AI Image Analysis: Detecting Multiple Diseases
- artificial intelligence is expanding its role in medical diagnostics, now capable of detecting early signs of cardiovascular disease from routine computed tomography (CT) scans.
- The study, presented Dec. 4 at the Radiological Society of North America (RSNA) meeting in Chicago, involved reanalyzing abdominal CT scans to assess the aorta, the body's main...
- Miriam Bredella,MD,MBA,the Bernard and Irene Schwartz Professor of Radiology at NYU Grossman School of Medicine,explained the goal is to use AI to screen abdominal CT scans,catching heart disease...
AI is revolutionizing medical diagnostics by detecting heart disease risks from routine CT scans. Researchers are leveraging this technology for “opportunistic screening,” analyzing existing images to identify aortic calcium buildup, a key indicator of cardiovascular events.This innovative approach could predict heart attack risk with remarkable accuracy, potentially offering earlier interventions and preventing severe health complications. The study, conducted by NYU Langone Health, showcases how advanced AI algorithms analyze abdominal CT scans usually taken for other purposes. News Directory 3 highlights this groundbreaking work. Discover what’s next as AI continues to reshape healthcare.
AI Identifies Heart Disease Risks in Routine CT Scans
artificial intelligence is expanding its role in medical diagnostics, now capable of detecting early signs of cardiovascular disease from routine computed tomography (CT) scans. This “opportunistic screening” approach, spearheaded by researchers at NYU Langone Health, repurposes existing medical images initially taken for other reasons, such as identifying tumors or infections.
The study, presented Dec. 4 at the Radiological Society of North America (RSNA) meeting in Chicago, involved reanalyzing abdominal CT scans to assess the aorta, the body’s main artery. Researchers used AI to measure aortic calcium levels,assigning a score to predict the risk of major cardiovascular events like heart attacks.
Miriam Bredella,MD,MBA,the Bernard and Irene Schwartz Professor of Radiology at NYU Grossman School of Medicine,explained the goal is to use AI to screen abdominal CT scans,catching heart disease earlier. This method avoids relying solely on dedicated coronary artery CT scans, which are less common and often not fully covered by insurance.
The team analyzed 3,662 CT scans from 2013 to 2023, focusing on older adults in the New York area who had both abdominal and coronary artery scans. The AI-driven measurements of aortic calcification accurately predicted calcification in the coronary arteries and the risk of cardiovascular events, suggesting that abdominal scans alone could be used for heart attack risk prediction.
The study found that individuals with aortic artery calcification were 2.2 times more likely to experiance a major heart attack, brain vessel blockage, or require procedures to restore blood flow within three years. This occurred in 324 participants. Moreover, the analysis revealed early signs of arterial calcium buildup in 29% of participants previously thought to be clear of such issues.
This research builds on a previous study published in Bone, which demonstrated opportunistic screening’s effectiveness in diagnosing osteoporosis.That study, also using AI, analyzed lung cancer screening CT scans to identify bone loss in 3,708 patients. The results showed important rates of osteoporosis across various racial and economic groups.
Bredella noted that opportunistic screening could improve the diagnosis and treatment of osteoporosis,especially in vulnerable groups like the elderly and smokers. She added that this work lays the groundwork for addressing prevention and screening gaps for osteoporosis, heart disease, cancer, and diabetes.
“Instead of relying on dedicated CT scans of coronary arteries…we seek to use AI to help screen abdominal CT scans that are done for many reasons to opportunistically catch heart disease more often and earlier,” Bredella said.
What’s next
Bredella emphasized the need for further research to confirm whether imaging data and analysis can provide sufficient early identification of individuals at high risk for coronary disease or osteoporosis, enabling effective treatment to reduce illness and death.