Business News

In a first, FDA authorizes AI-based test to predict sepsis in hospitals

Bobby Reddy Jr. walked around a hospital as he built his startup, observing how patient care began with a diagnosis and followed a set protocol. The electrical engineer thought he knew a better solution: an artificial intelligence tool that would individualize treatment.

Today, the Food and Drug Administration gave the green light to such a test developed by Reddy’s company, Chicago-based Prenosis, to predict the risk of sepsis — a complex disease that contributes to at least 350,000 deaths per year. year in the United States. It is the first AI-based algorithmic diagnostic tool for sepsis will receive the green light from the FDA, the company announced in a statement Wednesday.

“In hospitals and emergency departments, we always rely on a one-size-fits-all solution, when instead we should be treating each person based on their individual biology,” Reddy, the company’s CEO, said in an interview.

Sepsis occurs when a patient’s immune system tries to fight an infection and ends up attacking the body’s own organs. Sepsis management is a priority among federal health agencies, including the Centers for Disease Control and Prevention and the Centers for Medicare and Medicaid Services.

“Sepsis is a serious and sometimes life-threatening complication,” Jeff Shuren, director of the FDA’s Center for Devices and Radiological Health, said in a statement. “Technologies developed to help prevent this disease have the potential to provide significant benefit to patients. »

To build its test, Prenosis acquired more than 100,000 blood samples as well as clinical data from hospitalized patients and trained its algorithm to recognize the health measures most associated with the development of sepsis. The company limited its test to 22 parameters, including blood measurements and other vital signs such as temperature and heart rate. The diagnostic tool now produces a snapshot that classifies a patient’s sepsis risk into four categories, from low to very high.

However Prenosis is the first to obtain FDA authorization for such a test. Other companies, including Epic Systems, have already brought AI-based diagnostics for this disease to market. Epic, known for its electronic health records management software, has faced questions about the accuracy of its sepsis prediction algorithm.

Jacob Wright, an Epic spokesperson, said several studies showed its sepsis diagnostic model improved patient outcomes, adding that a second version released in 2022 “contains fewer false positives compared to the first version”. The company is seeking FDA authorization, he said.

Reddy said Prenosis built its technology without initially knowing what problem it would try to solve. A hospital in Illinois gave him office space and a badge, allowing him to move around the hospital and observe its staff interacting with patients. “What I’ve seen over and over again is that they actually operate based on protocols,” he said. Later, he came across an article about sepsis, he said, which opened his eyes to how many people are dying from it. “That’s what we’re going to do,” he said.

At least 1.7 million adults develop sepsis in a given year, including at least 350,000 who die while hospitalized or are referred to hospice care, according to the CDC. About 1 in 3 people who die in hospitals suffered from sepsis during their stay, and federal agencies aim to reward facilities that make progress in reducing the disease.

People at higher risk of sepsis include adults 65 and older, people with weakened immune systems, and those who have recently been seriously ill or hospitalized.

The new test comes as hospitals grapple with the future of medicine and how best to integrate artificial intelligence into practice. In some cases, artificial intelligence tools have created tension among frontline workers who fear the technology could lead to inaccurate results or replacement of staff.

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button