Cardiovascular risk from comprehensive evaluation of the CT calcium score exam

点击翻译按钮获取中文摘要

AI prediction of aortic valve disease and its role in MACE using free, or low-cost, CT calcium score ex- ams Supplement to NIH R01HL165218 parent, “Cardiovascular risk from comprehensive evaluation of the CT calci- um score exam” Summary Using a comprehensive machine learning analysis of aortic valve calcifications, we will predict aortic valve ste- nosis and future major adverse cardiovascular events (MACE). Earlier identification of patients at risk of aortic valve stenosis will improve preemptive patient management (e.g., monitoring, lifestyle changes, and possibly emerging medications) for this disease, which can often go unnoticed. In addition, detection methods could enable the trend of performing transcatheter aortic valve replacement (TAVR) earlier in the disease process and will enable trials of medical treatments. Aside from their role in aortic valve disease, aortic valve calcifica- tions have been shown to be associated with MACE. Improved characterization of MACE risk will also improve personalized patient management. With improved MACE risk prediction and identification of high-risk pheno- types, there will be an opportunity to guide precision preventive therapies, where guidance is needed, given the cost and side effects associated with some of these therapies. We will use large archives of CT calcium score exams, including those from the University Hospitals of Cleveland, which is an institution with the largest no-cost CT calcium scoring program (>100,000 scanned patients, >13,000 scans per year), providing a unique opportunity to create new personalized approaches for healthcare. Numerous technical innovations are planned, including novel methods for aortic valve calcium identification, calcium features, and machine- learning approaches. Research in the supplement is very synergistic with research in the parent grant, where we are predicting MACE using coronary calcium-omics and fat-omics features. In addition to clinical risk pre- diction, our CT calcium score analyses will dovetail in the future with many research interests, including the role of genes, metabolomics, co-morbidities (e.g., chronic kidney disease and hyperlipidemia), socio-economic status, and cardio-oncology on cardiovascular risk. As there are interesting sex and race implications associat- ed with aortic valve stenosis, we will carefully determine the role of these variables in our early diagnosis risk models.