Evaluating diagnosis-based risk-adjustment methods in a population with spinal cord dysfunction

Objective: To examine performance of models in predicting health care utilization for individuals with spinal cord dysfunction. Design: Regression models compared 2 diagnosis-based risk-adjustment methods, the adjusted clinical groups (ACGs) and diagnostic cost groups (DCGs). To improve prediction, we added to our model: (1) spinal cord dysfunction-specific diagnostic information, (2) limitations in self-care function, and (3) both 1 and 2. Setting: Models were replicated in 3 populations. Participants: Samples from 3 populations: (1) 40% of veterans using Veterans Health Administration services in fiscal year 1997 (FY97) (N = 1,046,803), (2) veteran sample with spinal cord dysfunction identified by codes from the International Statistical Classification of Diseases, 9th Revision, Clinical Modifications (N = 7666), and (3) veteran sample identified in Veterans Affairs Spinal Cord Dysfunction Registry (N=5888). Interventions: Not applicable. Main Outcome Measures: Inpatient, outpatient, and total days of care in FY97.2 Results: The DCG models (R-2 range, .22-.38) performed better than ACG models (R-2 range, .04-.34) for all outcomes. Spinal cord dysfunction-specific diagnostic information improved prediction more in the ACG model than in the DCG model (R-2 range for ACG, .14-.34; R-2 range for DCG, .24.38). Information on self-care function slightly improved performance (R-2 range increased from 0 to .04). Conclusions: The DCG risk-adjustment models predicted health care utilization better than ACG models. ACG model prediction was improved by adding information. (C) 2004 by the American Congress of Rehabilitation Medicine and the American Academy of Physical Medicine and Rehabilitation.