ECG lead intelligent selection method and system

Abstract

The invention relates to an ECG lead intelligent selection method and system. The system comprises a step of carrying out characteristic extraction on the ECG lead signals obtained at the same time period, and obtaining the global characteristic amount of each ECG signal, a step of classifying the corresponding ECG lead signals according to the maximum value of the integral waves of the ECG signals and a pooled local characteristic amount, and obtaining the signal quality level of each ECG lead signal, a step of extracting the maximum value of the integral waves of the ECG signals of different signal quality levels and the pooled local characteristic amount to carry out training to obtain a quality classifier, and a step of screening each ECG lead signal according to the quality classifier, and obtaining and outputting an optimal ECG lead signal. According to the embodiment of the present invention, the mutation of the signal at a local time can be reflected well, the accuracy is high, the human intervention is not needed in the whole process, time and human resources are saved, the judgment of signal quality and selection of lead can be completed before QRS detection, and the computation amount is saved.

Description

technical field [0001] The invention relates to the technical field of medical monitoring, in particular to a method and system for intelligently selecting ECG leads. Background technique [0002] The monitoring and analysis of ECG signals is an important function of monitors, electrocardiographs and other instruments. The acquisition of ECG signals is usually performed simultaneously on multiple leads. For the collected multi-lead signals, the instrument usually only selects the signal of one lead for subsequent analysis, such as QRS (magnetic resonance angiography, magnetic resonance angiography) detection. If the electrodes of the leads used for analysis are not in good contact with the human body, the collected ECG signals will be severely disturbed. [0003] The traditional ECG lead intelligent selection method is to calculate several characteristic quantities on a length of signal, and then compare with the preset empirical parameters to judge the quality of the signa...

AI Technical Summary

Problems solved by technology

The feature quantity obtained from a length of signal is difficult to reflect the short-term mutation of the signal, the workload of manually setting parameters is large, and the generalization ability is not strong. In addition, QRS detection is required to complete the judgment and guidance of signal quality. link selection

The traditional ECG lead intelligent selection method has the disadvantage of low accuracy

Images