Secondary Logo

Journal Logo

Institutional members access full text with Ovid®

Using Risk-Adjustment Models to Identify High-Cost Risks

Meenan, Richard T. PhD, MPH*; Goodman, Michael J. PhD; Fishman, Paul A. PhD; Hornbrook, Mark C. PhD*; O’Keeffe-Rosetti, Maureen C. MS*; Bachman, Donald J. MS*

doi: 10.1097/01.MLR.0000094480.13057.75
Original Articles

Background.  We examine the ability of various publicly available risk models to identify high-cost individuals and enrollee groups using multi-HMO administrative data.

Methods.  Five risk-adjustment models (the Global Risk-Adjustment Model [GRAM], Diagnostic Cost Groups [DCGs], Adjusted Clinical Groups [ACGs], RxRisk, and Prior-expense) were estimated on a multi-HMO administrative data set of 1.5 million individual-level observations for 1995–1996. Models produced distributions of individual-level annual expense forecasts for comparison to actual values. Prespecified “high-cost” thresholds were set within each distribution. The area under the receiver operating characteristic curve (AUC) for “high-cost” prevalences of 1% and 0.5% was calculated, as was the proportion of “high-cost” dollars correctly identified. Results are based on a separate 106,000-observation validation dataset.

Main Results.  For “high-cost” prevalence targets of 1% and 0.5%, ACGs, DCGs, GRAM, and Prior-expense are very comparable in overall discrimination (AUCs, 0.83–0.86). Given a 0.5% prevalence target and a 0.5% prediction threshold, DCGs, GRAM, and Prior-expense captured $963,000 (approximately 3%) more “high-cost” sample dollars than other models. DCGs captured the most “high-cost” dollars among enrollees with asthma, diabetes, and depression; predictive performance among demographic groups (Medicaid members, members over 64, and children under 13) varied across models.

Conclusions.  Risk models can efficiently identify enrollees who are likely to generate future high costs and who could benefit from case management. The dollar value of improved prediction performance of the most accurate risk models should be meaningful to decision-makers and encourage their broader use for identifying high costs.

From the *Center for Health Research, Northwest and Hawaii, Kaiser Permanente Northwest, Portland, Oregon.

From †HealthPartners Research Foundation, Minneapolis, Minnesota.

From the ‡Center for Health Studies, Group Health Cooperative of Puget Sound, Seattle, Washington.

This study was supported by the Agency for Healthcare Research and Quality, Kaiser Permanente Northwest, Kaiser Permanente Rocky Mountain, Kaiser Permanente Central East, Kaiser Permanente Northeast, HealthPartners, and Group Health Cooperative of Puget Sound.

Address correspondence and reprint requests to: Richard T. Meenan, PhD, MPH, Center for Health Research, Northwest and Hawaii, Kaiser Permanente Northwest, 3800 N. Interstate Avenue, Portland, OR 97227. E-mail:

© 2003 Lippincott Williams & Wilkins, Inc.