Hospital Mortality Rate Estimation for Public Reporting

Bayesian models are increasing fit to large administrative data sets and then used to make individualized recommendations. For instance, Medicare's Hospital Compare webpage provides information to patients about specific hospital mortality rates for a heart attack or Acute Myocardial Infarction (AMI). Hospital Compare's current recommendations are based on a random effects logit model with a random hospital indicator and patient risk factors. By checking the out of sample calibration of their individualized predictions against general empirical advice, we are led to substantial revisions of the Hospital Compare model for AMI mortality. As opposed to Hospital Compare, our revised models incorporate information about hospital volume, nursing staff, medical residents, and the hospital's ability to perform cardiovascular procedures, information that is clearly needed if a model is to make appropriately calibrated predictions. Additionally, we contrast several methods for summarizing a model's predictions for use by the public. We find that indirect standardization, as currently used by Hospital Compare, fails to adequately control for differences in patient risk factors, whereas direct standardization provides good control and is easy to interpret.

[1]  J. Silber,et al.  Does Admission to a Teaching Hospital Affect Acute Myocardial Infarction Survival? , 2013, Academic medicine : journal of the Association of American Medical Colleges.

[2]  James G. Scott,et al.  Bayesian Inference for Logistic Models Using Pólya–Gamma Latent Variables , 2012, 1205.0310.

[3]  P. Rosenbaum,et al.  The Hospital Compare mortality model and the volume-outcome relationship. , 2010, Health services research.

[4]  R. Kohn,et al.  Bayesian Estimation of a Random Effects Heteroscedastic Probit Model , 2008 .

[5]  B. Hansen The prognostic analogue of the propensity score , 2008 .

[6]  Elliott S Fisher,et al.  Analysis of observational studies in the presence of treatment selection bias: effects of invasive cardiac management on AMI survival using propensity score and instrumental variable methods. , 2007, JAMA.

[7]  J. Berger The case for objective Bayesian analysis , 2006 .

[8]  Jeroan J Allison,et al.  Nurse Staffing and Mortality for Medicare Patients with Acute Myocardial Infarction , 2004, Medical care.

[9]  Afschin Gandjour,et al.  Threshold Volumes Associated With Higher Survival in Health Care: A Systematic Review , 2003, Medical care.

[10]  S. Normand,et al.  The volume-outcome relationship: from Luft to Leapfrog. , 2003, The Annals of thoracic surgery.

[11]  Ethan A Halm,et al.  Is Volume Related to Outcome in Health Care? A Systematic Review and Methodologic Critique of the Literature , 2002, Annals of Internal Medicine.

[12]  R. Centor,et al.  Relationship of hospital teaching status with quality of care and mortality for Medicare patients with acute MI. , 2000, JAMA.

[13]  L. Wasserman,et al.  Computing Bayes Factors by Combining Simulation and Asymptotic Approximations , 1997 .

[14]  A. Gelfand,et al.  Bayesian Model Choice: Asymptotics and Exact Calculations , 1994 .

[15]  S. Chib,et al.  Bayesian analysis of binary and polychotomous response data , 1993 .

[16]  H. Luft,et al.  The volume-outcome relationship: practice-makes-perfect or selective-referral patterns? , 1987, Health services research.

[17]  George E. P. Box,et al.  Dispersion Effects From Fractional Designs , 1986 .

[18]  D. Rubin,et al.  Constructing a Control Group Using Multivariate Matched Sampling Methods That Incorporate the Propensity Score , 1985 .

[19]  A. Dawid The Well-Calibrated Bayesian , 1982 .

[20]  Gary King,et al.  Matching Methods for Causal Inference , 2011 .

[21]  D. Cox Tests of Separate Families of Hypotheses , 1961 .