Ventricular premature beat intelligent analysis method based on abnormal characteristic values

Abstract

The invention relates to a ventricular premature beat intelligent analysis method based on abnormal characteristic values. The method comprises the following steps: 1) signal preprocessing: denoisingan original signal by using a wavelet filter, positioning a QRS composite wave through digital analysis of slope, amplitude and width, and finally segmenting and extracting a single heart beat from acomplete ECG signal by taking an R peak as a center; 2) feature extraction: selecting a QRS composite wave area, an RR interval and a QRS amplitude vector sum as feature parameters for input of a classifier; 3) model training: repeatedly and randomly extracting k samples from the original training sample set in a place-back manner through a self-service method resampling technology to generate a new training sample set, then generating M classification trees according to the self-service sample set to form a random forest, and determining a classification result of new data according to a score formed by the voting amount of the classification trees. The method has the advantages that abnormal signals with abnormal electrocardiosignal centrality are identified accurately, and classification is accurate.

Description

technical field [0001] The invention belongs to the technical field of heartbeat detection and classification, and in particular relates to an intelligent analysis method for premature ventricular beats based on abnormal characteristic values. Background technique [0002] Electrocardiogram (ECG) is a graph that records changes in the electrical activity of the heart in each cardiac cycle from the body surface, and it contains a wealth of basic functional and pathological information of the heart. Therefore, it has great significance in the evaluation of heart safety and evaluation of various treatment methods, and is currently an important means for the examination and diagnosis of various heart diseases such as arrhythmia. . Premature systole is the most common clinical arrhythmia, which refers to the heartbeat caused by the premature impulse from the ectopic pacemaker. According to the site of origin, it can be divided into four types: sinus, atrial, atrioventricular ju...

AI Technical Summary

Problems solved by technology

Although highly accurate methods have been developed for detecting PVC cardiac beats, their efficiency is usually accompanied by long computation time and high complexity

Furthermore, the MIT-BIH arrhythmia database has far more normal heartbeat types than PVC heartbeat types, so they did not consider to solve some factors caused by data imbalance.

Images