Entropy triangle method predicts abnormal heart rhythms with high accuracy
The Entropy Triangle Method (ETM): A novel framework for the prevention of cardiac arrhythmia with a review of more than 10,000 patients
Artificial Intelligence
Summary
Predicting dangerous heart rhythms can help doctors prevent serious health problems. The authors created a new method called the entropy triangle method that uses machine learning to analyze ECG data from over 10,000 patients. Their approach can identify different types of irregular heartbeats with more than 85% accuracy. This involves three steps: preparing the data, creating balanced samples using a new oversampling technique, and then predicting the heart rhythm.
What this means in practice
- •For cardiology device engineers: Incorporate the entropy triangle method to improve arrhythmia prediction accuracy in ECG monitoring devices for early detection of abnormal heart rhythms.$Commercial implications: Enables development of advanced cardiac monitoring devices that better predict arrhythmias, enhancing patient care and enabling new product features.
- •For health data scientists: Use the entropy triangle framework to preprocess and balance large ECG datasets for improved machine learning-based arrhythmia classification.
Authors
Arman daliri
Abstract
One of the most important problems in medicine is to facilitate prediction. In this study, we propose entropy triangle method, a novel framework for predicting heart rhythms using a novel machine learning technique. This framework includes three steps: feature engineering, entropy triangle oversampling, and disease prediction. The dataset used in this study is a 12-lead electrocardiogram (ECG) arrhythmia research database with 10,646 patients. This dataset contains 11 different heart rhythms (5 sinus rhythms and 6 non-sinus rhythms). In this article, we introduce two firsts in machine learning and medicine that can predict non-sinus rhythm with over 85% accuracy. Our experimental results show, among others, that the most accurate classifier based on entropy triangles and the most useful oversampling are the supported vector classifiers and oversampling techniques for shark scent.