荧光原位杂交和细胞学在诊断上尿路尿路上皮癌的效率对比系统评价和荟萃分析

Comprehensive comparison between fluorescence in situ hybridization and cytology for the detection of upper urinary tract urothelial carcinoma:systematic review and meta-analysis

目的:深入比较荧光原位杂交(FISH)及细胞学对上尿路尿路上皮癌(UTUC)的诊断效率并讨论FISH的优势及缺陷。方法:本文以从中国知网、万方数据库、PubMed/Medline、Embase、Web of Science、Ovid、Web of Knowledge及Cochrane Library检索的14篇相关文献为基础进行系统评价和荟萃分析。纳入文献利用NOS、QUadas-2及STARD 2015等评价工具严格进行质量评价。经过纳入排除标准严格筛选,就诊于2005年1月～2017年11月的2 031例患者被纳入研究。测试结果利用二元随机效应模型。结果:合并诊断敏感性方面,FISH显著高于细胞学检查[84.0%(95%CI:74.4%～90.5%)vs.40.0%(95%CI:33.6%～46.7%),P<0.05],合并诊断特异性二者相近[89.5%(95%CI:85.3%～92.6%)vs.95.9%(95%CI:91.2%～98.1%),P>0.05]。结论:经过荟萃分析,本文发现在敏感性方面FISH明显优于细胞学,而在特异性方面二者相似。FISH在诊断UTUC的过程中极为敏感并且错误率也较低。

Objective:To compare the relative diagnostic effectiveness between fluorescence in situ hybridization(FISH)and cytology and to evaluate the advantages and potential deficiencies of FISH analysis.Method:We performed a complete systematic review based on studies from CNKI,WANFANG DATA,PubMed/Medline,EMBASE,Web of Science,Ovid,Web of Knowledge and Cochrane Library.We identified 2031 patients with strict criteria in 14 individual studies between January 2005 to November 2017 and conducted a standard meta-analysis using 29 crucial parameters.The identified reports were critically appraised according to the Newcastle-Ottawa Scale(NOS),Quality Assessment of Diagnostic Accuracy Studies(QUadas-2)and Standards for Reporting of Diagnostic Accuracy(STARD 2015).We summarized the test performance using bivariate random effects models.Result:FISH was superior to cytology in terms of pooled sensitivities [84.0%(95%CI:74.4%-90.5%)vs.40.0%(95%CI:33.6%-46.7%),P<0.05],while similar specificity was found [89.5%(95%CI:85.3%-92.6%)vs.95.9%(95%CI:91.2%-98.1%),P>0.05].Conclusion:We confirmed the superiority of FISH over cytology in terms of sensitivity and found similar diagnostic outcomes between them based on systematic analysis.Therefore,we demonstrated that FISH is extremely sensitive while still very reliable with a relatively low error rate.