Opportunistic screening with AI could be a game-changer for preventive cardiology

 

Artificial intelligence (AI) is being used more and more to perform opportunistic screening of computed tomography (CT) scans for a variety of diseases. This is believed to be one way care teams can potentially change the course of preventive care in the near future, and it has been a growing topic at radiology and cardiology conferences in recent years. 

One study study presented at the Society of Cardiovascular CT (SCCT) 2024 meeting led by Brittany Nicole Weber, MD, PhD, director of the Cardio-Rheumatology Clinic at Brigham and Women’s Hospital, is shedding light on the potential of using opportunistic screening in CT scans to detect cardiovascular disease (CVD). This study explored the use of the HealthCCSng AI algorithm developed by Nanox, which was cleared by the FDA in 2021 to identify coronary artery calcium (CAC) in CT scans originally performed for noncardiac reasons. Weber said this strategy could significantly improve early detection and intervention in patients at risk for cardiovascular events. Coronary calcium is a marker of coronary disease on imaging and can be seen in any types of CT scans of the chest. The software can identify and quantify the calcium burden to risk stratify a patient without human intervention.

"Patients with autoimmune disorders are at a significantly higher risk for cardiovascular disease, largely due to systemic inflammation. However, many of these patients are not receiving the preventive therapies they need," Weber explained in an interview with Cardiovascular Business. 

The study included non-ECG gated chest CT scans from the past decade from more than 2,000 patients with known autoimmune disorders such as lupus, rheumatoid arthritis and psoriatic disease. She said these patients frequently undergo chest CTs for various noncardiac indications.

The results were striking. Over 50% of the patients had detectable CAC, with the highest prevalence found in those with psoriasis. This finding suggests that systemic inflammation associated with immune-mediated systemic inflammatory diseases (IMIDs) such as psoriasis could be strongly correlated with the risk of cardiovascular disease.

"Even patients with mild evidence of atherosclerosis were at a higher risk for adverse cardiovascular events," Weber noted. This points to the potential value of opportunistic screening in identifying patients who might benefit from earlier intervention and prevention therapies.

Changing how patients are screened for early disease detection

The study also highlighted the promise of AI in automating the detection of incidental findings in CT scans. Rather than a hospital system creating a formal program like those used for mammography or low-dose lung CT to detect cancers, AI would just search through current and previous imaging studies to find patients with undetected diseases, based on data from their electronic medical records.

"This technology could enable us to act on existing data in the medical record, potentially transforming how we approach prevention in high-risk populations," Weber explained.

The AI screenings also allow more diagnostic value for patients to be extracted from any of the exams they get. 

"Many patients undergo imaging of the chest for completely different reasons than cardiac exams. They may undergo a chest CT if they have any symptoms or concerns about pneumonia or lung cancer screening. And often when we look at those chest CTs, we can see if there's coronary calcifications. So there are plenty of papers that have described this that have shown that these findings are rarely reported. And even when they are reported by radiologists, often the severity or amount of plaque is not reported. Now there's an opportunity with AI to analyze those images and to detect and quantify the amount of calcified plaque. And there are groups, ours and others, that are looking at what happens when you provide this information to physicians," explained a co-author on the study, Ron Blankstein, MD, associate director of the cardiovascular imaging program and director of cardiac computed tomography at Brigham and Women’s Hospital and a professor of medicine and radiology at Harvard Medical School

Nanox and several other vendors are developing opportunistic screening AI for a variety of diseases. The FDA has already cleared some AI algorithms that can identify some types of incidental findings in radiology exams. AI automation can take these types of incidental findings to the next level by sending alerts to designated people who can then followup with patients for additional consultation or testing.

FDA clears colchicine for preventive treatment of coronary inflammation

The importance of detecting and treating coronary inflammation has gained attention over the years. That momentum increased significantly following the FDA's 2023 approval of colchicine, the first drug indicated for treating coronary inflammation. This has spurred interest in identifying inflammation-related cardiovascular risks in patients, going beyond traditional prevention methods like statins.

The new drug indication and the known higher rates of heart disease in patient with inflammatory diseases has also has given rise to a growing number of cardio-rheumatology clinics such as Weber's.

Looking forward, Weber envisions a future where opportunistic screening could become a routine part of patient care, particularly for those with IMIDs who might not otherwise receive cardiovascular assessments. 

"The goal is to integrate this into broader health systems, using AI to identify at-risk patients and guide them towards appropriate interventions," she explained.

Watch the video at the top of the page to hear more details from Weber.

Dave Fornell is a digital editor with Cardiovascular Business and Radiology Business magazines. He has been covering healthcare for more than 16 years.

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: dfornell@innovatehealthcare.com

Around the web

Several key trends were evident at the Radiological Society of North America 2024 meeting, including new CT and MR technology and evolving adoption of artificial intelligence.

Ron Blankstein, MD, professor of radiology, Harvard Medical School, explains the use of artificial intelligence to detect heart disease in non-cardiac CT exams.

Eleven medical societies have signed on to a consensus statement aimed at standardizing imaging for suspected cardiovascular infections.