Published on: April 2026
PUBLIC HEALTH AI ASSISTANT A RETRIEVAL-AUGMENTED GENERATION (RAG) FRAMEWORK TO DELIVER INTELLIGENT, MULTILINGUAL, AND ACCESSIBLE HEALTH CARE INFORMATION
Milan Kumar Shoaib Ahmad
Article Status
Available Documents
Abstract
Methodology: The proposed system combines a RAG and multilingual neural machine translation using the corpora produced by both the WHO and MoHFW.
Results: The results indicate that the RAG system was capable of providing end-to-end responses in approximately 1.8 seconds; retrieval latency was <20 ms, and hallucinations decreased from 38.7% to 9.1%. The capacity for operationalisation in multiple languages across several important Indian languages has been confirmed through real-world deployment on Hugging Face Spaces.
Conclusion: The findings demonstrate that deploying based multilingual LLMs can produce reliable and equitable communication about public health on a very large scale. Follow up investigations will focus on providing voice interfaces, conducting clinical trials, and establishing AWS/GCP cloud scalability.
Keywords: NLLB-200; SentenceTransformers; WHO; MoHFW India; Retrieval-Augmented Generation; LLM; Public Health AI; Multilingual NLP; Healthcare Chatbot
How to Cite this Paper
Kumar, M. & Ahmad, S. (2026). Public Health AI Assistant A Retrieval-Augmented Generation (RAG) Framework to Deliver Intelligent, Multilingual, and Accessible Health Care Information. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(04). https://doi.org/10.55041/ijcope.v2i4.132
Kumar, Milan, and Shoaib Ahmad. "Public Health AI Assistant A Retrieval-Augmented Generation (RAG) Framework to Deliver Intelligent, Multilingual, and Accessible Health Care Information." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 04, 2026, pp. . doi:https://doi.org/10.55041/ijcope.v2i4.132.
Kumar, Milan, and Shoaib Ahmad. "Public Health AI Assistant A Retrieval-Augmented Generation (RAG) Framework to Deliver Intelligent, Multilingual, and Accessible Health Care Information." International Journal of Creative and Open Research in Engineering and Management 02, no. 04 (2026). https://doi.org/https://doi.org/10.55041/ijcope.v2i4.132.
Search & Index
References
[1] World Health Organization. (2023). World Health Statistics 2023: Monitoring Health for the SDGs. WHO Press.[2] Ministry of Health and Family Welfare, Government of India. (2023). National Health Profile 2023. CBHI.
[3] Ji, Z., Lee, N., Frieske, R., et al. (2023). Survey of Hallucinations in Natural Language Generation. ACM Computing Surveys, 55(12), 1–38.
[4] Lewis, P., Perez, E., Piktus, A., et al. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. NeurIPS 2020. arXiv:2005.11401.
[5] Gao, Y., Xiong, Y., et al. (2024). Retrieval-Augmented Generation for LLMs: A Survey. arXiv:2312.10997.
[6] Siriwardhana, S., et al. (2023). Improving Domain Adaptation of RAG Models for Open-Domain QA. Trans. ACL, 11, 1–18.
[7] Bedi, S., Liu, Y., et al. (2025). Systematic Review of RAG in Healthcare AI. AI, 6(9), 226. https://doi.org/10.3390/ai6090226
[8] Xiong, G., Jin, Q., Lu, Z., & Zhang, A. (2024). Benchmarking RAG for Medicine. Findings of ACL 2024. PMC12157099.
[9] Abbasian, M., et al. (2025). RAGMed: Conversational Medical AI Using RAG. AI, 6(10), 240. https://doi.org/10.3390/ai6100240
[10] Yunxiang, L. et al. (2024). RAG for Reliable Healthcare AI. npj Health Systems, 1, 4. https://doi.org/10.1038/s44401-024-00004-1
Ethical Compliance & Review Process
- •All submissions are screened under plagiarism detection.
- •Review follows editorial policy.
- •Authors retain copyright.
- •Peer Review Type: Double-Blind Peer Review
- •Published on: Apr 08 2026
This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.