Multidimensional management of atherosclerotic cardiovascular disease From model development to clinical validation

This thesis focused on improving cardiovascular risk management by addressing the identification, risk assessment, and treatment of individuals at risk for atherosclerotic cardiovascular disease (ASCVD). Part I investigated the need for improved identification of high-risk patients, revealing that nearly half of those who experienced myocardial infarctions had not been adequately identified or treated. Part II introduced novel artificial intelligence (AI)-guided algorithms that utilized biomarkers and coronary imaging to more accurately estimate cardiovascular risk. These AI models outperformed traditional methods in predicting long-term ASCVD risk and plaque progression. Part III explored the clinical utility of these novel risk models, demonstrating their potential to improve diagnostic confidence, reduce unnecessary testing, and optimize therapy in real-world settings. Part IV reviewed advanced therapeutic options for lowering ASCVD risk, emphasizing the importance of personalized treatment strategies based on individual risk profiles, including genetic and biomarker data. The findings highlight the promise of integrating AI, genetics, and biomarkers for personalized ASCVD management and stress the need for early and potent interventions. Prospective trials are recommended to validate these innovative approaches and facilitate their integration into clinical practice.