A Data-Driven Intelligent Supervision System for Generating High-Risk Organized Fraud Clues in Medical Insurance Funds
Open Access
- 18 August 2025
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 14 (16) , 3268
Abstract
Medical insurance fraud, especially organized drug resale schemes, has become increasingly sophisticated, challenging traditional supervision methods. This paper presents an AI-powered legal supervision model that automatically detects fraudulent drug resale activities in medical insurance claims. Unlike rule-based approaches, our solution employs multi-dimensional behavioral analysis and adaptive clustering techniques to identify both individual anomalies and organized fraud networks. The proposed model follows a three-stage detection pipeline: (1) automated clue generation through feature aggregation across frequency, cost, and behavioral dimensions; (2) group behavior analysis using spatiotemporal patterns and medication similarity metrics; (3) risk stratification via FLASC clustering to dynamically determine suspicion thresholds. Key innovations include a data-driven threshold generation mechanism that eliminates expert bias and a cross-dimensional fraud pattern recognition system that connects individual outliers with group behaviors. Validated on real-world medical insurance data (8917 insurance cards, 1.1 million records), the model achieved 89% precision, 42% recall, and 87% accuracy in detecting high-risk fraud cases while uncovering previously unnoticed organized fraud rings. This research provides a scalable framework for intelligent healthcare fund supervision, with potential applications in other social security domains.Keywords
Funding Information
- National Key Research and Development Plan (2023YFC3306100)
This publication has 31 references indexed in Scilit:
- Predictive analysis for healthcare fraud detection: Integration of probabilistic model and interpretable machine learningInformation Sciences, 2025
- A robust and interpretable ensemble machine learning model for predicting healthcare insurance fraudScientific Reports, 2025
- Using a Bayesian Belief Network to detect healthcare fraudExpert Systems with Applications, 2023
- Building prediction models and discovering important factors of health insurance fraud using machine learning methodsJournal of Ambient Intelligence and Humanized Computing, 2023
- Deep Isolation Forest for Anomaly DetectionIEEE Transactions on Knowledge and Data Engineering, 2023
- K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big dataInformation Sciences, 2022
- Improving graph-based label propagation algorithm with group partition for fraud detectionApplied Intelligence, 2020
- Unsupervised K-Means Clustering AlgorithmIEEE Access, 2020
- Outlier detection in healthcare fraud: A case study in the Medicaid dental domainInternational Journal of Accounting Information Systems, 2016
- Categorizing and Describing the Types of Fraud in HealthcareProcedia Computer Science, 2015