Using machine learning techniques to differentiate acute coronary syndrome

摘要: Backgroud: Acute coronary syndrome (ACS) is an unstable and dynamic process that includes angina, ST elevation myocardial infarction, non-ST infarction. Despite recent technological advances in early diognosis of ACS,  differentiating between different types diseases the hours admission controversial. The present study was aimed to accurately differentiate various events, using machine learning techniques. Such methods, as a subset artificial intelligence, include algorithms allow computers learn play major role treatment decisions. Methods: 1902 patients diagnosed with ACS  admitted hospital were selected according Euro Heart Survey on ACS. Patients classified based decision tree J48. Bagging aggregation implemented increase efficiency algorithm. Results: performance classifiers estimated compared their accuracy computed from confusion matrix. rates bagging algorithm calculated be 91.74% 92.53%, respectively. Conclusion: proposed methods used this proved have ability identify In addition, matrix confusion, acceptable number subjects acute identified each class.