基于机器学习的新冠肺炎与流感快速鉴别方法的研究

Research on the Rapid Identification Method of COVID-19 and Influenza Based on Machine Learning

新冠肺炎作为一种新发性传染疾病,与流感均含有发热、咳嗽等临床特征,快速准确地将新冠肺炎与流感进行鉴别,有助于对患者进行救治。采用独立样本t检验的方法对患者检验数据中多个指标进行差异性分析,选择差异性较大的指标,评估机器学习中线性与非线性算法、集成算法等多种算法在流感与新冠肺炎快速鉴别中的应用效果。结果显示,SVM算法在新冠肺炎与流感的鉴别问题上效果更好。

As a new infectious disease,COVID-19 and influenza contain clinical features such as fever and cough.Quickly and accurately distinguish the COVID-19 from influenza,which is helpful for the treatment of patients.In this paper,the independent sample t test method is used to analyze the differences of multiple indicators in the patient test data,select the indicators with greater differences,the application effect in rapid identification of COVID-19 and influenza by linear and nonlinear algorithms and integrated algorithms in machine learning are evaluated.The results show that the SVM algorithm is better at distinguishing COVID-19 from influenza.