies in a hospital has sepsis, a severe inflammatory response to an infection, marked by organ dysfunction, according to the Centers for Disease Control and Prevention. This heavy toll makes predicting which patients are at risk for developing the devastating condition a top priority for clinicians.

Additional motivation to identify and treat sepsis cases lies in the fact that sepsis serves as a system-level quality measure, with hospitals judged by both the by the federal Department of Health and Human Services and the CDC on their sepsis rates. Complicating efforts to reduce sepsis is how difficult it can be to diagnose—both accurately and quickly.

"Sepsis is something we can know occurs with certainty after the fact, but when it's unfolding, it's often unclear whether a patient has sepsis or not," said Karandeep Singh, MD, MMSc, assistant professor of Learning Health Sciences and Internal Medicine at Michigan Medicine. "But the cornerstone of sepsis treatment is timely recognition and timely therapy."

Singh and his colleagues recently evaluated a sepsis prediction model developed by Epic Systems, a healthcare software vendor used by 56% of hospitals and health systems in the U.S. In a new paper published in JAMA Internal Medicine, they reveal that the prediction tool performs much worse than indicated by the model's information sheet, correctly sorting patients on their risk of sepsis just 63% of the time.

Like Podcasts? Add the Michigan Medicine News Break on iTunes, Google Podcast or anywhere you listen to podcasts.

The discrepancy lies in how the model was developed, explained Singh. The first problem, he says, is that the model incorporates data from all cases billed as sepsis, which is problematic because "people bill differently across services and hospitals and it's been well recognized that trying to figure out who has sepsis based on billing codes alone is probably not accurate." Second, in the model's development, the onset of sepsis was defined as the time the clinician intervened—for example, ordering antibiotics or lab work.

"In essence, they developed the model to predict sepsis that was recognized by clinicians at the time it was recognized by clinicians. However, we know that clinicians miss sepsis."

To evaluate the model using a definition of sepsis more closely aligned to that used by Medicare and CDC, the research team looked at close to 40,000 hospitalizations at Michigan Medicine from 2018-2019, removing scores from patients who were alerted by the model to have sepsis after a clinician had already intervened. Doing so brought the tool's area under the curve from 76-83% as reported by Epic Systems to 63% determined by the validation study.

What's more, the model sent out an alert on nearly 1 in 5 of all patients, with most of those patients not actually having sepsis. "When it alerts, the chance of a patient actually has sepsis during the remainder of their hospital stay is 12%. What that essentially means is that even if you only evaluated people the first time the system alerted, you'd still need to evaluate 8 people to find one case of sepsis," said Singh.

MORE FROM THE LAB: Subscribe to our weekly newsletter

Prediction tools come with a trade-off, noted Singh. "The tradeoff is basically between generating alerts on a patient who turned out not to have the predicted condition or not generating alerts on patients who do." But in this instance, if a health system is using the Epic sepsis model to improve its quality measures, "it's not really going to be able to do that."

The results of the study point to a need for more regulatory oversight and governance of clinical software tools, said Singh, as well as a need for more open-source models that can be easily externally validated and turned off if it turns out they aren't useful.

He added that Epic isn't wrong in their analysis. "We differ in our definition of the onset and timing of sepsis. In our view, their definition of sepsis based on billing codes alone is imprecise and not the one that is clinically meaningful to a health system or to patients."

Additional authors include Andrew Wong, M.D.; Erkin Otles, MEng; John P. Donnelly, Ph.D.; Andrew Krumm, Ph.D.; Jeffrey McCullough, Ph.D.; Olivia DeTroyer-Cooley, B.S.E.; Justin Pestrue, MEcon; Marie Phillips, B.A.; Judy Konye, M.S.N., R.N.; Carleen Penoza, MHSA, R.N.; and Muhammad Ghous, MBBS.

Paper cited: "External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized Patients," JAMA Internal Medicine. DOI: 10.1001/jamainternmed.2021.2626


More Articles About: Lab Report Hospitals & Centers Health Care Quality Health Care Delivery, Policy and Economics All Research Topics Future Think Emerging Technologies Patient Safety
Health Lab word mark overlaying blue cells
Health Lab

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

Media Contact Public Relations

Department of Communication at Michigan Medicine

[email protected]

734-764-2220

Stay Informed

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

Subscribe
Featured News & Stories yellow tinted graphic moving with mouth opening seeing down throat red and tonsils in pink in back
Health Lab
Study finds tonsil removal not linked to undesirable weight gain, contrary to popular belief
A trial involving Michigan Medicine researchers has upended a long-held belief that adenotonsillectomies for children with mild sleep-disordered breathing lead to undesirable weight gain.
patient looking at paper with provider in scrubs blue in clinic
Health Lab
How race impacts patients’ response to cancer immunotherapy
The first large scale analysis finds immune checkpoint inhibitors are equally effective in Black and white patients, with Black patients having fewer side effects.
bone close up of cells inside green bbble with cells inside in yellow brown pink and red orange background
Health Lab
How breast cancer cells survive in bone marrow after remission
A new study from researchers at the University of Michigan and the University of California San Diego has shed light on a previously poorly understood aspect of breast cancer recurrence: how cancer cells survive in bone marrow despite targeted therapies.
emergency sign wording in red on brick building
Health Lab
Refining tools that spot risk of violence in young adults in urban ERs may save lives
Half of young adult patients treated in emergency departments in three urban hospitals across the country reported experiencing violence either as a victim or aggressor, including firearm violence, in the six months prior to seeking treatment, according to a University of Michigan study.
Microscope
Health Lab
Nerve damage reduced in prediabetic mice with diet, exercise
A low calorie diet and high intensity exercise can reduce nerve damage in prediabetic mice, according to a Michigan Medicine study.
frozen dial with ice on it with red dial
Health Lab
Enzyme identified as new therapeutic target for “cold” tumors
A study identifies an enzyme as a new therapeutic target for “cold” tumors.