无辅助临床医生与深度学习辅助临床医生在基于图像的癌症诊断中的对比研究卡塔尔世界杯8强波胆分析系统评价与荟萃分析%A薛%A，斯鹏%A，秦明宇%A，魏东旭%A，魏炳旭%A Seery,Samuel %A Ye，陈子辰%A，王明阳%A，宋苏萌%A，张诚%A，丁博%A，张明%A，白文玲%A，闫安英%A，邓会娇%A，赵乐%A，赵玉倩%A Rezhake,Remila %A，乔绍凯%A，曲友林%A，蒋一民%A，余%+人口医学与公共卫生学院流行病学与生物统计学系中国医学科学院、北京协和医学院，北京东城东单三条9号，100730,86 10 8778 8489,jiangyu@pumc.edu.cn %K深度学习%K癌症诊断%K系统评价%K meta分析%D 2023 %7 2.3.2023 %9综述%J J Med Internet Res %G English %X许多出版物已经证明，深度学习(DL)算法在基于图像的癌症诊断中与临床医生相匹配或优于临床医生，但这些算法通常被认为是对手而不是合作伙伴。尽管临床医生在循环DL方法具有巨大的潜力，但没有研究系统地量化临床医生在基于图像的癌症识别中使用或不使用DL的诊断准确性。目的:我们系统地量化临床医生在基于图像的癌症识别中有和没有DL帮助的诊断准确性。方法:检索PubMed、Embase、IEEEXplore和Cochrane Library，检索2012年1月1日至2021年12月7日之间发表的研究。任何类型的研究设计都是允许的，重点是比较无辅助临床医生和dl辅助临床医生在使用医学成像识别癌症方面的差异。使用医学波形数据图形材料的研究和研究图像分割而不是分类的研究被排除在外。提供二元诊断准确性数据和列联表的研究被纳入进一步的meta分析。 Two subgroups were defined and analyzed, including cancer type and imaging modality. Results: In total, 9796 studies were identified, of which 48 were deemed eligible for systematic review. Twenty-five of these studies made comparisons between unassisted clinicians and DL-assisted clinicians and provided sufficient data for statistical synthesis. We found a pooled sensitivity of 83% (95% CI 80%-86%) for unassisted clinicians and 88% (95% CI 86%-90%) for DL-assisted clinicians. Pooled specificity was 86% (95% CI 83%-88%) for unassisted clinicians and 88% (95% CI 85%-90%) for DL-assisted clinicians. The pooled sensitivity and specificity values for DL-assisted clinicians were higher than for unassisted clinicians, at ratios of 1.07 (95% CI 1.05-1.09) and 1.03 (95% CI 1.02-1.05), respectively. Similar diagnostic performance by DL-assisted clinicians was also observed across the predefined subgroups. Conclusions: The diagnostic performance of DL-assisted clinicians appears better than unassisted clinicians in image-based cancer identification. However, caution should be exercised, because the evidence provided in the reviewed studies does not cover all the minutiae involved in real-world clinical practice. Combining qualitative insights from clinical practice with data-science approaches may improve DL-assisted practice, although further research is required. Trial Registration: PROSPERO CRD42021281372; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=281372 %M 36862499 %R 10.2196/43832 %U //www.mybigtv.com/2023/1/e43832 %U https://doi.org/10.2196/43832 %U http://www.ncbi.nlm.nih.gov/pubmed/36862499