Arrhythmia detection device

Abstract

The invention relates to an arrhythmia detection device, which comprises electrocardiogram acquisition equipment and a processor, and is characterized in that the processor processes an electrocardiogram signal acquired by the electrocardiogram acquisition equipment, and finally obtains the arrhythmia condition of a patient by performing preprocessing, feature extraction and neural network classification on the electrocardiogram signal. By means of the device, the arrhythmia condition of the patient can be automatically obtained, and detection is accurate and timely.

Description

technical field [0001] The invention relates to the technical field of medical equipment for monitoring physiological conditions, in particular to an arrhythmia detection device. Background technique [0002] Arrhythmia (arrhythmia) is due to abnormal sinoatrial node excitation or excitation outside the sinoatrial node, the conduction of the excitation is slow, blocked, or conducted through abnormal channels, that is, the origin of cardiac activity and / or conduction disorders lead to the frequency of cardiac beating And (or) abnormal rhythm. Arrhythmia is an important group of diseases in cardiovascular diseases. It can occur alone or with other cardiovascular diseases. Its prognosis is related to the etiology, inducement, evolution trend of arrhythmia, and whether it leads to severe hemodynamic disturbance. It can occur suddenly and cause sudden death, or it can continue to involve the heart and cause it to fail. Effective detection of arrhythmia can prevent heart diseas...

AI Technical Summary

Problems solved by technology

[0003] The main means of clinical diagnosis of arrhythmia is electrocardiogram detection, but most of the measurement of electrocardiogram requires the use of complex electrocardiogram equipment. Self-monitoring, diagnosis and management of activity and abnormal heart rhythms

[0004] Some institutions try to classify ECG signals through the current popular classification methods to judge the patient's heart rhythm status. It is known that some institutions use support vector machines for classification, but those skilled in the art are a binary classification method , the output results are only 0 and 1, but arrhythmia obviously includes nearly a dozen situations, and the classification results of only binary classification obviously cannot meet the detection requirements

At the same time, when extracting ECG features for analysis, usually only analyzing RR intervals, QRS composite bands, etc., the feature extraction of ECG signals is not targeted, and the characteristics of ECG signals cannot be obtained well

Images