ABSTRACT
BACKGROUND AND OBJECTIVE: Atrial fibrillation (AF) is one of the common cardiovascular diseases, and electrocardiography (ECG) is a key indicator for the detection and diagnosis of AF and other heart diseases. In this study, an improved machine learning method is proposed for rapid modeling and accurate diagnosis of AF. METHODS: This paper presents a novel IRBF-RVM model that combines the integrated radial basis function (IRBF) and relevance vector machine (RVM), which is utilized for the diagnosis of AF. The synchronous 12-lead ECG signals are collected from the human body surface so as to fully reflect the electrical activity of the whole heart. RR intervals of the QRS-waves in ECG signals are obtained by means of the classical Pan-Tompkins algorithm. The RR-features extracted from RR intervals are adopted as the diagnostic features for AF patients. In addition, the conventional RBF-RVM model, support vector machine (SVM) and other machine learning methods are also investigated for the diagnosis of AF so as to reflect the advantage of the proposed IRBF-RVM model. The open MIT-BIH arrhythmia database (MITDB) is also used to evaluate the predictive performance of these state-of-the-art methods. RESULTS: Altogether 1056 AF patients and 904 healthy people are participated in this study and validate the effectiveness of each channel of the 12-lead ECG signals. Experimental results show that the classification rate of IRBF-RVM can reach up to 98.16% by recurring to Channel II of the 12-lead ECG signals. CONCLUSIONS: IRBF-RVM absorbs the advantages of IRBF, which makes the kernel parameter of IRBF-RVM have a much larger selectable region than RBF-RVM. In addition, RVM has faster modeling and recognition speed in comparison with SVM. This work lays the foundation for the application of RVM to accurate diagnosis of AF.
