The incidence of acute myocardial infarction (AMI) in young patients is on the rise, placing a heavy health and economic burden on individuals, families, and society. The clinical phenotype and pathophysiological mechanisms of AMI in this population exhibit significant heterogeneity compared to elderly patients, and existing risk assessment tools have limited applicability in this specific group. The core problem this study aims to address is: how to accurately identify specific risk factors in young AMI patients and build an effective risk prediction model to prevent and optimize clinical diagnosis and treatment.
This study will adopt a prospective cohort design to collect multi-dimensional clinical data from young AMI patients. It will systematically analyze their clinical characteristics, risk factors, and coronary lesion status to comprehensively map the clinical, risk factor, and pathophysiological diversity of young AMI patients. Secondly, it will delve into identifying specific risk factors that influence the onset, progression, and long-term prognosis of young AMI. Thirdly, it will combine machine learning algorithms to develop a risk prediction model for young AMI, performing internal validation in the prospective cohort and external validation in the MIMIC-IV database. Simultaneously, it will explore novel biomarkers associated with disease onset and progression. The key outcomes of this study are to establish a high-quality clinical database of young AMI patients, design a risk prediction model for young AMI based on the study results, and produce high-level academic publications.