MediTrust: AI-Based Verification System for Detecting Fraudulent Medical Fund Requests and Ensuring Donor Confidence

C.Divagar,; P.Kanimozhi,; K.Janani,; M.Arunkumar,

doi:https://doi.org/10.55041/ijcope.v2i4.981

Volume 02, Issue 04

Published on: April 2026

MEDITRUST: AI-BASED VERIFICATION SYSTEM FOR DETECTING FRAUDULENT MEDICAL FUND REQUESTS AND ENSURING DONOR CONFIDENCE

C.Divagar P.Kanimozhi K.Janani M.Arunkumar

Department of Computer Science and Engineering Jayalakshmi Institute Of Technology Dharmapuri

DOI:https://doi.org/10.55041/ijcope.v2i4.981

Article Status

Plagiarism Passed Peer Reviewed Open Access

Available Documents

Download PDF Review Report

Abstract

Medical Fund refers to financial assistance provided to individuals or families to cover medical treatments, surgeries, or emergencies. However, the increasing prevalence of fraudulent medical fund requests has become a critical challenge, with scammers fabricating treatment documents or bills to deceitfully solicit donations. Existing verification methods are often manual or semi-automated, requiring human intervention to validate submitted documents. These approaches are time-consuming, error-prone, and struggle to detect sophisticated fraudulent attempts, leading to donor skepticism and reduced contributions. To address these issues, this project introduces an AI-powered Medical Fund Verification System that automates the detection and validation of submitted bills. The system first employs CRAFT (Character Region Awareness for Text Detection) to accurately identify text regions in uploaded medical documents, even in complex layouts. Extracted text regions are then processed using Donut (Document Understanding Transformer), a deep learning–based OCR model that converts document images into structured text, capturing critical details such as patient name, hospital information, and treatment costs. Finally, the Fuzzy Matching Algorithm cross-verifies the extracted information against a trusted hospital database to identify discrepancies and detect potential fraud. By combining advanced text detection, transformer-based recognition, and intelligent pattern matching, this system ensures accurate and timely verification of medical fund requests, safeguarding donor contributions, enhancing transparency, and restoring trust in medical crowdfunding platforms.

Keywords-- Medical Fund Verification, Fraud Detection, Artificial Intelligence, Deep Learning, Document Analysis, Fuzzy Matching, Medical Crowdfunding.

How to Cite this Paper

C.Divagar, , P.Kanimozhi, , K.Janani, & M.Arunkumar, (2026). MediTrust: AI-Based Verification System for Detecting Fraudulent Medical Fund Requests and Ensuring Donor Confidence. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(04). https://doi.org/10.55041/ijcope.v2i4.981

C.Divagar, , et al.. "MediTrust: AI-Based Verification System for Detecting Fraudulent Medical Fund Requests and Ensuring Donor Confidence." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 04, 2026, pp. . doi:https://doi.org/10.55041/ijcope.v2i4.981.

C.Divagar, , P.Kanimozhi, K.Janani, and M.Arunkumar. "MediTrust: AI-Based Verification System for Detecting Fraudulent Medical Fund Requests and Ensuring Donor Confidence." International Journal of Creative and Open Research in Engineering and Management 02, no. 04 (2026). https://doi.org/https://doi.org/10.55041/ijcope.v2i4.981.

Search & Index

References

Lee and V. Lehdonvirta, “New digital safety net or just more ‘friendfunding’? Institutional analysis of medical crowdfunding in the United States,” Inform. Commun. Soc., vol. 1, no. 3, pp. 1–25, Apr. 2020.

Snyder and V. A. Crooks, “Is there room for privacy in medical crowdfunding?” J. Med. Ethics, vol. 47, no. 12, p. e49, Nov. 2020. .

Deng, Y., & Liu, L. (2021). “PaddleOCR: An Open-Source Optical Character Recognition (OCR) Toolkit.” arXiv preprint arXiv:2104.01932. DOI: 10.48550/arXiv.2104.0193.

Koo, D., & Jeong, S. (2020). “Deep Learning for Medical Fraud Detection.” Computers in Biology and Medicine, 123, 103894. DOI: 10.1016/j.compbiomed.2020.103894

no. e0229760.Sahu, S., & Nayak, R. (2020). “Medical Fraud Detection using Machine Learning Techniques.” Journal of Healthcare Engineering, 2020. DOI: 10.1155/2020/3281564.

Kenworthy, Z. Dong, A. Montgomery, E. Fuller, and L. Berliner, “A cross-sectional study of social inequities in medical crowdfunding campaigns in the United States,” PLoS ONE, vol. 15, no. 3, Mar. 2020Vinciarelli et al. (2009) – Social signal processing.
– Provides foundational concepts for analyzing human behavioral signals in interactions.

Fong, M. Jain, W. Sacks, A. Ho, and Y. Chen, “Crowdfunding campaigns and thyroid surgery: Who, what, where, and how much?” J. Surgical Res., vol. 253, pp. 63–68, Sep. 2020. .

Snyder and V. A. Crooks, “Is there room for privacy in medical crowdfunding?” J. Med. Ethics, vol. 47, no. 12, p. e49, Nov. 2020.

J. Renwick and E. Mossialos, “Crowdfunding our health: Eco nomic risks and benefits,” Social Sci. Med., vol. 191, pp. 48–56, Oct. 2017.

C. Short, D. J. Ketchen, A. F. McKenny, T. H. Allison, and R. D. Ireland, “Research on crowdfunding: Reviewing the (very recent) past and celebrating the present,” Entrepreneurship Theory Pract., vol. 41, no. 2, pp. 149–160, 2017.

Ethical Compliance & Review Process

•All submissions are screened under plagiarism detection.
•Review follows editorial policy.
•Authors retain copyright.
•Peer Review Type: Double-Blind Peer Review
•Published on: May 01 2026

CCBYNC

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.

View License

Back to Volume 02, Issue 04 View All Issues Next Article

← Previous Article

MEDI AI : A DISEASE PREDICTION SYSTEM

Next Article →

Melanoma Classification on Dermoscopy Images Using A Neural Network Ensemble Model