A method for identifying premature beats in ambulatory electrocardiogram

Abstract

A method for identifying premature beats in a dynamic electrocardiogram, comprising the following steps: 1) extracting a ten-dimensional feature inputFeature according to the detected beat position; 2) extracting sinus and supraventricular from the ECG signal database with existing beat types The inputFeature‑0 of premature beats and premature ventricular beats is merged into training data; 3) Extract the corresponding inputFeature from all the beats in the dynamic ECG to be analyzed, and merge them into test data testData; 4) Use supervised learning algorithm to pre-classify testData , the output is the corresponding heart beat type, and the position information of the sinus heart beat is extracted; 5) Select a certain number of pre-classified sinus heart beats, take the average value, and obtain a sinus QRS complex wave template; 6) Use the similarity measure , ECG morphology and RR interval expert system to judge supraventricular premature beats and ventricular premature beats. The invention is applicable to the identification of ventricular premature beats and supraventricular premature beats in the long-term electrocardiographic data of dynamic electrocardiograms, and effectively assists doctors to quickly perform related diagnoses.

Description

technical field [0001] The invention relates to the technical field of automatic auxiliary detection of a dynamic electrocardiogram, in particular to a method for identifying supraventricular premature beats and ventricular premature beats in a dynamic electrocardiogram. Background technique [0002] The ambulatory electrocardiogram is a long-term continuous recording of the body surface electrocardiogram, which contains more abundant physiological information of the human body than the conventional electrocardiogram, and can more objectively reflect and monitor the patient's physical condition. But at the same time, due to its long-term nature, the dynamic electrocardiogram contains a large number of heart beats and complicated types, which greatly increases the workload of doctors, which makes the automatic auxiliary detection technology of dynamic electrocardiogram increasingly important. [0003] Premature contractions, also known as premature contractions, include atria...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the deficiencies of the poor accuracy of existing premature beat measurement methods, the purpose of the present invention is to provide a method for identifying supraventricular premature beats and ventricular premature beats in dynamic electrocardiograms. First, pre-classify dynamic cardiogram data based on supervised learning methods The normal sinus beat, supraventricular premature beat and ventricular premature beat are extracted, and then the extracted QRS complex wave of the normal sinus beat is used as a heart beat template, and finally the logic-based expert system is used to identify supraventricular premature beat and premature ventricular beat

Images