Atrial fibrillation classification method, device and system based on RR interval spatial features

Abstract

The invention discloses an atrial fibrillation classification method, device and system based on RR interval spatial features, and the method comprises the steps: obtaining an RR interval sequence with a fixed time length, and carrying out the preprocessing of the RR interval sequence; performing sliding window cutting on the preprocessed RR interval sequence to obtain a multi-dimensional data matrix corresponding to the RR interval sequence, and performing Fourier transform on the multi-dimensional data matrix to obtain multi-dimensional space phase data of the multi-dimensional data matrix; dimension reduction is carried out on the multi-dimensional space phase data based on a principal component analysis method, feature extraction is carried out on the data after dimension reduction, and a feature matrix is obtained; inputting the feature matrix into an atrial fibrillation classification model to obtain an atrial fibrillation prediction probability; comparing the prediction probability with a preset atrial fibrillation division threshold, and determining an atrial fibrillation prediction result; according to the method, the difference between the atrial fibrillation rhythm and other types of rhythms in RR interval spatial features is effectively obtained, and atrial fibrillation recognition is effectively achieved.

Description

technical field [0001] The present invention relates to the technical field of atrial fibrillation classification, in particular to a method, device and system for classifying atrial fibrillation based on spatial features of RR intervals. Background technique [0002] Atrial fibrillation refers to atrial fibrillation, in which the heart fibrillates in a fast and disordered rhythm, but the atria do not contract significantly, causing blood to store and form clots in the atria. Although atrial fibrillation does not usually directly cause death, the vast majority of strokes are attributed to blood clots that form during AF; it also multiplies the risk of complications such as heart failure. [0003] In China, there are currently more than 10 million patients with atrial fibrillation, and the prevalence will increase with age, with a prevalence of up to 3% in people over 65 years old. With the increasing aging of my country's population, the number of people with atrial fibrill...

AI Technical Summary

Problems solved by technology

On the one hand, this kind of quantization method is limited by the mathematical feature extraction method, and on the other hand, it ignores the relationship between the density and relative position of the points in the spatial distribution, resulting in insufficient representativeness of the quantization results.

Images