Application of machine learning to predict the occurrence of arrhythmia after acute myocardial infarction
Open Access
- 2 November 2021
- journal article
- research article
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 21 (1) , 1-14
Abstract
Background: Early identification of the occurrence of arrhythmia in patients with acute myocardial infarction plays an essential role in clinical decision-making. The present study attempted to use machine learning (ML) methods to build predictive models of arrhythmia after acute myocardial infarction (AMI). Methods: A total of 2084 patients with acute myocardial infarction were enrolled in this study. (All data is available on Github: https://github.com/wangsuhuai/AMI-database1.git). The primary outcome is whether tachyarrhythmia occurred during admission containing atrial arrhythmia, ventricular arrhythmia, and supraventricular tachycardia. All data is randomly divided into a training set (80%) and an internal testing set (20%). Apply three machine learning algorithms: decision tree, random forest (RF), and artificial neural network (ANN) to learn the training set to build a model, then use the testing set to evaluate the prediction performance, and compare it with the model built by the Global Registry of Acute Coronary Events (GRACE) risk variable set. Results: Three ML models predict the occurrence of tachyarrhythmias after AMI. After variable selection, the artificial neural network (ANN) model has reached the highest accuracy rate, which is better than the model constructed using the Grace variable set. After applying SHapley Additive exPlanations (SHAP) to make the model interpretable, the most important features are abnormal wall motion, lesion location, bundle branch block, age, and heart rate. Among them, RBBB (odds ratio [OR]: 4.21; 95% confidence interval [CI]: 2.42–7.02), ≥ 2 ventricular walls motion abnormal (OR: 3.26; 95% CI: 2.01–4.36) and right coronary artery occlusion (OR: 3.00; 95% CI: 1.98–4.56) are significant factors related to arrhythmia after AMI. Conclusions: We used advanced machine learning methods to build prediction models for tachyarrhythmia after AMI for the first time (especially the ANN model that has the best performance). The current study can supplement the current AMI risk score, provide a reliable evaluation method for the clinic, and broaden the new horizons of ML and clinical research. Trial registration Clinical Trial Registry No.: ChiCTR2100041960.Keywords
All Related Versions
This publication has 64 references indexed in Scilit:
- Restrictive Left Ventricular Filling Pattern and Risk of New-Onset Atrial Fibrillation After Acute Myocardial InfarctionThe American Journal of Cardiology, 2011
- The Toronto score for in-hospital mortality after percutaneous coronary interventionsAmerican Heart Journal, 2009
- Atrial fibrillation in acute myocardial infarction: a systematic review of the incidence, clinical features and prognostic implicationsEuropean Heart Journal, 2008
- Early Sustained Ventricular Arrhythmias Complicating Acute Myocardial InfarctionThe American Journal of Medicine, 2008
- Risk Stratification of Patients With Acute Anterior Myocardial Infarction and Right Bundle-Branch BlockCirculation, 2006
- Ventricular arrhythmias after acute myocardial infarction: A 20-year community studyAmerican Heart Journal, 2006
- Increased risk of sudden and non-sudden cardiovascular death in patients with atrial fibrillation/flutter following acute myocardial infarctionEuropean Heart Journal, 2005
- Sustained ventricular tachycardia or fibrillation in the cardiac catheterization laboratory among patients receiving primary percutaneous coronary interventionJACC, 2004
- The Telephone Directory, a Source of Evidence for HistoriansJournal of the History of Medicine and Allied Sciences, 1982
- Left ventricular and coronary angiographic anatomy. Relationship to ventricular irritability in the late hospital phase of acute myocardial infarction.Circulation, 1977