High-Performance Personalized Heartbeat Classification Model for Long-Term ECG Signal

TLDR

Long‑term ECG is a key diagnostic tool for detecting cardiovascular diseases, yet automatic heartbeat classification remains challenging, especially for personalized, real‑time analysis of Holter data. The study implements a parallel general regression neural network to classify heartbeats, aiming to improve personalized, real‑time ECG analysis. An online learning program trains a personalized GRNN model for each patient. The personalized GRNN achieved 88 % accuracy on patient‑specific ECG data and its parallel implementation on a GTX780Ti accelerated processing by 450×.

Abstract

Long-term electrocardiogram (ECG) has become one of the important diagnostic assist methods in clinical cardiovascular domain. Long-term ECG is primarily used for the detection of various cardiovascular diseases that are caused by various cardiac arrhythmia such as myocardial infarction, cardiomyopathy, and myocarditis. In the past few years, the development of an automatic heartbeat classification method has been a challenge. With the accumulation of medical data, personalized heartbeat classification of a patient has become possible. For the long-term data accumulation method, such as the holter, it is difficult to obtain the analysis results in a short time using the original method of serial design. The pressure to develop a personalized automatic classification model is high. To solve these challenges, this paper implemented a parallel general regression neural network (GRNN) to classify the heartbeat, and achieved a 95% accuracy according to the Association for the Advancement of Medical Instrumentation. We designed an online learning program to form a personalized classification model for patients. The achieved accuracy of the model is 88% compared to the specific ECG data of the patients. The efficiency of the parallel GRNN with GTX780Ti can improve by 450 times.