Abstract:
|
Bayesian models are increasingly fit to large administrative data sets and then used to make individualized recommendations. In particular, Medicare's Hospital Compare webpage provides information to patients about specific hospital mortality rates for Acute Myocardial Infarction (AMI), based on a random-effects logit model with a random hospital indicator and patient risk factors. Here we calibrate such recommendation systems by checking, out of sample, whether their predictions aggregate to give correct general advice derived from another sample. This process of calibrating individualized predictions leads to substantial revisions in the Hospital Compare model for AMI mortality. Our revised models incorporate information about hospital volume, nursing staff, medical residents, and the hospital's ability to perform cardiovascular procedures. For the ultimate purpose of comparisons, hospital mortality rates must be standardized to adjust for patient mix variation across hospitals. To provide good control and correctly calibrated rates, we propose direct standardization instead of the indirect standardization used by Hospital Compare.
|