“…The 14 feature variables recruited for the analyzes were the suggested predictors of MACE in previous studies as follows [5,6,14]: age, sex, smoking, body mass index (BMI), and past histories of hypertension (ICD-9-CM: 401-405 or ICD-10: I10-I16), hyperlipidemia (ICD-9-CM: 272.0-272.5, 277.7 or ICD-10: E78.0-E78.5, E88.81), diabetes (ICD-9-CM: 250 or ICD-10: E08-E13), chronic kidney disease (ICD-9-CM: 585 or ICD-10: N18), coronary artery disease (ICD-9-CM: 410-414 or ICD-10: I20-I25), cerebrovascular diseases (ICD-9-CM: 430-438 or ICD-10: I60-I69, G45), peripheral artery occlusive disease (ICD-9-CM: 443.9 or ICD-10: I73.9), and last laboratory data including high sensitive troponin-I, hemoglobin, and serum creatinine. The last high sensitive troponin-I is automatically captured into the AI prediction model when the ED physician pushes the AI button in the HIS when they need assistance.…”