FDA clears opportunistic AI for detecting cardiothoracic issues in CT scans
The U.S. Food and Drug Administration (FDA) has cleared HeartLung Corporation's AI-CVD, an artificial intelligence (AI) algorithm that can perform 11 different opportunistic health screening assessments on chest CT exams ordered for any reason.
The AI works in the background to review scans for various types of incidental findings that can enhance preventive medicine by issuing alerts for doctors to follow up on. It can also assess previous CT exams to identify patients who may need additional follow-up imaging.
AI-CVD automatically looks at coronary artery calcium (CAC) scoring, aortic wall calcium, aortic valve calcium, mitral valve calcium, cardiac chamber volumetry, epicardial fat volumetry, aorta and pulmonary artery sizing, lung attenuation analysis, liver attenuation analysis, bone mineral density and muscle–fat composition. These quantitative measurements can be used to estimate a patient's cardiac risk score and detect early signs coronary artery disease, heart failure, atrial fibrillation, stroke, osteoporosis, liver steatosis, diabetes, or other adverse health conditions.
With this 510(k) clearance, AI-CVD became the most comprehensive FDA-cleared opportunistic screening platform available for CT imaging. The company said the technology can be used on nearly 40 million CT scans performed each year in the United States. HeartLung said this represents about half of all CT scans.
“For decades, medicine has waited for patients to declare disease. AI-CVD allows us to find disease while it is still silent using scans that already exist,” Morteza Naghavi, MD, founder and president of HeartLung, said in a statement. “This FDA clearance represents a fundamental shift. CT is no longer just diagnostic imaging, it becomes a scalable, opportunistic prevention platform capable of identifying risk across the heart, lungs, bones, liver and metabolism in a single pass.”
Radiology and cardiology experts see opportunistic AI as a major change in preventive screening
Interest in opportunistic AI assessments is on the rise as a way to get more useful information out of existing CT imaging. Supporters of the technology in radiology and cardiology say opportunistic imaging could change preventive care significantly in the coming years with a more proactive approach for health screenings.
“Coronary calcium revealed long ago that atherosclerosis begins well before symptoms,” said Arthur Agatston, MD, a clinical professor of medicine at Florida International University, developer of the Agatston Coronary Calcium Score and member of HeartLung’s Scientific Advisory Board. “AI-CVD extends that insight by enabling systematic identification of patients who are unaware of their cardiovascular risk—using CT scans that already exist.”
Agatston was an early adopter of coronary CT angiography (CCTA) and sees the latest generation of CCTA imaging systems with high-resolution imaging combined with AI as a major shift in how patients will be screened and tracked for cardiovascular disease in the future.
“Modern CT contains far more clinically meaningful information than we traditionally extract,” added David Yankelevitz, MD, a professor of radiology with Icahn School of Medicine at Mount Sinai and member of HeartLung’s Scientific Advisory Board. “AI-CVD allows clinicians to leverage routine CT scans responsibly and efficiently, without adding imaging burden. That is exactly how opportunistic screening should be done and we are now entering the new domain of comprehensive screening”
Dave Fornell has covered healthcare for more than 17 years, with a focus in cardiology and radiology. Fornell is a 5-time winner of a Jesse H. Neal Award, the most prestigious editorial honors in the field of specialized journalism. The wins included best technical content, best use of social media and best COVID-19 coverage. Fornell was also a three-time Neal finalist for best range of work by a single author. He produces more than 100 editorial videos each year, most of them interviews with key opinion leaders in medicine. He also writes technical articles, covers key trends, conducts video hospital site visits, and is very involved with social media. E-mail: [email protected]