This project aims to explore the pathogenesis of Myocardial Infarction with Non-Obstructive Coronary Arteries (MINOCA). The primary research objectives are: 1) To explore the relationships between MINOCA and demographic, sociological, lifestyle, metabolic biomarker, and genetic factors; 2) To identify environmental factors affecting the efficacy and safety of MINOCA treatments; and 3) To develop AI algorithms that integrate multimodal imaging, multi-omics, and genetic data to enhance the accuracy of MINOCA diagnosis, risk stratification, and prognosis.
The scientific rationale is that the long-term prognosis for MINOCA remains poor due to an incomplete understanding of its underlying mechanisms. Personalized medicine is crucial for improving outcomes, necessitating a deeper understanding of risk factors and mechanisms. This project will employ data-driven AI techniques-including deep learning, machine learning, statistical learning, and genomic analysis-to integrate multimodal data. This integration aims to precisely identify novel disease biomarkers, potential environmental etiological factors, and genetic variants to guide the diagnosis, treatment, and prognosis of MINOCA.