Outlier detection in healthcare fraud: A case study in the Medicaid dental domain
Outlier detection in healthcare fraud: A case study in the Medicaid dental domain
复制标题
DOI：
10.1016/j.accinf.2016.04.001
复制
发表时间：
2016-06-01
影响因子：
4.6
通讯作者：
van Hillegersberg, Jos
中科院分区：
文献类型：
--
作者：
van Capelleveen, Guido;Poel, Mannes;van Hillegersberg, Jos
医疗保险欺诈是一个紧迫的问题，导致医疗保险计划成本高昂且不断增加。由于提交的索赔数量巨大（估计每天有 50 亿），审核个人索赔或提供者是一项艰巨的任务。这鼓励使用自动预付款控制和更好的付款后决策支持工具，以实现主题专家分析。本文介绍了如何在付款后阶段应用无监督异常值技术来检测收到的保险索赔的欺诈模式。本文特别强调系统架构、为异常值检测设计的指标以及可疑提供商的标记，这可以支持欺诈专家评估提供商并揭露欺诈行为。这些算法在医疗补助数据上进行了测试，其中包含一个州的 650,000 份医疗保健索赔和 369 名牙医。两名医疗保健欺诈专家评估了已标记的案例，并得出结论，排名前 17 的提供商中有 12 家 (71%) 提交了可疑的索赔模式，应将其转交给官员进行进一步调查。其余 5 个提供商 (29%) 可能被视为错误分类，因为它们的模式可以通过提供商的特殊特征来解释。选择顶级标记的提供商被证明是一种有价值的定位方法，并且个别提供商分析揭示了一些潜在欺诈的案例。该研究的结论是，通过异常值检测，可以识别潜在欺诈的新模式，并可能在未来的自动检测机制中利用。 (C) 2016 Elsevier Inc. 保留所有权利。
Health care insurance fraud is a pressing problem, causing substantial and increasing costs in medical insurance programs. Due to large amounts of claims submitted, estimated at 5 billion per day, review of individual claims or providers is a difficult task. This encourages the employment of automated pre-payment controls and better post-payment decision support tools to enable subject matter expert analysis. This paper presents how to apply unsupervised outlier techniques at post-payment stage to detect fraudulent patterns of received insurance claims. A special emphasis in this paper is put on the system architecture, the metrics designed for outlier detection and the flagging of suspicious providers which may support the fraud experts in evaluating providers and reveal fraud. The algorithms were tested on Medicaid data encompassing 650,000 health-care claims and 369 dentists of one state. Two health care fraud experts evaluated flagged cases and concluded that 12 of the top 17 providers (71%) submitted suspicious claim patterns and should be referred to officials for further investigation. The remaining 5 providers (29%) could be considered mis-classifications as their patterns could be explained by special characteristics of the provider. Selecting top flagged providers is demonstrated to be a valuable as an, targeting method, and individual provider analysis revealed some cases of potential fraud. The study concludes that, through outlier detection, new patterns Of potential fraud can be identified and possibly utilized in future automated detection mechanisms. (C) 2016 Elsevier Inc. All rights reserved.