The PET/CT artificial intelligence model performed better than clinical data in predicting heart attack risk in individuals with established coronary artery disease.
Predicting a heart attack in standard clinical practice is difficult. Cardiovascular risk factors and scores are commonly used to predict the chance of a heart attack, especially in individuals with suspected coronary artery disease. Cardiovascular risk factors and scores, on the other hand, don’t always represent the whole picture in individuals with established coronary artery disease.
According to the research published in the January edition of The Journal of Nuclear Medicine, clinicians can enhance their prediction of heart attacks by integrating information from two sophisticated imaging modalities with clinical data. When evaluated together in the AI model, coronary 18F-NaF uptake on PET and quantitative coronary plaque characteristics on CT angiography were found to be complementary, significant predictors of heart attack risk in patients with prior coronary artery disease, providing risk prediction superior to clinical data alone.
“Recently, advanced imaging techniques have demonstrated considerable promise in determining which coronary artery disease patients are most at risk for a heart attack. These techniques include 18F-sodium fluoride (18F-NaF) PET, which assesses disease activity in the coronary arteries, and CT angiography, which provides a quantitative plaque analysis. Our goal in the study was to investigate whether the information provided by 18F-NaF PET and CT angiography is complementary and could improve prediction of heart attacks with the use of artificial intelligence techniques” told Piotr J. Slomka, PhD, FACC, FASNC, FCCPM, director of Innovation in Imaging at Cedars-Sinai Medical Center in Los Angeles, California.
The study included nearly 300 participants with documented coronary artery disease. All patients had a baseline clinical examination that included an assessment of their cardiovascular risk factor profile. All patients had a hybrid 18F-NaF PET and contrasted CT coronary angiography. By combining essential characteristics from the clinical evaluation, 18F-NaF PET results, and quantitative CT data, machine learning—a sort of artificial intelligence—was applied to create a combined score for heart attack risk.
Compared to clinical data alone, the machine learning model demonstrated a significant improvement in heart attack prediction. This method showed that 18F-NaF PET and CT angiography are complementary and additive, with the combination offering the highest accurate result prediction.
Story Source: Jacek Kwiecinski et al, Machine Learning with 18F-Sodium Fluoride PET and Quantitative Plaque Analysis on CT Angiography for the Future Risk of Myocardial Infarction, Journal of Nuclear Medicine (2021). DOI: 10.2967/jnumed.121.262283
Dr. Tamanna Anwar is a Scientist and Co-founder of the Centre of Bioinformatics Research and Technology (CBIRT). She is a passionate bioinformatics scientist and a visionary entrepreneur. Dr. Tamanna has worked as a Young Scientist at Jawaharlal Nehru University, New Delhi. She has also worked as a Postdoctoral Fellow at the University of Saskatchewan, Canada. She has several scientific research publications in high-impact research journals. Her latest endeavor is the development of a platform that acts as a one-stop solution for all bioinformatics related information as well as developing a bioinformatics news portal to report cutting-edge bioinformatics breakthroughs.
