Hospital system uses AI to root out, investigate radiologist errors in CT analysis

Sutter Health has launched a new artificial intelligence tool that helps administrators catch missed cancer diagnoses before they snowball into an untreatable state.

The Sacramento, California-based provider uses this new AI platform to analyze both medical images and radiologist reports, with algorithms detecting overlooked abnormalities and flagging them for follow-up. Leaders at the 24-hospital system are specifically targeting lung cancer care and are one of the first to use the platform on CT scans, according to an announcement.

"For those rare instances where a nodule is overlooked, we can in a very quick time period—usually within 24 hours—continue the care process instead of waiting until larger nodules are detected at a later medical visit," Charles McDonnell III, MD, a Sutter Medical Group radiologist and associate medical director of risk management, said in a statement. "Having a system for quality coverage of our diagnostic decisions makes us stronger, more effective advocates for our patients, and gives patients greater comfort and peace of mind."

In the instances where there is an unnoticed nodule or other discrepancy, the AI system tags the report and then sends it back to chest imaging experts and the hospital quality committee for investigation. If confirmed, experts transmit the report back to the original radiologist for revision, according to the announcement.

Since launching AI quality review in CT last year, the platform has reviewed about 10,000 images, flagging 83 for additional radiologist review. And a smaller subset of that group did, in fact, require intervention, the team noted.

These gains are on top of the health system already reporting discrepancy rates four times lower than the estimated national rate of error.

"This is a testament to the quality of work done by our radiologists on behalf of our patients," added Jason Wiesner, MD, a radiologist and medical director of the health system's diagnostic imaging service line. "We are giving our doctors and patients a safety net and ensuring we continue to provide the highest quality of care.”

Marty Stempniak

Marty Stempniak has covered healthcare since 2012, with his byline appearing in the American Hospital Association's member magazine, Modern Healthcare and McKnight's. Prior to that, he wrote about village government and local business for his hometown newspaper in Oak Park, Illinois. He won a Peter Lisagor and Gold EXCEL awards in 2017 for his coverage of the opioid epidemic. 

Trimed Popup
Trimed Popup