Liou Fen-May, Tang Ying-Chan, Chen Jean-Yi
Graduate Institute of Business Management, Yuanpei University Hsinchu, 306, Yuanpei St., Hsin Chu 300, Taiwan.
Health Care Manag Sci. 2008 Dec;11(4):353-8. doi: 10.1007/s10729-008-9054-y.
Hospitals and health care providers tend to get involved in exaggerated and fraudulent medical claims initiated by national insurance schemes. The present study applies data mining techniques to detect fraudulent or abusive reporting by healthcare providers using their invoices for diabetic outpatient services. This research is pursued in the context of Taiwan's National Health Insurance system. We compare the identification accuracy of three algorithms: logistic regression, neural network, and classification trees. While all three are quite accurate, the classification tree model performs the best with an overall correct identification rate of 99%. It is followed by the neural network (96%) and the logistic regression model (92%).
医院和医疗保健提供者往往会卷入由国家保险计划发起的夸大和欺诈性医疗索赔中。本研究应用数据挖掘技术，通过医疗保健提供者的糖尿病门诊服务发票来检测欺诈或滥用报告。这项研究是在台湾国民健康保险系统的背景下进行的。我们比较了三种算法的识别准确率：逻辑回归、神经网络和分类树。虽然这三种算法都相当准确，但分类树模型表现最佳，总体正确识别率为99%。其次是神经网络（96%）和逻辑回归模型（92%）。
