Meta-analysis of non-randomized comparative studies of the short-term outcomes of laparoscopic resection for colorectal cancer

Abstract

Laparoscopic resection remains to be established as the procedure of first choice for operable colorectal cancer. The aim of the study was to conduct a systematic review of non-randomized comparative studies of laparoscopic resection for colorectal cancer. Published work in English was searched for relevant articles published by the end of 2003. The MOOSE statement was used to conduct the meta-analysis. Study quality was assessed by two investigators using the MINORS tool and the analysis was conducted using Comprehensive Meta-analysis software (Biostat, Englewood, NJ, USA) and Microsoft Excel (Microsoft, Redmond, WA, USA). One thousand two hundred and twenty abstracts were reviewed and 398 articles examined in detail. Out of 108 articles reporting the results of relevant studies, 75 were reports of 64 non-randomized comparative studies. Fifteen studies were excluded. Analysis of the outcomes of 6438 resections showed that the conversion rate was 13.3% with a statistically significant difference between studies with more than 50 versus those with 50 or less attempted resections (11.7 vs 16.5%; P<0.001). Laparoscopic resection took 27.6% (41 min) longer to carry out than open resection. There was no significant difference between the two groups in early mortality rates (1.2 vs 1.1%; P=0.787) or likelihood of re-operation (2.3 vs 1.5%; P=0.319). Laparoscopic resection was associated with a lower morbidity rate (24.05 vs 30.80%, odds ratio (95% confidence interval)=0.77 (0.63-0.95); P=0.014, n=4111, random-effects model). Time until passage of first flatus, passage of a bowel motion, tolerating oral fluids and a solid diet was 1.2-1.6 days (26 to 37%) shorter, measurements of pain and narcotic analgesic requirements were 16-35% lower and hospital stay was 3.5 days (18.8%) shorter following laparoscopic resection compared with open resection. The two approaches were 99% similar in terms of adequacy of oncological clearance. Meta-analysis of non-randomized comparative studies favours laparoscopic over open resection for colorectal cancer. The results were remarkably similar to those of a contemporaneous meta-analysis of randomized controlled trials published by the end of 2002.