Association between degree of exposure to the Hospital Value Based Purchasing Program and 30-day mortality: experience from the first four years of Medicare's pay-for-performance program

Background The Hospital Value Based Purchasing Program (HVBP) in the United States, announced in 2010 and implemented since 2013 by the Centers for Medicare and Medicaid Services (CMS), introduced payment penalties and bonuses based on hospital performance on patient 30-day mortality and other indicators. Evidence on the impact of this program is limited and reliant on the choice of program-exempt hospitals as controls. As program-exempt hospitals may have systematic differences with program-participating hospitals, in this study we used an alternative approach wherein program-participating hospitals are stratified by their financial exposure to penalty, and examined changes in hospital performance on 30-day mortality between hospitals with high vs. low financial exposure to penalty. Methods Our study examined all hospitals reimbursed through the Medicare Inpatient Prospective Payment System (IPPS) - which include most community and tertiary acute care hospitals - from 2009 to 2016. A hospital's financial exposure to HVBP penalties was measured by the share of its annual aggregate inpatient days provided to Medicare patients ("Medicare bed share"). The main outcome measures were annual hospital-level 30-day risk-adjusted mortality rates for acute myocardial infarction (AMI), heart failure (HF) and pneumonia patients. Using difference-in-differences models we estimated the change in the outcomes in high vs. low Medicare bed share hospitals following HVBP. Results In the study cohort of 1902 US hospitals, average Medicare bed share was 61 and 41% in high (n = 540) and low (n = 1362) Medicare bed share hospitals, respectively. High Medicare bed share hospitals were more likely to have smaller bed size and less likely to be teaching hospitals, but ownership type was similar among both Medicare bed share groups.. Among low Medicare bed share (control) hospitals, baseline (pre-HVBP) 30-day mortality was 16.0% (AMI), 10.9% (HF) and 11.4% (pneumonia). In both high and low Medicare bed share hospitals 30-day mortality experienced a secular decrease for AMI, increase for HF and pneumonia; differences in the pre-post change between the two hospital groups were small (< 0.12%) and not significant across all three conditions. Conclusions HVBP was not associated with a meaningful change in 30-day mortality across hospitals with differential exposure to the program penalty.