Open Access Research article

Comparison of alternative risk adjustment measures for predictive modeling: high risk patient case finding using Taiwan's National Health Insurance claims

Hsien-Yen Chang1*, Wui-Chiang Lee2 and Jonathan P Weiner1

Author Affiliations

1 Department of Health Policy & Management, Bloomberg School of Public Health, Johns Hopkins University, 624 N. Broadway, Baltimore, MD 21205, USA

2 Department of Medical Affairs & Planning, Taipei Veterans General Hospital, and Institute of Hospital Administration & Management, School of Medicine, National Yang-Ming University, 201 Section 2, Shih-Pai Rd, Taipei City 11217, Taiwan

For all author emails, please log on.

BMC Health Services Research 2010, 10:343  doi:10.1186/1472-6963-10-343

Published: 20 December 2010

Abstract

Background

Predictive modeling presents an opportunity to contain the expansion of medical expenditures by focusing on very few people. Evaluation of how risk adjustment models perform in predictive modeling in Taiwan or Asia has been rare. The aims of this study were to evaluate the performance of different risk adjustment models (the ACG risk adjustment system and prior expenditures) in predictive modeling, using Taiwan's National Health Insurance (NHI) claims data, and to compare characteristics of potentially high-expenditure subjects identified through different models.

Methods

A random sample of NHI enrollees continuously enrolled in 2002 and 2003 (n = 164,562) was selected. Health status measures and total expenditures derived from 2002 NHI claims data were used to predict the possibility of becoming 2003 top users. Statistics-based indicators (C-statistics, sensitivity, & Predictive Positive Value) and characteristics of identified top groups by different models (expenditures and prevalence of manageable diseases) were presented.

Results

Both diagnosis-based and prior expenditures models performed much better than the demographic model. Diagnosis-based models were better in identifying top users with manageable diseases; prior expenditures models were better in statistics-based indicators and identifying people with higher average expenditures. Prior expenditures status could correctly identify more actual top users than diagnosis-based or demographic models. The proportions of actual top users that could be identified by diagnosis-based models alone were much lower than that identified by prior expenditures status.

Conclusions

Predicted top users identified by different models have different characteristics and there is little agreement between modes regarding which groups would be potentially top users; therefore, which model to use should depend on the purpose of predictive modeling. Prior expenditures are a more powerful tool than diagnosis-based risk adjusters in terms of correctly identifying more actual high expenditures users. There is still much room left for improvement of diagnosis-based models in predictive modeling.