Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69063
Volume:
10 |
11 |
Nov 2026
Pages:
1-7
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Engineering
SVPM’s College of Engineering, Malegaon BK. Baramati, Maharashtra, India
Department of Computer Engineering
SVPM’s College of Engineering, Malegaon BK. Baramati, Maharashtra, India
Department of Computer Engineering
SVPM’s College of Engineering, Malegaon BK. Baramati, Maharashtra, India
Department of Computer Engineering
SVPM’s College of Engineering, Malegaon BK. Baramati, Maharashtra, India
Department of Computer Engineering
SVPM’s College of Engineering, Malegaon BK. Baramati, Maharashtra, India
Healthcare insurance fraud and inaccurate medical claims create financial losses, slow down valid claim processing, and increase the load of work of claim auditors. Traditional claim review often depend on manually checking documents and predefined rules, which can be difficult to scale when claim volumes are large and documents contain inconsistent or unstructured information. This survey outlines a practical taxonomy of approaches used in automated medical claim auditing, including optical character recognition (OCR), rule-based validation, supervised machine learning, unsupervised anomaly detection, Machine Learning, and explainable artificial intelligence. It discusses how document extraction by OCR and Rule validation can be combined with predictive models to prioritize claims for human review. The paper also compares the strengths and limitations of representative model families and highlights recurring evaluation concerns, particularly class imbalance, limited access to representative labelled data, privacy, interpretability, and generalization across providers and regions. Published reviews already examine machine-learning-based healthcare claims fraud detection; therefore, a useful contribution for a new survey must be a clearly scoped synthesis focused on the interaction between document-level extraction, rule validation, model-based risk scoring, and human audit workflows. The paper concludes with recommendations for transparent evaluation, cautious use of risk scores, and human-in-the-loop decision-making.
KEYWORDS
Artificial intelligence-based healthcare fraud detection can support medical claim auditors by combining rule-based validation with machine learning models that prioritize claims for further investigation. Optical Character Recognition (OCR) and document-processing techniques help convert unstructured medical documents into structured data for automated analysis. However, errors during information extraction can affect subsequent validation and prediction results. Supervised learning, anomaly detection, and ensemble methods offer different advantages, but their effectiveness depends on data quality, class distribution, feature availability, and evaluation methodology. Therefore, no single algorithm should be considered universally suitable for all medical claim fraud detection scenarios. Reliable and responsible claim auditing systems require representative datasets, appropriate evaluation metrics for imbalanced classes, interpretable results, data privacy safeguards, and human supervision. This survey emphasizes the importance of examining the complete claim-auditing process, from document extraction and rule-based validation to machine learning-based risk assessment and auditor review. Its contribution should be established through a clearly defined scope, a systematic and reproducible literature search, and a critical comparison of the selected studies. Future research should focus on evaluating integrated auditing frameworks, improving OCR reliability, strengthening model explainability, and assessing performance under realistic operational conditions.
[1] M. S. Iqbal, A. Abd-Alrazaq, and M. Househ, “Artificial Intelligence Solutions to Detect Fraud in Healthcare Settings: A Scoping Review,” Studies in Health Technology and Informatics, vol. 295, pp. 20–23, 2022, doi: 10.3233/SHTI220649. [2] A. du Preez, S. Bhattacharya, P. Beling, and E. Bowen, “Fraud Detection in Healthcare Claims Using Machine Learning: A Systematic Review,” Artificial Intelligence in Medicine, vol. 160, Art. no. 103061, 2025, doi: 10.1016/j.artmed.2024.103061. [3] E. D. Curtis, P. Billion-Polak, T. M. Khoshgoftaar, et al., “A Review of Distinct Machine Learning Classifiers for Healthcare Fraud Detection,” Journal of Big Data, vol. 12, Art. no. 238, 2025, doi: 10.1186/s40537-025-01295-3. [4] J. M. Johnson and T. M. Khoshgoftaar, “Data-Centric AI for Healthcare Fraud Detection,” SN Computer Science, vol. 4, Art. no. 389, 2023, doi: 10.1007/s42979-023-01809-x. [5] B. Hong, P. Lu, H. Xu, J. Lu, K. Lin, and F. Yang, “Health Insurance Fraud Detection Based on Multi-Channel Heterogeneous Graph Structure Learning,” Heliyon, vol. 10, no. 9, Art. no. e30045, 2024, doi: 10.1016/j.heliyon.2024.e30045. [6] M. A. Abo El-Enen, D. Tbaishat, A. T. Sahlol, A. Nazir, K. AlMaymun, M. AbdulRazek, R. Muhammad, F. Adlan, and R. Sharma, “Fraud Detection in Medical Insurance Claims Using Majority Voting of Multiple Unsupervised Algorithms,” Procedia Computer Science, vol. 244, pp. 9–22, 2024, doi: 10.1016/j.procs.2024.10.173. [7] J. T. Hancock, R. A. Bauder, H. Wang, and T. M. Khoshgoftaar, “Explainable Machine Learning Models for Medicare Fraud Detection,” Journal of Big Data, vol. 10, Art. no. 154, 2023, doi: 10.1186/s40537-023-00821-5. [8] R. A. Bauder and T. M. Khoshgoftaar, “The Effects of Varying Class Distribution on Learner Behavior for Medicare Fraud Detection with Imbalanced Big Data,” Health Information Science and Systems, vol. 6, Art. no. 9, 2018, doi: 10.1007/s13755-018-0051-3. [9] E. Nabrawi and A. Alanazi, “Fraud Detection in Healthcare Insurance Claims Using Machine Learning,” Risks, vol. 11, no. 9, Art. no. 160, 2023, doi: 10.3390/risks11090160. [10] S. Shekhar, J. Leder-Luis, and L. Akoglu, “Unsupervised Machine Learning for Explainable Health Care Fraud Detection,” National Bureau of Economic Research, Working Paper No. 30946, 2023, doi: 10.3386/w30946.
Publication Date
11/16/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...