Hospital volume and mortality after pancreatic resection: a systematic review and an evaluation of intervention in the Netherlands

Abstract

Objectives: To evaluate the best available evidence on volume-outcome effect of pancreatic surgery by a systematic review of the existing data and to determine the impact of the ongoing plea for centralization in The Netherlands.

Summary background data: Centralization of pancreatic resection (PR) is still under debate. The reported impact of hospital volume on the mortality rate after PR varies. Since 1994, there has been a continuous plea for centralization of PR in The Netherlands, based on repetitive analysis of the volume-outcome effect.

Methods: A systematic search for studies comparing hospital mortality rates after PR between high- and low-volume hospitals was used. Studies were reviewed independently for design features, inclusion and exclusion criteria, cutoff values for high and low volume, and outcome. Primary outcome measure was hospital or 30-day mortality. Data were obtained from the Dutch nationwide registry on the outcome of PR from 1994 to 2004. Hospitals were divided into 4 volume categories based on the number of PRs performed per year. Interventions and their effect on mortality rates and centralization were analyzed.

Results: Twelve observational studies with a total of 19,688 patients were included. The studies were too heterogeneous to allow a meta-analysis; therefore, a qualitative analysis was performed. The relative risk of dying in a high-volume hospital compared with a low-volume hospital was between 0.07 and 0.76, and was inversely proportional to the volume cutoff values arbitrarily defined. In 5 evaluations within a decade, hospital mortality rates were between 13.8% and 16.5% in hospitals with less than 5 PRs per year, whereas hospital mortality rates were between 0% and 3.5% in hospitals with more than 24 PRs per year. Despite the repetitive plea for centralization, no effect was seen. During 2001, 2002, and 2003, 454 of 792 (57.3%) patients underwent surgery in hospitals with a volume of less than 10 PRs per year, compared with 280 of 428 (65.4%) patients between 1994 and 1996.

Conclusions: The data on hospital volume and mortality after PR are too heterogeneous to perform a meta-analysis, but a systematic review shows convincing evidence of an inverse relation between hospital volume and mortality and enforces the plea for centralization. The 10-year lasting plea for centralization among the surgical community did not result in a reduction of the mortality rate after PR or change in the referral pattern in The Netherlands.

FIGURE 1. Forest plot. Individual relative risk (RR) for hospital or 30-day mortality after pancreatic resection in high-volume hospitals versus low-volume hospitals. Categories I to IV represent the cutoff values for the volumes 2, 5, 10, and 20 procedures per year. N, total number of operated patients; n, number of deaths; RR, relative risk

FIGURE 2. Hospital mortality in the 4 volume categories at the different time intervals (1994–1995, 1996–1998, 1999–2000, 2001–2003).

FIGURE 3. Referral pattern to hospitals performing less than 10 PDs per year over a 10-year period (1994–2004). The arrows indicate the interventions by means of national or international presentations and publications.