预防性应用生长抑素对降低胰十二指肠切除术后并发症的Meta分析

Meta-analysis of randomized controlled trials on the effectiveness of prophylactic using somatostatin for panereatieoduodenectomy

目的:以循证医学证据评价胰十二指肠切除术预防性使用生长抑素的临床疗效。方法:通过计算机检索Pubmed数据库、EMBASE、万方数据库、中国全文期刊数据库和维普数据库,并结合文献追溯、网上查询(www.baidu.com;www.google.com)的方法,收集关于预防性应用生长抑素在胰十二指肠切除术后临床疗效的随机对照试验,并按Cochrane协作网推荐的方法对符合纳入标准的11个研究共1041例病人进行Meta分析,发表偏倚用漏斗图评估。结果:与对照相比,预防性应用生长抑素能降低胰十二指肠切除术后总并发症的发生率(P=0.04),但二者在术后胰瘘发生率(P=0.13)、围手术期病死率(P=0.69)、住院天数(P=0.52)方面均无统计学差异。结论:Meta分析结果显示术后预防性应用生长抑素,能在一定程度上降低术后并发症的发生,但是不能有效预防胰瘘的发生、降低围手术期病死率和缩短住院天数。由于纳入的样本存在选择偏倚、发表偏倚及测量偏倚的可能性,影响结果的论证强度,最终结论需要进行更多高质量的随机对照试验。

Objective： To evaluate the clinical effect of prophylactic using somatostatin in panereatieoduodenectomy by evidence based medicine. Methods： clinical data of effect in panereatieoduodenectomy under went prophylactic using somatostatin or not were collected from computer literature searching, which was carried out in PubMed, EMBASE, Wanfang and VIP database etc, also performed searching based on www. baidu, com and www.google.com. Meta analysis that recommended by Cochrane Collaboration was done for the data obtained that 1041 patients who met with the eleven criteria of enrollment were included in this study. Publication bias was assessed by using a funnel plot. Results： The results of Meta-ananlysis show that the total complcation rate was lower in patients treated with prophylactic using somatostatin than in those treated with not using somatostatin （P=0.04）,however, compared with the control group,there was no significantly statistical difference in the incidence of pancreatic fistula（P=0.13）, perioperative mortality（P=0.69） and length of hospital stay （P=0.52）. Conclusion： The results show that prophylactic using somatostatin after panereatieoduodenectomy can reduce the incidence of postoperative complications in a certain de- gree. But it can not effectively prevent the occurrence of pancreatic fistula, perioperative mortality and reduce hospital stay. Further more,because these RCTs included may have selection bias, publication bias and measurement bias which can strength affect the outcome of the argument, so the further conclusion need more high-quality RCTs to deeply explore and demonstrate.