Comparison of alternative risk adjustment measures for predictive modeling: high risk patient case finding using Taiwan's National Health Insurance claims.
Comparison of alternative risk adjustment measures for predictive modeling: high risk patient case finding using Taiwan's National Health Insurance claims.
复制标题
DOI：
10.1186/1472-6963-10-343
复制
发表时间：
2010-12-20
影响因子：
2.8
通讯作者：
Weiner JP
中科院分区：
文献类型：
--
作者：
Chang HY;Lee WC;Weiner JP
预测模型提供了一个通过关注极少数人来控制医疗支出扩张的机会。在台湾或亚洲，对风险调整模型在预测模型中的表现进行评估的情况很少。本研究的目的是利用台湾国民健康保险（NHI）索赔数据评估不同风险调整模型（ACG风险调整系统和先前支出）在预测建模中的表现，并比较通过不同模型识别的潜在高支出受试者的特征。随机抽取了 2002 年和 2003 年连续参加的 NHI 参保者样本（n = 164,562）。根据 2002 年 NHI 索赔数据得出的健康状况衡量标准和总支出用于预测成为 2003 年最大用户的可能性。提出了基于统计的指标（C 统计、敏感性和预测正值）和通过不同模型确定的顶级群体的特征（可管理疾病的支出和患病率）。基于诊断的模型和先前的支出模型都比人口模型表现得好得多。基于诊断的模型可以更好地识别患有可控制疾病的顶级用户；以前的支出模型在基于统计的指标和识别平均支出较高的人群方面更好。与基于诊断或人口统计模型相比，之前的支出状态可以正确识别更多实际的顶级用户。仅通过基于诊断的模型即可识别出的实际顶级用户的比例远低于通过之前的支出状况识别出的比例。不同模型识别的预测顶级用户具有不同的特征，并且模型之间关于哪些群体可能是潜在顶级用户的共识很少；因此，使用哪种模型应取决于预测建模的目的。就正确识别更多实际高支出用户而言，先前支出是比基于诊断的风险调整器更强大的工具。预测建模中基于诊断的模型仍有很大的改进空间。
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. 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. 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. 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.
登录
查看更多内容
影响因子：
3
作者：
Lee, Wui-Chiang;Huang, Tong-Po
通讯作者：
Huang, Tong-Po
影响因子：
3
作者：
Meenan, RT;Goodman, MJ;Bachman, DJ
通讯作者：
Bachman, DJ
影响因子：
9.7
作者：
Berk, ML;Monheit, AC
通讯作者：
Monheit, AC
影响因子：
--
作者：
Radcliff, Tiffany A;Cote, Murray J;Duncan, R Paul
通讯作者：
Duncan, R Paul
影响因子：
9.3
作者：
Chang, Hsien-Yen;Weiner, Jonathan P.
通讯作者：
Weiner, Jonathan P.