Benchmarking hospital performance

RiskStandard: This R-package implements statistical methods for benchmarking hospital performance based on a binary quality indicator such as 30-day mortality. Logistic regression with direct or indirect standardization of risks is used to adjust for differences in patient case-mix.

ROC webtool: In this Excel-based webtool, the user can insert relevant hospital risks (e.g. the standardized risks from the previous year), select a benchmark (a clinically relevant deviation) and a statistical confidence level. The theoretical sensitivities and specificities that result from different scenarios are then calculated and summarized through ROC curves.

Reference:

Varewyck M, Goetghebeur E, Eriksson M, Vansteelandt S. On shrinkage and model extrapolation in the evaluation of clinical center performance. Biostatistics. 2014;15(4):651-64.