Adjusting for social risk factors impacts performance and penalties in the hospital readmissions reduction program

Abstract

Objective: Medicare's Hospital Readmissions Reduction Program (HRRP) does not account for social risk factors in risk adjustment, and this may lead the program to unfairly penalize safety-net hospitals. Our objective was to determine the impact of adjusting for social risk factors on HRRP penalties.

Study design: Retrospective cohort study.

Data sources/study setting: Claims data for 2 952 605 fee-for-service Medicare beneficiaries with acute myocardial infarction (AMI), congestive heart failure (CHF) or pneumonia from December 2012 to November 2015.

Principal findings: Poverty, disability, housing instability, residence in a disadvantaged neighborhood, and hospital population from a disadvantaged neighborhood were associated with higher readmission rates. Under current program specifications, safety-net hospitals had higher readmission ratios (AMI, 1.020 vs 0.986 for the most affluent hospitals; pneumonia, 1.031 vs 0.984; and CHF, 1.037 vs 0.977). Adding social factors to risk adjustment cut these differences in half. Over half the safety-net hospitals saw their penalty decline; 4-7.5 percent went from having a penalty to having no penalty. These changes translated into a $17 million reduction in penalties to safety-net hospitals.

Conclusions: Accounting for social risk can have a major financial impact on safety-net hospitals. Adjustment for these factors could reduce negative unintended consequences of the HRRP.

Keywords: Medicare; readmission.

Figure 1

A, Proportion of hospitals with changes in penalties after social risk adjustment. B, Change in Dollar amount of penalties (in millions of dollars) [Color figure can be viewed at wileyonlinelibrary.com] Source: (A) Authors’ calculations using CMS 100% Inpatient and Outpatient Research Identifiable File Claims Data for Medicare Fee‐For‐Service beneficiaries aged 65 and older with an index admission for AMI, pneumonia or CHF between December 1, 2012 and November 30, 2015. (B) Penalty estimates provided by DataGen using CMS base operating DRG payment data applied to the authors’ calculations using CMS 100% Inpatient and Outpatient Research Identifiable File Claims Medicare Fee‐For‐Service beneficiaries aged 65 and older with an index admission for AMI, pneumonia or CHF between December 1, 2012 and November 30, 2015. Notes: (A) Results include hospitals eligible for penalties under the HRRP (IPPS acute care hospitals with 25 or more index admissions for each condition during the 36‐month study period). Social risk risk adjustment includes Medicaid dual‐eligibility status, original entitlement for disability status, number of residential ZIP codes, fifth‐quintile of ADI for census block group of patient residence, fifth‐quintile of ADI for hospital population. AMI=acute myocardial infarction; CHF=congestive heart failure. (B) Results include hospitals eligible for penalties under the HRRP (IPPS acute care hospitals with 25 or more index admissions for each condition during the 36‐month study period). Social risk adjustment includes Medicaid dual‐eligibility status, original entitlement for disability status, number of residential ZIP codes, fifth‐quintile of ADI for census block group of patient residence, fifth‐quintile of ADI for hospital population. AMI=acute myocardial infarction; CHF=congestive heart failure.