MediTrust: Intelligent AI Framework for Detecting Fraudulent Medical Fund Requests Using Document Understanding and Data Verification

MediTrust offers a comprehensive and intelligent solution to the growing problem of fraud in medical crowdfunding platforms. By combining advanced AI techniques with structured document verification processes, the system ensures that financial assistance is directed toward genuine patients. The proposed framework enhances transparency, builds donor trust, and reduces the risk of misuse. Its scalable architecture makes it suitable for large-scale deployment, while its modular design allows for future enhancements. In the future, the system can be extended by integrating real-time hospital databases, blockchain-based document verification, and more advanced deep learning models. These improvements can further strengthen the reliability and accuracy of the framework, making MediTrust a robust solution for secure and trustworthy medical fundraising.

 1. S. Hussain et al., “Blockchain-Based Trust Management in Crowdfunding,” IEEE Access, 2026.  2. S. Lee et al., “Fraud Detection Using Feature Selection,” IEEE Access, 2025.  3. O. K. Alia et al., “IHSAN Crowdfunding Platform,” IEEE Access, 2024.  4. K. O. Asamoah et al., “Blockchain-Based Loan Platform,” IEEE Access, 2023.  5. I. Matloob et al., “Sequence Mining for Fraud Detection,” IEEE Access, 2022. 6. IEEE, “Standards for Artificial Intelligence and Data Verification Systems,” IEEE Standards Association, 2022. 7. R. Smith, “An Overview of the Tesseract OCR Engine,” Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2007. 8.  J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” NAACL-HLT, 2019. 9.  M. Schuster and K. Nakajima, “Japanese and Korean Voice Search,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012. 10. Z. Akata et al., “CRAFT: Character Region Awareness for Text Detection,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.