对医疗保险数据进行可解释的无监督异常检测
Hannes De Meulemeester1, Frank De Smet2,3, Johan van Dorst2
1Department of Electrical Engineering, ESAT-STADIUS, KU Leuven, Kasteelpark Arenberg 10, B-3001 Leuven, Belgium. hannes.demeulemeester@gmail.com.
本研究介绍了一种机器学习工作流程,用于检测医疗保健浪费和欺诈行为. 它使用先进的异常检测和解释来帮助保险公司有效地识别不寻常的供应商行为.
科学领域:
- 医疗信息学 医疗信息学
- 数据科学数据科学数据科学
- 机器学习 机器学习
背景情况:
- 医疗保健浪费和欺诈对保险公司构成重大挑战.
- 大数据分析和机器学习为检测提供了潜在的解决方案.
- 获取标记数据用于训练欺诈检测模型是困难和昂贵的.
研究的目的:
- 开发一种机器学习工作流程,用于检测医疗保健浪费和欺诈行为.
- 帮助调查人员识别使用异常资源的从业者.
- 提高打击医疗保险中浪费和欺诈的效率.
主要方法:
- 综合分类嵌入,无监督异常检测和沙普利增量解释 (SHAP).
- 应用于高卡丁级分类变量和异常检测的技术.
- 使用SHAP用于医疗保险异常检测中的模型解释性.
主要成果:
- 类别嵌入比标准方法显著提高了性能.
- 无监督的异常检测技术通常优于传统方法.
- 工作流成功地发现了全科医生的新奇异常趋势.
结论:
- 拟议的工作流可以有效地检测具有非典型行为的医疗保健提供者.
- 它帮助专家调查人员做出有关潜在欺诈和过度消费的明智决策.
- 这种方法加强了对医疗保险的浪费和欺诈的打击.
更多相关视频
06:55Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
相关概念视频
Unusual Results
According to the range rule of thumb, any value above or below two standard deviations, 2σ from the mean, μ is considered unusual.
Maximum unusual value =...
What Are Outliers?
The z score is used to find outliers or unusual values. It should be noted that any values beyond -2 and +2 are...
Steps in Outbreak Investigation
Outliers and Influential Points
Issues And Trends In Healthcare Delivery System
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Quantifying and Rejecting Outliers: The Grubbs Test
