EUVIMEDEUVIMED entdecken
Crossref

Automated Health Insurance Claim Processing Using Flask Microservices, Vector-Augmented Language Models

Sameer Singh, Vandana Swami, Rajendra Singh

International Journal of Advanced Research in Science Communication and Technology · 12.05.2026 · 178

DOI: 10.48175/ijarsct-35219 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Advanced Research in Science Communication and Technology, online erschienen am 12.05.2026. Verfasst von Sameer Singh und 2 weiteren Autor:innen. Die Arbeit nennt 14 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The deployment of artificial intelligence systems in production cloud environments presents significant engineering challenges including memory management, latency optimization, and infrastructure cost minimization. Health insurance claim processing systems that incorporate large language models, vector databases, and optical character recognition pipelines are particularly demanding in terms of computational resources, making cost-effective cloud deployment a critical research problem. This paper presents the design, implementation, and performance evaluation of a scalable cloud-based automated health insurance claim processing system built on Flask microservices architecture and Docker containerization, deployed on Hugging Face Spaces at zero infrastructure cost. The system integrates a FAISS-powered vector retrieval pipeline for insurance policy handbook search, EasyOCR for medical bill digitization, and the Groq LLaMA 3.3 70B large language model for claim evaluation and executive report generation. A key architectural contribution is a three-stage claim validation pipeline that minimizes expensive language model API invocations by resolving obvious rejection cases at lightweight validation layers before escalating to language model inference. Performance benchmarking demonstrates median end-to-end processing latency of 3.2 seconds for claims requiring full AI evaluation and sub-10-millisecond processing for claims resolved at validation layers one and two. The deployed system sustains concurrent request handling without resource exhaustion on a free-tier instance providing 16 gigabytes of RAM. Comparative analysis against alternative deployment platforms confirms that Hugging Face Spaces provides the optimal balance of available memory, deployment simplicity, and zero operational cost for AI-intensive applications of this class..

Zitieren

APA

Singh, S., Swami, V., & Singh, R. (2026). Automated Health Insurance Claim Processing Using Flask Microservices, Vector-Augmented Language Models. International Journal of Advanced Research in Science Communication and Technology, 178. https://doi.org/10.48175/ijarsct-35219

Vancouver

Singh S, Swami V, Singh R. Automated Health Insurance Claim Processing Using Flask Microservices, Vector-Augmented Language Models. International Journal of Advanced Research in Science Communication and Technology. 2026:178. doi:10.48175/ijarsct-35219

BibTeX
@article{Singh2026,
  author = {Singh, Sameer and Swami, Vandana and Singh, Rajendra},
  title = {Automated Health Insurance Claim Processing Using Flask Microservices, Vector-Augmented Language Models},
  journal = {International Journal of Advanced Research in Science Communication and Technology},
  year = {2026},
  pages = {178},
  doi = {10.48175/ijarsct-35219}
}
Kostenlos starten →