Key result
A random forest machine learning model accurately predicted acute myocardial infarction and all-cause mortality within 1 month in emergency department patients with chest pain, achieving AUCs of 0.915 and 0.999, respectively.
Why the study?
A big-data-driven AI and machine learning approach had never been integrated with hospital information systems to predict MACE in emergency department patients with chest pain.
Does a random forest AI prediction model accurately predict acute myocardial infarction and all-cause mortality within 1 month in emergency department patients with chest pain?
Cohort (n=85,254)
Yes
Does a random forest AI prediction model accurately predict acute myocardial infarction and all-cause mortality within 1 month in emergency department patients with chest pain?
Effect estimate: AUC 0.915
A real-time AI prediction model using a random forest algorithm integrated into the hospital information system demonstrated high accuracy for predicting 1-month AMI and all-cause mortality in ED patients with chest pain.
No takes yet. Share an insight, caveat, or question.
AI model integrated with HIS shows high accuracy for MACE prediction in ED chest pain; leaves open impact on clinical outcomes before adoption.
Zhang et al. (2020) conducted a cohort in Chest pain in the emergency department (n=85,254). Random forest machine learning model vs. Logistic regression, support-vector clustering (SVC), and K-nearest neighbor (KNN) models was evaluated on Prediction of acute myocardial infarction < 1 month (AUC 0.915). A random forest machine learning model accurately predicted acute myocardial infarction and all-cause mortality within 1 month in emergency department patients with chest pain, achieving AUCs of 0.915 and 0.999, respectively.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: