EUVIMEDEUVIMED entdecken
Crossref

An Adaptive Machine Learning System for Fraud Detection in Healthcare Data

K. Vijayprabakaran, R. Ganesan, S. Boopathi, A.Adharsh Jayaraj

International Journal of Engineering & Extended Technologies Research · 28.03.2026 · 08 (02)

DOI: 10.15662/ijeetr.2026.0802227 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Engineering & Extended Technologies Research, online erschienen am 28.03.2026. Verfasst von K. Vijayprabakaran und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid growth of digital healthcare systems and the increasing volume of medical claim data have created a critical need for intelligent and adaptive fraud detection systems. Healthcare organizations, particularly insurance providers and large-scale hospitals, face significant challenges due to fraudulent activities such as false claims, duplicate billing, and identity misuse. Traditional fraud detection methods, primarily based on rule-based systems and manual auditing, are insufficient for identifying complex, evolving, and hidden fraud patterns. To address these limitations, Artificial Intelligence (AI) has emerged as an effective solution for enhancing fraud detection frameworks. AI-driven systems integrate Machine Learning (ML) techniques to analyze large-scale healthcare datasets, enabling accurate identification of suspicious and fraudulent activities. Recent advancements in ensemble learning algorithms have significantly improved detection performance and system adaptability in fraud detection applications. In particular, Extreme Gradient Boosting (XGBoost) enables efficient classification by minimizing prediction errors through iterative learning and optimized feature selection. Additionally, advanced data preprocessing techniques, including handling missing values, encoding, normalization, and feature engineering, enhance model robustness and reduce false negative rates. The integration of data balancing methods such as Synthetic Minority Over-sampling Technique (SMOTE) further improves the detection of rare fraudulent cases. Adaptive learning capabilities also enable the system to respond dynamically to emerging fraud patterns in real time. This paper presents an adaptive AI-driven healthcare fraud detection framework designed for large-scale medical datasets. The proposed system leverages XGBoost-based classification along with multiple machine learning models to improve detection accuracy while maintaining computational efficiency. Experimental evaluation demonstrates that the proposed approach outperforms conventional methods in terms of accuracy, recall, and overall reliability, making it suitable for real-world healthcare fraud detection applications

Zitieren

APA

Vijayprabakaran, K., Ganesan, R., Boopathi, S., & Jayaraj, A. (2026). An Adaptive Machine Learning System for Fraud Detection in Healthcare Data. International Journal of Engineering & Extended Technologies Research, 08(02). https://doi.org/10.15662/ijeetr.2026.0802227

Vancouver

Vijayprabakaran K, Ganesan R, Boopathi S, Jayaraj A. An Adaptive Machine Learning System for Fraud Detection in Healthcare Data. International Journal of Engineering & Extended Technologies Research. 2026;08(02). doi:10.15662/ijeetr.2026.0802227

BibTeX
@article{Vijayprabakaran2026,
  author = {Vijayprabakaran, K. and Ganesan, R. and Boopathi, S. and Jayaraj, A.Adharsh},
  title = {An Adaptive Machine Learning System for Fraud Detection in Healthcare Data},
  journal = {International Journal of Engineering & Extended Technologies Research},
  year = {2026},
  volume = {08},
  number = {02},
  doi = {10.15662/ijeetr.2026.0802227}
}
Kostenlos starten →