Survival and disease-progression benefits with treatment regimens for advanced colorectal cancer: a meta-analysis

Background Many randomised trials have compared different systemic treatment regimens inpatients with advanced colorectal cancer. While survival advances have apparently been achieved, the magnitude of these incremental benefits across diverse regimens is less clear. The aim of our study was to estimate the magnitude of survival and disease progression benefits with the use of different regimens in patients with advanced colorectal cancer. Methods We systematically reviewed randomised trials comparing systemic treatment regimens in advanced colorectal cancer. Treatment was categorised by use of or no use of fluorouracil-based regimens, irinotecan, oxaliplatin, bevacizurnab, and cetuximab. We used multiple-treatment meta-analysis methodology to combine information from direct comparisons (ie, treatments compared within a randomised trial) and. indirect comparisons (ie, treatments compared between trials by combining results on how effective they are against a common comparator treatment) of different chemotherapy regimens. The primary endpoint was death and the secondary endpoint was disease progression. Monte Carlo simulations were used to establish which regimen offered the most benefit for these endpoints. We did analyses of all trials and analysed separately trials that studied first-line treatments and non-first-line treatments. Findings 242 trials published in 1967-2007 (N=56677 patients) involved 137 different chemotherapy regimens. 37 of these trials were eligible for the multiple-treatment meta-analysis, according to our categorisation, including 47 comparisons of data on death (N=13875 patients) and 48 comparisons of data on disease progression (N=15158 patients). Compared with fluorouracil plus leucovorin alone, the risk of death was most decreased with the addition of irinotecan plus bevacizumab (hazard ratio [HR] 0.60, 95% credibility intervals (CrI) 0.44-0.84) and considerable benefits were also noted with addition of irinotecan plus oxaliplatin (HR 0.72 [95% CrI 0.54-0.97]); oxaliplatin plus bevacizumab (HR 0.72 [0.57-0.90]); bevacizumab alone (HR 0.78 [0.60-1.03]); and oxaliplatin alone (HR 0.87 [0.78-0.98]). The disease progression benefits were even more prominent for the addition of irinotecan plus bevacizumab (HR 0.41 [0.28-0.60]); irinotecan plus oxaliplatin (0.53 [0.38-0.73]); oxaliplatin plus bevacizumab (0.46 [0.34-0.61]); bevacizurnab alone (0.56 [0.41-0.76]); oxaliplatin alone (0.64 [0.56-0.73]); irinotecan plus cetuximab (HR 0.62 [0.42-0.92]); and irinotecan alone (HR 0.73 [0.65-0.82]). Findings were similar for first-line and non-first-line treatment analyses although data were sparse for non-first-line treatment analyses. Compared with a patient with an anticipated 1-year survival who is treated with fluorouracil and leucovorin, the absolute survival benefit is estimated at 8 months' prolongation with addition of irinotecan plus bevacizumab, 4.7 months' prolongation with addition of oxaliplatin plus bevacizumab or irinotecan plus oxaliplatin, and 1-1.8 months' prolongation with addition of irinotecan alone or oxaliplatin alone. Interpretation Distinct incremental benefits are noted for diverse chemotherapy regimens in patients with advanced colorectal cancer, with more prominent effects on disease progression than on death. More data are needed at least for the newest drugs to estimate more accurately the magnitude of the benefit derived from their use.