Heart rhythm classification system based on machine learning

Abstract

The invention discloses a heart rhythm classification system based on machine learning. The heart rhythm classification system comprises a data collection module, a data preprocessing module and a classification algorithm module; the data collection module collects an electrocardiosignal of a subject; and the data preprocessing module performs noise analysis and filtration, collects 45% of samplesin a left interval and correspondingly collects 55% of samples in a right interval to complete segmentation of a heart beat, and performs normalization processing at last. On the basis, the classification algorithm module for a convolutional neural network (CNN) model and an encoding-decoding model is established, and a classification model is established by using a good characteristic extractionability of the CNN and a time sequence characteristic extraction ability of long short-term memory (LSTM), so the problem that the RNN cannot process a far-distance reliance independently is overcome; and according to the heart rhythm classification system provided by the invention, the average sensitivity and the average accuracy are greatly improved, the complex characteristic extraction is avoided, the influence on a classification result due to manual extraction of a characteristic value is reduced, and the heart rhythm classification effect is improved.

Description

technical field [0001] The invention belongs to the technical field of medical equipment, and in particular, relates to a heart rhythm classification system based on machine learning. Background technique [0002] In recent years, with the continuous improvement of material level, people pay more and more attention to their own health. Among various diseases, heart disease is not only a relatively common type of disease, but also poses a greater threat to human life and health. [0003] As a common means of heart disease examination, electrocardiogram can well reflect the state of the heart at each moment, and is an important reference for doctors to diagnose heart disease. However, the identification of ECG still requires experienced medical personnel to accurately diagnose the pathology. Therefore, it is of great practical significance to use intelligent medical equipment to monitor the current patient's heart beating status in time and automatically classify the heart r...

AI Technical Summary

Problems solved by technology

It can be seen that the quality of extracted feature values ​​greatly affects the classification effect of subsequent classifiers. At the same time, manual extraction of feat

Images