Association of hospital and surgeon volume with mortality following major surgical procedures Meta-analysis of meta-analyses of observational studies

Accumulation of the literature has suggested an inverse association between healthcare provider volume and mortality for a wide variety of surgical procedures. This study aimed to perform meta-analysis of meta-analyses (umbrella review) of observational studies and to summarize existing evidence for associations of healthcare provider volume with mortality in major operations. We searched MEDLINE, SCOPUS, and Cochrane Library, and screening of references. Meta-analyses of observational studies examining the association of hospital and surgeon volume with mortality following major operations. The primary outcome is all-cause short-term morality after surgery. Meta-analyses of observational studies of hospital/surgeon volume and mortality were included. Overall level of evidence was classified as convincing (class I), highly suggestive (class II), suggestive (class III), weak (class IV), and non-significant (class V) based on the significance of the randomeffects summary odds ratio (OR), number of cases, small-study effects, excess significance bias, prediction intervals, and heterogeneity. Twenty meta-analyses including 4,520,720 patients were included, with 19 types of surgical procedures for hospital volume and 11 types of surgical procedures for surgeon volume. Nominally significant reductions were found in odds ratio in 82% to 84% of surgical procedures in both hospital and surgeon volume-mortality associations. To summarize the overall level of evidence, however, only one surgical procedure (pancreaticoduodenectomy) fulfilled the criteria of class I and II for both hospital and surgeon volume and mortality relationships, with a decrease in OR for hospital (0.42, 95% confidence interval[CI] [0.35-0.51]) and for surgeon (0.38, 95% CI [0.30-0.49]), respectively. In contrast, most of the procedures appeared to be weak or "nonsignificant." Only a very few surgical procedures such as pancreaticoduodenectomy appeared to have convincing evidence on the inverse surgeon volume-mortality associations, and yet most surgical procedures resulted in having weak or "non-significant" evidence. Therefore, healthcare professionals and policy makers might be required to steer their centralization policy more carefully unless more robust, higher-quality evidence emerges, particularly for procedures considered as having a weak or non-significant evidence level including total knee replacement, thyroidectomy, bariatric surgery, radical cystectomy, and rectal and colorectal cancer resections.