Related Experiment Videos
Comparison of an Updated Risk Stratification Index to Hierarchical Condition Categories
George F Chamoun1, Linyan Li, Nassib G Chamoun
1The Lown Institute, Boston, Massachusetts (G.F.C., N.G.C., V.S.); Department of Environmental Health, Harvard T.H. Chan School of Public Health, Boston, Massachusetts (L.L.); and Department of Outcomes Research, Cleveland Clinic, Cleveland, Ohio (D.I.S.).
Insights
The rederived Risk Stratification Index (RSI) shows improved discrimination and prediction accuracy compared to Hierarchical Condition Categories (HCC) for mortality and length of stay, making it superior for quality metrics.
Area of Science:
- Health Services Research
- Health Economics
- Medical Informatics
Background:
- Two primary models, Risk Stratification Index (RSI) and Hierarchical Condition Categories (HCC), assess baseline risk using comorbidities and procedures.
- HCC models are updated annually, while the RSI has not been rederived since 2010.
- A direct comparison between the RSI and HCC models has been lacking.
Purpose of the Study:
- To rederive the Risk Stratification Index using recent data.
- To directly compare the performance of the rederived RSI against the contemporaneous Hierarchical Condition Categories model.
- To evaluate the predictive accuracy and discrimination capabilities of both risk adjustment models.
Main Methods:
- Reimplementation of the original Risk Stratification Index derivation procedures using Medicare data from 2007-2011.
- Construction of Hierarchical Condition Categories using Center for Medicare and Medicaid Services-provided software on the entire dataset.
- Comparison of model discrimination using C-Statistics and evaluation of predictive accuracy via calibration plots.
Main Results:
- The rederived Risk Stratification Index demonstrated improved discrimination compared to its original derivation.
- The RSI significantly outperformed the HCC model in predicting in-hospital, 30-day, and 1-year mortality, as well as hospital length-of-stay.
- Both models showed linear predictive accuracy upon calibration, but the RSI exhibited less variance in its predictions.
Conclusions:
- The enhanced discrimination and reduced variance in predictions establish the Risk Stratification Index as superior to the Hierarchical Condition Categories.
- The rederived RSI offers a robust foundation for developing reliable care-quality metrics.
- The RSI's improved performance supports its utility for objective provider comparisons in healthcare.
Background:
The Risk Stratification Index and the Hierarchical Condition Categories model baseline risk using comorbidities and procedures. The Hierarchical Condition categories are rederived yearly, whereas the Risk Stratification Index has not been rederived since 2010. The two models have yet to be directly compared. The authors thus rederived the Risk Stratification Index using recent data and compared their results to contemporaneous Hierarchical Condition Categories.
Methods:
The authors reimplemented procedures used to derive the original Risk Stratification Index derivation using the 2007 to 2011 Medicare Analysis and Provider review file. The Hierarchical Condition Categories were constructed on the entire data set using software provided by the Center for Medicare and Medicaid Services. C-Statistics were used to compare discrimination between the models. After calibration, accuracy for each model was evaluated by plotting observed against predicted event rates.
Results:
Discrimination of the Risk Stratification Index improved after rederivation. The Risk Stratification Index discriminated considerably better than the Hierarchical Condition Categories for in-hospital, 30-day, and 1-yr mortality and for hospital length-of-stay. Calibration plots for both models demonstrated linear predictive accuracy, but the Risk Stratification Index predictions had less variance.
Conclusions:
Risk Stratification discrimination and minimum-variance predictions make it superior to Hierarchical Condition Categories. The Risk Stratification Index provides a solid basis for care-quality metrics and for provider comparisons.