心律失常辅助诊断系统的研制

Research of Assistant Diagnosis System for Arrhythmias

目的:研制心律失常辅助诊断系统,以减少医生的工作量,并提高其对心电信号诊断的准确性。方法:首先利用小波变换理论建立滤波和波形识别算法,提取出有效的特征参数;然后利用粗糙集理论约简特征参数并根据相应的分类决策规则,利用分支逻辑法对波形进行识别分类;最后利用模糊神经网络理论得出异常心拍的隶属度。结果:实现了滤波、波形识别、诊断分类等主要模块,形成了一个完整的系统。结论:该系统能识别十九种心律失常并得出异常心拍的隶属度和位置信息,对医生的诊断有良好的辅助作用。

Objective： Develop an assistant diagnosis system for arrhythmias which can reduce doctors＇ workload and improve their veracity of diagnosing ECG. Methods： Firstly, this paper achieves filter and detection of waves using wavelet transform and extracts parameters; Secondly, it reduces parameters using rough set and identifies arrhythmias according to relevant roles; At last, it gets the membership of abnormal heart beat by fuzzy neural network. Results： The main modules such as filter, detection of waves and identification of arrhythmias are achieved well, and a complete system is formed. Conclusions： This system can identify nineteen arrhythmias and get their membership and position. It could assist doctors in making the proper diagnosis on ECG potentially.