EUVIMEDEUVIMED entdecken
Crossref

AI-Driven Fraud Detection in Healthcare: Architecture, Implementation, and Impact

Sri Venkata Aravindbabu Malempati

Computer Fraud and Security · 04.04.2026 · 1010-1018

DOI: 10.52710/cfs.1013 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Fraud and Security, online erschienen am 04.04.2026. Verfasst von Sri Venkata Aravindbabu Malempati.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Healthcare fraud remains one of the most costly and structurally persistent threats confronting the United States healthcare system. It diverts immense resources away from legitimate care and erodes trust in the institutions involved. Furthermore, healthcare fraud has outstripped customary rule-based and manual audit processes both in velocity and complexity, and in the adaptive capacity of fraud networks. Artificial intelligence and machine learning-based systems have emerged as an alternative that can look at hundreds of variables across thousands of claims, identify anomalies in real time, and continuously learn as fraud schemes evolve. Technical architectures that include supervised ensemble models, unsupervised anomaly detectors, and graph network analyses have shown improved performance on insurer data. When data quality, algorithm fairness, model explainability, provider due process, and human intervention and monitoring are prioritized, AI-based fraud detection can add long-lasting value to patients, payers, and the healthcare system by recapturing payments to fraudsters and preventing future losses at scale.

Zitieren

APA

Malempati, S. V. A. (2026). AI-Driven Fraud Detection in Healthcare: Architecture, Implementation, and Impact. Computer Fraud and Security, 1010-1018. https://doi.org/10.52710/cfs.1013

Vancouver

Malempati SVA. AI-Driven Fraud Detection in Healthcare: Architecture, Implementation, and Impact. Computer Fraud and Security. 2026:1010-1018. doi:10.52710/cfs.1013

BibTeX
@article{Malempati2026,
  author = {Malempati, Sri Venkata Aravindbabu},
  title = {AI-Driven Fraud Detection in Healthcare: Architecture, Implementation, and Impact},
  journal = {Computer Fraud and Security},
  year = {2026},
  pages = {1010--1018},
  doi = {10.52710/cfs.1013}
}
Kostenlos starten →