Northwestern Medicine Develops Own Generative AI Tool for Radiology
A Northwestern Medicine team of radiologists and engineers has developed a generative AI system to boost productivity and better identify life-threatening conditions.
In a study published in JAMA Network Open, the AI system was deployed across the 11-hospital Northwestern Medicine network, where nearly 24,000 radiology reports were analyzed over a five-month period in 2024. The Northwestern Medicine team then compared radiograph report creation times and clinical accuracy with and without the AI tool.
They reported an average 15.5% boost in radiograph report completion efficiency — with some radiologists achieving gains as high as 40% — without compromising accuracy. Follow-on work, still unpublished, shows up to 80% efficiency gains and enables the tool for CT scans. The time saved allowed radiologists to return diagnoses much faster, particularly in critical cases in which every second counts.
Senior author on the study is Mozziyar Etemadi, M.D., Ph.D., an assistant professor of anesthesiology at Northwestern University Feinberg School of Medicine and of biomedical engineering at Northwestern’s McCormick School of Engineering. “This is, to my knowledge, the first use of AI that demonstrably improves productivity, especially in healthcare. Even in other fields, I haven’t seen anything close to a 40% boost,” he said in an announcement on the Northwestern Medicine website.
The authors say that Northwestern’s holistic model analyzes the entire X-ray or CT scan. It then generates a report that is 95% complete and personalized to each patient, in the radiologists’ own reporting style, which the radiologist can choose to use, review and finalize. These reports summarize key findings and offer a template to augment the radiologists’ diagnosis and treatment.
“For me and my colleagues, it’s not an exaggeration to say that it doubled our efficiency. It’s such a tremendous advantage and force multiplier,” said co-author Samir Abboud, M.D., chief of emergency radiology at Northwestern Medicine and clinical assistant professor of radiology at Feinberg, in a statement. “On any given day in the ER, we might have 100 images to review, and we don’t know which one holds a diagnosis that could save a life,” Abboud said. “This technology helps us triage faster — so we catch the most urgent cases sooner and get patients to treatment quicker.”
The Northwestern Medicine team also is adapting the AI model to detect potentially missed or delayed diagnoses, such as early-stage lung cancer.
The project team stressed that rather than adapting large, internet-trained models like ChatGPT, the Northwestern Medicine engineers built their own system from scratch using clinical data from within the Northwestern Medicine network, which allowed the team to create a lightweight, nimble AI model designed specifically for radiology at Northwestern.
Two patents have been approved for the Northwestern Medicine technology and others are in various stages of the approval process. The tool is in the early stages of commercialization.
