Duke AI Health Director Michael Pencina, PhD, who is a professor of biostatistics and bioinformatics at Duke and serves as the medical school’s vice dean for data science and information technology, was recently quoted in an article appearing in STAT News examining the use of commercially developed predictive algorithms in medicine.

In an investigative report for STAT News, correspondent Casey Ross spoke with employees in multiple health systems across the country that use clinical algorithms created by Epic, one of the nation’s largest electronic health record vendors. A series of recent studies and academic publications have cast doubt on the reliability of some of these algorithms, with researchers reporting flaws in their performance while also noting that their opacity makes them difficult to evaluate and optimize. A machine learning tool developed to alert clinicians to sepsis risk has come under particular scrutiny.

“I would say Epic and other developers have used the environment to their advantage,” said Pencina in his comments to Ross for the STAT article. “Our naiveté has enabled this kind of behavior. I think it’s time for health systems to say, ‘No, we’re not going to take it just because you can deliver it easily. Before we can use it, it needs to be evaluated so we can trust that it will perform well in our setting.’”

The full story is available at STAT News (article requires log-in).