Relationship Between Hospital Volume, System Clinical Resources, and Mortality in Pancreatic Resection

BACKGROUND: The relationship between hospital volume and perioperative mortality in pancreaticoduodenectomy has been well established. We studied whether associations exist between hospital volume and hospital clinical resources and between both of these factors to mortality to help explain this relationship. STUDY DESIGN: This two-part study reviewed publicly available hospital information from the Leapfrog Group, HealthGrades, and hospital Web sites. Hospitals were evaluated for Leapfrog ICU staffing criteria and Safe Practice Score; HealthGrades five-star rating for complex gastrointestinal procedures and operations; and presence of a general surgery residency, gastroenterology fellowship, and interventional radiology. Evaluation used trend analysis and multiple logistic regression analysis. The second part determined the mortality rate for pancreaticoduodenectomy using inpatient mortality data from the National Inpatient Sample and Leapfrog. Hospitals were categorized by low volume (<= 10/year), high volume (>= 11/year), strong clinical support (presence of all support factors), and weak clinical support (absence of any factor). Data were correlated by number of pancreatic resections per hospital, hospital system clinical resources, and operative mortality. RESULTS: As hospital volume increased, statistically significant increases occurred in the frequency of hospitals meeting Leapfrog ICU staffing criteria (p < 0.0001), Leapfrog Safe Practice Score (p = 0.0004), HealthGrades 5-star rating (p < 0.00001), general surgery residency (p < 0.00001), gastroenterology fellowship (p < 0.00001), and interventional radiology services (p < 0.00001). No significant relationships were found between resection volume and any one of the clinical support factors and perioperative death. Presence of strong clinical support was associated with lower mortality (odds ratio = 0.32; p = 0.001). CONCLUSIONS: System clinical resources were more influential in operative mortality for pancreatic resection. This might help explain why high-volume hospitals, low-volume surgeons in high-volume institutions, and some lower-volume hospitals with excellent clinical resources have lower perioperative mortality rates for pancreatic resection. (J Am Coll Surg 2009;208:520-527. c 2009 by the American College of Surgeons)