Sokol L, Garcia B, Rodriguez J, West M, Johnson K
Veridian Corporation, Fairfax, Virginia, USA.
Top Health Inf Manage. 2001 Aug;22(1):1-13.
Data mining can be/used to detect health care fraud and abuse through visualization of very large data sets to isolate new and unusual patterns of activity. Data mining has allowed better direction and use of health care fraud detection and investigative resources by recognizing and quantifying the underlying indicators of fraudulent claims, fraudulent providers, and fraudulent beneficiaries. A large amount of work must be performed prior to the actual data mining. These precursory tasks include: customer discussions, data extraction and cleaning, transformation of the database, and auditing (basic statistics and visualization of the information) of the data. This paper describes the tasks performed in support of a project for HCFA (Health Care Financing Administration).
数据挖掘可用于通过对超大型数据集进行可视化处理，以识别新的和异常的活动模式，从而检测医疗保健欺诈和滥用行为。数据挖掘通过识别和量化欺诈性索赔、欺诈性医疗服务提供者和欺诈性受益人的潜在指标，使医疗保健欺诈检测和调查资源得到了更好的导向和利用。在实际进行数据挖掘之前，必须完成大量工作。这些前期任务包括：与客户进行讨论、数据提取与清理、数据库转换以及对数据进行审计（基本统计和信息可视化）。本文描述了为支持医疗保健财务管理局（HCFA）的一个项目而执行的任务。
