Detecting Healthcare Billing Fraud with Graph Neural Networks
Keywords:
Healthcare Payment Integrity, Fraud Waste and Abuse Detection, Unsupervised Machine Learning, Graph-Based Anomaly Detection, Payer–Provider Network Analytics, Billing Pattern Analysis, Medicaid Payment Oversight, Healthcare Claims Analytics, Encounter-Level Fraud Detection, Normalized Payment Amount Modeling, Data-Driven Healthcare Compliance, Subrogation Data Integration, Network-Based Risk Scoring, Real-Time Payment Monitoring, Public Healthcare Program Integrity.Abstract
Healthcare payment accuracy directly influences both cost and quality of care, yet high rates of fraud, waste, and abuse continue to persist. These challenges are exacerbated by the inherent complexity and lack of transparency surrounding payment analytics. Addressing these issues, this study proposes an effective, data-driven solution for detecting potentially fraudulent or erroneous billing practices, using unsupervised machine learning to analyze payer-provider relationships. The primary motivation is threefold: first, such unsupervised approaches eliminate the need for a labeled training set; second, they take advantage of the richness and heterogeneity of the data, including subrogation and encounter information; and third, they have no bias toward any specific type of anomaly.
Core methodological contributions include the novel application of unsupervised and graph-based methods for billing analysis and anomaly detection, and the integration of external data into traditional billing tables to uncover new patterns. Testing demonstrates that model-enriched Normalized Payment Amount can help identify fraudulent encounters, offering long-term potential for both real-time monitoring and assisting state-level agencies responsible for managing Medicaid-funded healthcare.
References
1. Ekin, T., Frigau, L., & Conversano, C. (2021). Health care fraud classifiers in practice. Applied Stochastic Models in Business and Industry, 37(5), 890–903.
2. Kanksha, Bhaskar, A., Pande, S., Malik, R., & Khamparia, A. (2021). An intelligent unsupervised technique for fraud detection in health care systems. Intelligent Decision Technologies, 15(1), 101–112.
3. Inala, R. (2023). AI-powered investment decision support systems: Building smart data products with embedded governance controls. Journal for ReAttach Therapy and Developmental Diversities, 6(10), 2251-2266.
4. Musal, R. M., & others. (2021). How to detect healthcare fraud? A systematic review. Gaceta Sanitaria, 35(Suppl. 2), S441–S449.
5. Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021). A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 32(1), 4–24.
6. Ying, C., Cai, T., Luo, S., Zheng, S., Ke, G., He, D., Shen, Y., & Liu, T.-Y. (2021). Do transformers really perform badly for graph representation? Advances in Neural Information Processing Systems, 34, 28877–28888.
7. Kolla, S. K., & Mangalampalli, B. M. (2024). Edge-Based Deep Learning Systems for Point-of-Care Diagnostic Intelligence. Journal of Neonatal Surgery, 13(1), 2387-2399.
8. Wang, J., Ma, A., Chang, Y., Gong, J., Jiang, Y., et al. (2021). scGNN is a novel graph neural network framework for single-cell RNA-seq analyses. Nature Communications, 12, 1882.
9. Li, M. M., Huang, K., & Zitnik, M. (2022). Graph representation learning in biomedicine and healthcare. Nature Biomedical Engineering, 6(12), 1353–1369.
10. Gu, Y., Yang, X., Tian, L., Yang, H., Lv, J., Yang, C., Wang, J., Xi, J., Kong, G., & Zhang, W. (2022). Structure-aware siamese graph neural networks for encounter-level patient similarity learning. Journal of Biomedical Informatics, 127, 104027.
11. Inala, R., & Somu, B. (2024). Agentic ai in retail banking: Redefining customer service and financial decision-making. Journal of Artificial Intelligence and Big Data Disciplines, 1(1), 1-19.
12. Cho, H. N., Ahn, I., Gwon, H., Kang, H. J., Kim, Y., Seo, H., Choi, H., Kim, M., Han, J., Kee, G., Jun, T. J., & Kim, Y.-H. (2022). Heterogeneous graph construction and HinSAGE learning from electronic medical records. Scientific Reports, 12, Article 20893.
13. Zou, Y., Pesaranghader, A., Song, Z., Verma, A., Buckeridge, D. L., & Li, Y. (2022). Modeling electronic health record data using an end-to-end knowledge-graph-informed topic model. Scientific Reports, 12, Article 17868.
14. Settipalli, L., & Gangadharan, G. R. (2022). WMTDBC: An unsupervised multivariate analysis model for fraud detection in health insurance claims. Expert Systems with Applications, 205, 119259.
15. Davuluri, P. S. L. (2023). AI-Augmented Sanctions Screening: Enhancing Accuracy and Latency in Real Time Compliance Systems. AI-Augmented Sanctions Screening: Enhancing Accuracy and Latency in Real Time Compliance Systems (December 15, 2023).
16. Kumaraswamy, N., Markey, M. K., Barner, J. C., & Rascati, K. (2022). Feature engineering to detect fraud using healthcare claims data. Expert Systems with Applications, 210, 118433.
17. Hou, Z., Liu, X., Cen, Y., Dong, Y., Yang, H., Wang, C., & Tang, J. (2022). GraphMAE: Self-supervised masked graph autoencoders. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 594–604.
18. Rampášek, L., Galkin, M., Dwivedi, V. P., Luu, A. T., Wolf, G., & Beaini, D. (2022). Recipe for a general, powerful, scalable graph transformer. Advances in Neural Information Processing Systems, 35, 14501–14515.
19. Gottimukkala, V. R. R. (2024). Federated Learning Approaches for Fraud Detection in International Payment Systems. https://www. jisem-journal. com/download/118_JISEM. pdf.
20. Adebayo, J., Mardanbeigi, D., & others. (2022). A novel fraud detection and prevention method for healthcare claim processing using machine learning and blockchain technology. Digital Applications in Archaeology and Cultural Heritage, 26, 100122.
21. Yun, S., Jeong, M., Yoo, S., Lee, S., Yoon, S., Kim, R., Kang, J., & Kim, H. J. (2022). Graph transformer networks: Learning meta-path graphs to improve GNNs. Neural Networks, 153, 104–119.
22. Qiu, Y., Lin, F., Chen, W., & Xu, M. (2023). Pre-training in medical data: A survey. Machine Intelligence Research, 20, 147–179.
23. Kolla, S. K., & Reddy, V. A. R. (2024). Evaluating Cloud-Native vs. Hybrid Architectures for Health Benefit Administration Systems. International Journal of Medical Toxicology and Legal Medicine, 27(5), 1042-1053.
24. Lu, J., Lin, K., Chen, R., & Lin, M. (2023). Health insurance fraud detection by using an attributed heterogeneous information network with a hierarchical attention mechanism. BMC Medical Informatics and Decision Making, 23, Article 62.
25. Xiao, S., Bai, T., Cui, X., Wu, B., Meng, X., & Wang, B. (2023). A graph-based contrastive learning framework for Medicare insurance fraud detection. Frontiers of Computer Science, 17(2), 172341.
26. Yoo, Y., Shin, J., & Kyeong, S. (2023). Medicare fraud detection using graph analysis: A comparative study of machine learning and graph neural networks. IEEE Access, 11, 88278–88294.
27. Hancock, J. T., Bauder, R. A., Wang, H., & Khoshgoftaar, T. M. (2023). Explainable machine learning models for Medicare fraud detection. Journal of Big Data, 10, Article 154.
28. Mao, Q., Liu, Z., Liu, C., & Sun, J. (2023). HINormer: Representation learning on heterogeneous information networks with graph transformer. Proceedings of the ACM Web Conference 2023, 599–608.
29. Nikolentzos, G., Vazirgiannis, M., Xypolopoulos, C., Lingman, M., & Brandt, E. G. (2023). Synthetic electronic health records generated with variational graph autoencoders. npj Digital Medicine, 6, Article 83.
30. Inala, R. Designing Scalable Technology Architectures for Customer Data in Group Insurance and Investment Platforms.
31. Meng, X., & Zou, T. (2023). Clinical applications of graph neural networks in computational histopathology: A review. Computers in Biology and Medicine, 164, 107201.
32. Paul, S. G., Saha, A., Hasan, M. Z., Noori, S. R. H., & Moustafa, A. (2024). A systematic review of graph neural network in healthcare-based applications: Recent advances, trends, and future directions. IEEE Access, 12, 15145–15170.
33. Boll, H. O., Amirahmadi, A., Ghazani, M. M., de Morais, W. O., de Freitas, E. P., Soliman, A., Etminani, F., Byttner, S., & Recamonde-Mendoza, M. (2024). Graph neural networks for clinical risk prediction based on electronic health records: A survey. Journal of Biomedical Informatics, 151, 104616.
34. Hong, B., Lu, P., Xu, H., Lu, J., Lin, K., & Yang, F. (2024). Health insurance fraud detection based on multi-channel heterogeneous graph structure learning. Heliyon, 10(9), e30045.
35. Kolla, T. (2024). Graph Neural Networks for HCC Risk Adjustment and Interoperability. International Journal of Science, Research and Technology, 7(6), 13244-13255.
36. Leevy, J. L., Hancock, J., & Khoshgoftaar, T. M. (2024). Medicare fraud detection: A comparative study on the effectiveness of one-class and binary classification models. International Journal of Computers and Applications, 47(3), 1–12.
37. Piya, F. L., Gupta, M., & Beheshti, R. (2024). HealthGAT: Node classifications in electronic health records using graph attention networks. Proceedings of the IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies, 132–141.
38. Johnson, R., Li, M. M., Noori, A., Queen, O., & Zitnik, M. (2024). Graph artificial intelligence in medicine. Annual Review of Biomedical Data Science, 7, 345–368.
