人工智能诊断冠心病效能的Meta分析

Diagnostic efficacy of artificial intelligence for coronary artery disease:a Meta-analysis Yu Yanqiao

目的评价人工智能(artificial intelligence,AI)诊断冠状动脉粥样硬化性心脏病(冠心病)的价值。方法计算机检索PubMed、EMbase、The Cochrane Library、万方、中国知网、维普,检索人工智能诊断冠心病的诊断性试验,检索时限均从建库至2021年6月30日。由两名研究者独立筛选文献、提取信息,并评价纳入文献的质量。采用Meta-Disc 1.4和Revman 5.4软件进行Meta分析,以患者为单位,计算AI诊断冠心病的合并灵敏度、特异度、阳性似然比、阴性似然比、诊断比值比和受试者工作特征曲线下面积。结果共纳入11项研究,2898例患者。Meta分析结果显示,AI诊断冠心病合并灵敏度、特异度、阳性似然比、阴性似然比、诊断比值比分别为0.82(95%CI:0.81,0.84)、0.64(95%CI:0.61,0.67)、4.01(95%CI:2.23,7.21)、0.18(95%CI:0.13,0.27)和22.52(95%CI:10.28,49.31),受试者工作特征曲线下面积为0.90。结论人工智能对冠心病具有较高诊断价值,可作为一种有效的诊断方法。日后应选择合适的AI算法模型,并进行较大样本量的测试与训练。

Objective To evaluate the diagnostic value of artificial intelligence(AI)in diagnosis of coronary heart disease.Methods The databases of PubMed,EMbase,The Cochrane Library,Wanfang,CNKI,and VIP,were retrieved to search diagnostic trials related to artificial intelligence in coronary heart disease.The retrieval time was from the establishment of the database to June 30,2021.Two researchers independently screened the literature,extracted information,and evaluated the quality of the included literature.Meta-Disc 1.4 and Revman 5.4 software were used for Meta-analysis.The pooled sensitivity,specificity,positive likelihood ratio,negative likelihood ratio,diagnostic odds ratio and the area under the receiver operating characteristic curve are calculated.Results A total of 11 studies with 2898 patients were included.The results showed that the pooled sensitivity,specificity,positive likelihood ratio,negative likelihood ratio,diagnostic odds ratio of AI-assisted diagnosis of coronary heart disease was 0.82(95%CI:0.81,0.84),0.64(95%CI:0.61,0.67),4.01(95%CI:2.23,7.21),0.18(95%CI:0.13,0.27),22.52(95%CI:10.28,49.31).The area under the receiver operating characteristic curve is 0.90.Conclusion AI exerts a good diagnostic value for coronary artery disease and can be used as an effective auxiliary diagnostic method.