Improving Hospital Performance Rankings Using Discrete Patient Diagnoses for Risk Adjustment of Outcomes

Health Serv Res. 2018 Apr;53(2):974-990. doi: 10.1111/1475-6773.12683. Epub 2017 Mar 13.


Objective: To assess the changes in patient outcome prediction and hospital performance ranking when incorporating diagnoses as risk adjusters rather than comorbidity indices.

Data sources: Healthcare Cost and Utilization Project State Inpatient Databases for New York State, 2005-2009.

Study design: Conducted tree-based classification for mortality and readmission by incorporating discrete patient diagnoses as predictors, comparing with traditional comorbidity indices such as those used for Centers for Medicare and Medicaid Services (CMS) outcome models.

Principal findings: Diagnosis codes as predictors increased predictive accuracy 5.6 percent (95% CI: 4.5-6.9 percent) relative to CMS condition categories for heart failure 30-day mortality. Most other outcomes exhibited statistically significant accuracy gains and facility ranking shifts. Sensitivity analysis showed improvements even when predictors were limited to only the diagnoses included in CMS models.

Conclusions: Discretizing patient severity information beyond the levels of traditional comorbidity indices improves patient outcome predictions and substantially shifts facility rankings.

Keywords: Medicare; Risk adjustment; machine learning.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Age Factors
  • Benchmarking / methods*
  • Centers for Medicare and Medicaid Services, U.S. / statistics & numerical data
  • Comorbidity
  • Heart Failure / mortality
  • Humans
  • Logistic Models
  • Machine Learning
  • Patient Readmission / statistics & numerical data
  • Quality Indicators, Health Care / statistics & numerical data
  • Quality of Health Care / statistics & numerical data
  • Risk Adjustment / methods*
  • Severity of Illness Index
  • Sex Factors
  • Socioeconomic Factors
  • Treatment Outcome
  • United States