EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

AI-Driven Fraud, Waste, and Abuse Detection in Medicaid Claims Using Graph Neural Networks

Arpit Gupta

Journal of Advanced Scientific Research · 17.03.2026 · 17 (03) · 8-21

DOI: 10.55218/jasr.2026170302 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Advanced Scientific Research, online erschienen am 17.03.2026. Verfasst von Arpit Gupta. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Medicaid is one of the largest public health insurance programs in the United States, processing millions of claims annually and managing billionsof dollars in healthcare expenditures. The scale and complexity of its multi-entity billing ecosystem make it highly susceptible to fraud, waste,and abuse, including phantom billing, upcoding, identity misuse, and coordinated provider networks. Traditional detection approaches rely onrule-based audits and tabular machine learning models that analyze claims as independent records. These methods often fail to capture hiddenrelational patterns and interconnected fraud schemes embedded within provider–patient–facility networks.This study proposes an AI-driven fraud detection framework using Graph Neural Networks to model Medicaid claims as a heterogeneous graphstructure. Providers, beneficiaries, claims, and facilities are represented as nodes, while billing interactions, referrals, and shared identifiers formedges. The model leverages graph-based message passing to capture relational dependencies and detect coordinated fraud behavior. To addressclass imbalance, imbalance-aware learning strategies are incorporated during training. Baseline comparisons include conventional machinelearning classifiers and network embedding techniques.Experimental results demonstrate significant improvements in precision, recall, F1-score, and ROC-AUC compared to traditional approaches.The proposed framework also integrates explainability mechanisms to identify influential subgraphs and high-risk billing patterns, supportingtransparency in fraud investigations. Overall, this research presents a scalable, interpretable, and policy-relevant solution for enhancing Medicaidprogram integrity.

Zitieren

APA

Gupta, A. (2026). AI-Driven Fraud, Waste, and Abuse Detection in Medicaid Claims Using Graph Neural Networks. Journal of Advanced Scientific Research, 17(03), 8-21. https://doi.org/10.55218/jasr.2026170302

Vancouver

Gupta A. AI-Driven Fraud, Waste, and Abuse Detection in Medicaid Claims Using Graph Neural Networks. Journal of Advanced Scientific Research. 2026;17(03):8-21. doi:10.55218/jasr.2026170302

BibTeX
@article{Gupta2026,
  author = {Gupta, Arpit},
  title = {AI-Driven Fraud, Waste, and Abuse Detection in Medicaid Claims Using Graph Neural Networks},
  journal = {Journal of Advanced Scientific Research},
  year = {2026},
  volume = {17},
  number = {03},
  pages = {8--21},
  doi = {10.55218/jasr.2026170302}
}
Kostenlos starten →