Background: Anomalous origin of coronary artery (AOCA) can lead to complications, such as narrowed coronary ostia and aberrant alignments, potentially causing myocardial ischemia due to coronary compression. Symptoms like chest tightness and dyspnea, and in severe cases, myocardial infarction, can be life-threatening. Coronary computed tomography angiography (CCTA) can offer comprehensive insights into the characteristics of the coronary arteries. By integrating CCTA with artificial intelligence techniques, we aimed to analyze CCTA imaging and clinical features in AOCA patients, to predict myocardial infarction and identify features more closely associated with its occurrence. Methods: In this retrospective analysis, we compiled data on 20 characteristics from 131 AOCA patients. The dataset encompassed both CCTA imaging attributes and clinical parameters. To identify the most salient features, we employed the Chi-square feature selection method to include features with Chi scores greater than 1 in the study, thereby narrowing the selection to ten key variables, including cardiac function and gender. Subsequently, we evaluated seven classifiers known for their efficacy in classification tasks. Through rigorous training and testing, we conducted a comparative analysis to identify the top three classifiers with the highest accuracy rates. Results: Among the classifiers employed, the top three performers included the rough tree classifier, linear support vector machine classifier, and bagging ensemble learning classifier. Their respective accuracies were 97.4%, 84.6%, and 97.4% with AUC values of 0.98, 1.0, and 0.99. Conclusions: Machine learning (ML) models can predict myocardial infarction caused by anomalous origins of the right coronary artery, alerting clinicians and enabling timely treatment.