Chicago-based Northwestern Medicine built its own artificial intelligence program that has identified a daily average of 68 incidental findings among diagnostic images, which has triggered follow-ups to prevent delayed care.
The hospital created a program that integrates AI into its electronic health record system to alert displayed findings and recommend follow-ups from radiology reports directly into a physcian's workflow, according to a March 16 press release.
The program, implemented in December 2020, ran on nearly every imaging study ordered at the hospital, screened more than 460,000 imaging studies, and flagged 23,000 for follow-up recommendations.
"Our data shows just how common these incidental findings are in diagnostic imaging studies and further supports the need to find a scalable solution," Mozziyar Etemadi, MD, PhD, of Northwestern Medicine said in the press release. "Our team developed an electronic health record integrated natural language processing system to automatically identify radiographic findings requiring follow-up. Once identified, the AI triggers automatic alerts to both physicians and patients to schedule and track completion of recommended follow-ups."
The hospital is working toward expanding the program to hepatic, thyroid and ovarian findings requiring follow-ups and is also releasing a website that outlines the process of building and deploying this system so that other hospitals and health systems can implement similar technology.