Method for analyzing ECG signals

Abstract

The invention provides a method for analyzing an ECG signal. The method comprises the following steps: measuring the ECG signal by a sensor; detecting one or more specified waveforms in the ECG signal; obtaining a plurality of ECG features from each specified waveform; inputting the ECG features into a plurality of candidate models to obtain a plurality of candidate scores; comparing each candidate score to a standard value to obtain an ideal score among the candidate scores; and selecting one candidate model corresponding to the ideal score as a risk prediction model, and predicting the disease risk through a risk prediction model.

Description

technical field [0001] The invention relates to a disease prediction method, in particular to a method for analyzing electrocardiogram signals. Background technique [0002] In modern life, the prevention of heart disease is becoming more and more important. If it can be detected and treated early, there will be better results. Therefore, predicting the risk of heart disease becomes an important issue. In the past literature, the prediction of heart disease risk mostly used risk factors to build models, for example, using age, total cholesterol, high-density cholesterol, blood pressure, smoking, diabetes, etc. to establish a Cox proportional hazard model to predict the risk of heart disease. Of course, some invasive ways to obtain risk factors of internal conditions will cause some people to resist, and then reject to the hospital for examination. [0003] In the past, doctors usually used changes in electrocardiography (ECG) to assist in identifying types of heart disease...

AI Technical Summary

Problems solved by technology

The source of electrocardiogram data collection is also from the hospital's equipment, but the electrocardiogram checked in the hospital can only judge the current situation, and cannot be measured in real time when people are slightly ill.

Images