Northwestern Medicine’s pioneering AI technology enhances radiology efficiency by up to 40%, addresses the global radiologist shortage and flags critical health conditions in real time.
Northwestern Medicine has unveiled a first-of-its-kind generative AI system that promises to revolutionize the field of radiology by significantly boosting productivity, rapidly identifying life-threatening conditions and offering a potential solution to the global radiologist shortage.
This breakthrough, detailed in a study published in JAMA Network Open, has far-reaching implications for the health care industry.
“This is, to my knowledge, the first use of AI that demonstrably improves productivity, especially in health care. Even in other fields, I haven’t seen anything close to a 40% boost,” senior author Mozziyar Etemadi, an assistant professor of anesthesiology at Northwestern University Feinberg School of Medicine and of biomedical engineering at Northwestern’s McCormick School of Engineering, said in a news release.
The AI system analyzed nearly 24,000 radiology reports across the Northwestern Medicine network’s 12 hospitals over five months in 2024.
The study found that the AI enhanced report completion efficiency by an average of 15.5%, with some radiologists achieving up to a 40% increase — without compromising accuracy.
Boosting Efficiency and Accuracy
Notable for being integrated directly into clinical workflows, Northwestern’s AI system is the first generative AI radiology tool to demonstrate high accuracy and increased efficiency across all types of X-rays, from skulls to toes.
“For me and my colleagues, it’s not an exaggeration to say that it doubled our efficiency,” added co-author Samir Abboud, the chief of emergency radiology at Northwestern Medicine and a clinical assistant professor of radiology at Feinberg. “It’s such a tremendous advantage and force multiplier.”
Identifying Critical Conditions in Real Time
Beyond efficiency, the AI tool flags life-threatening conditions such as pneumothorax (collapsed lung) in real time, before a radiologist examines the X-rays.
Automated tools scan the AI-generated reports for critical findings and cross-check them with patient records. This capability allows for quicker triaging and potentially life-saving interventions.
“This technology helps us triage faster — so we catch the most urgent cases sooner and get patients to treatment quicker,” Abboud added.
Custom Engineered for Radiology
Unique among AI tools, this system was built entirely in-house using clinical data from the Northwestern Medicine network.
Unlike large, pre-trained AI models like ChatGPT, the custom-built system is designed specifically for radiology, offering greater speed and accuracy with less computing power.
“There is no need for health systems to rely on tech giants,” added first author Jonathan Huang, a third-year medical student who holds a doctorate in biomedical engineering from McCormick.
Addressing a Global Shortage
The AI system also offers a strategic solution to a looming crisis in radiology. With the United States potentially facing a shortage of up to 42,000 radiologists by 2033, the AI tool could help alleviate backlogs and ensure quicker diagnostic results.
Northwestern’s technology, which is in the early stages of commercialization and has two patents approved, aims to support radiologists rather than replace them.
“You still need a radiologist as the gold standard,” Abboud concluded. “Medicine changes constantly — new drugs, new devices, new diagnoses — and we have to make sure the AI keeps up. Our role becomes ensuring every interpretation is right for the patient.”
Source: Northwestern University