一种用于心拍分类的可解释机器学习方法

An interpretable machine learning method for heart beat classification

目的探讨Tsetlin Machine(TM)在心拍分类中的应用。方法运用TM对中国生理信号挑战赛2020数据集中正常、室性早搏和室上性早搏心拍图片进行三分类,并对分类结果进行解释性分析。该数据集包括10例心律失常患者的单导联心电图数据,排除1例心房颤动患者,最终纳入9例患者数据。结果分类结果表明,TM的九折平均识别准确率达84.3%,并且能通过位模式解释图展示分类判别的依据。结论TM在分类心拍的同时能对分类结果作出解释,对分类结果的合理解释便于人们理解模型在进行心拍图分类时的判决依据,进而增加模型的可信度。

Objective To explore the application of Tsetlin Machine(TM)in heart beat classification.Methods TM was used to classify the normal beats,premature ventricular contraction(PVC)and supraventricular premature beats(SPB)in the 2020 data set of China Physiological Signal Challenge.This data set consisted of the single-lead electrocardiogram data of 10 patients with arrhythmia.One patient with atrial fibrillation was excluded,and finally data of the other 9 patients were included in this study.The classification results were then analyzed.Results The classification results showed that the average recognition accuracy of TM was 84.3%,and the basis of classification could be shown by the bit pattern interpretation diagram.Conclusion TM can explain the classification results when classifying heart beats.The reasonable interpretation of classification results can increase the reliability of the model and facilitate people’s review and understanding.