Authors : Pratik Sangde; Rohit Kachroo; Shrikant Shengule; Anish Pandita; Sachin Shelke

Volume/Issue : Volume 10 - 2025, Issue 12 - December

Google Scholar : https://tinyurl.com/mrxnfwr8

Scribd : https://tinyurl.com/5xc4uzhf

DOI : https://doi.org/10.38124/ijisrt/25dec1652

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Healthcare research today operates within an en- vironment rich in complex and interconnected data sources, ranging from Electronic Health Records (EHRs) and diagnostic imaging to pharmacological studies and clinical trial outputs. Traditional retrieval systems and general-purpose Large Lan- guage Models (LLMs), though effective in surface- level analysis, often fail to capture the deep semantic relationships that un- derpin this data. Consequently, they generate responses lacking verifiable evidence and contextual accuracy. To address these challenges, this paper surveys the emerging paradigm of Retrieval-Augmented Generation (RAG) enhanced by Knowledge Graphs (KGs), forming a bridge between sym- bolic reasoning and neural generation. The proposed study establishes a taxonomy of healthcare Question-Answering (QA) frameworks—spanning relational databases, vector embedding retrieval, and hybridKG-RAGarchitectures—while emphasizing their relevance in clinical information systems. Furthermore, the paper outlines the necessity of such in- tegration for improving medical decision support, focusing on the dynamic translation of natural language into formal graph queries, scalable knowledge maintenance, and multi-hop infer- encing. By systematically reviewing technological advances and identifying key implementation challenges, this survey provides a structured roadmap for developing reliable, explainable, and ethically aligned AI systems in healthcare.

Keywords : Retrieval-Augmented Generation, Knowledge Graphs, Graph Database, Natural Language Processing, Large Language Models, Neo4j, Healthcare AI.

References :

1. A. E. W. Johnson, T. J. Pollard, L. Shen, et al., “MIMIC-IV: A Freely Accessible Electronic Health Record Dataset,” Scientific Data, vol. 10, 2023.
2. X. Huang, S. Zhang, and Y. Zhou, “A Knowledge Graph-Based Question Answering Method for the Medical Domain,” BMC Medical Informatics and Decision Making, vol. 21, no. 1, 2021.
3. G. Gao, L. Li, and H. Chen, “MedKGQA: Graph-Based Neural Question Answering in Biomedicine,” IEEE Access, 2022.
4. S. Lee, “Real-Time Graph Analytics in TigerGraph,” in Proc. Graph Tech Conf., 2022.
5. R. Yang, X. Zhao, and Y. Wang, “KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs,” in Workshop on Biomedical NLP, 2024.
6. R. Rossi, L. Brown, and A. Kim, “Temporal KG Models for Evolving Biomedical Knowledge,” Journal of Biomedical Informatics, 2023.
7. L. Brown, J. Li, and S. Kumar, “Knowledge Graph-Augmented RAG for Biomedical QA,” in Proc. BioNLP, 2024.
8. N. Kotonya and F. Toni, “Explainable Automated Fact-Checking for Public Health Claims,” arXiv preprint arXiv:2010.09926, 2020.
9. S. Sahu, V. Ramesh, and P. Singh, “Explainability Metrics for KG-Based QA,” in AAAI Workshop on Explainable AI (XAI), 2023.
10. M. Jin, L. Huang, and X. Zhou, “RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation Systems,” arXiv preprint arXiv:2404.12457, 2024.
11. X. Zhao, H. Chen, and R. Yang, “MedRAG: Hybrid KG-RAG for Healthcare Copilot,” arXiv preprint arXiv:2502.04413, 2025.
12. E. Dai, Z. Wang, and F. Zhou, “FakeHealth: A Knowledge Graph for Health Misinformation Detection,” arXiv preprint arXiv:2005.03991, 2020.
13. Y. Zhang, A. Wang, and P. Liu, “DDXPlus: A Differential Diagnosis Dataset for Clinical Reasoning,” arXiv preprint arXiv:2005.13756, 2021.
14. J. Kim, M. Li, and C. Zhao, “Composite Evaluation Metrics for KG- RAG Systems,” in ACL Findings, 2024.
15. L. Chen, M. Xu, and Z. Huang, “BioMedGraphQA: Graph-Attention Transformer for Biomedical Question Answering,” IEEE Transactions on Neural Networks and Learning Systems, 2023.
16. L. Chen, X. Han, and Y. Zhou, “Knowledge-Graph-Enabled Biomedical Entity Linking for Context-Aware Inference,” Journal of Biomedical Informatics, 2023.
17. H. Wang, C. Liu, and S. Zhang, “Text-to-GraphQL: Bridging Natural Language and Graph Query Generation for Biomedical QA,” in Proc. IEEE International Conference on Data Mining, 2023.
18. A. Sharma, S. R. Patel, and R. Verma, “An Online Medical Chatbot System Using Knowledge Graph and NLP Integration,” Journal of Intelligent Systems, 2023.
19. E. Dai, F. Luo, and C. Huang, “Knowledge Graph-Assisted End-to-End Medical Dialog Generation,” IEEE Access, 2023.
20. X. Zhao, M. Jin, and Y. Yang, “Knowledge-Empowered Dynamic Graph Networks for Biomedical QA,” IEEE Transactions on Artificial Intelligence, 2023.
21. Y. Su, P. Zhang, and R. Wang, “KGARevion: Iterative Error Revision for Medical Knowledge Graph Question Answering,” EmergentMind, 2024.
22. European Commission, “General Data Protection Regulation (GDPR) — 2024 Revision Update,” Official Journal of the European Union, 2024.
23. T. Jones, A. Patel, and M. Garcia, “Graph Database Benchmarking for Enterprise Applications,” IEEE Transactions on Big Data, 2023.
24. S. Lee, “Real-Time Graph Analytics in TigerGraph,” in Graph Tech Conference, 2022.
25. S. Sahu, P. Singh, and A. Verma, “Explainability Metrics for KG-Based QA Systems,” AAAI Workshop on Explainable AI, 2023.
26. L. Brown, T. Smith, and A. Kim, “Knowledge Graph-Augmented Retrieval-Augmented Generation for Biomedical QA,” in Proceedings of BioNLP, 2024.
27. Y. Wu, L. Li, and X. Chen, “MedC-K: KG-Augmented Models for Clinical QA,” in Proc. BioNLP, 2023.
28. X. Zhao, R. Yang, and H. Chen, “MedRAG: Hybrid Knowledge Graph–RAG Architecture for Clinical Applications,” arXiv preprint arXiv:2502.04413, 2025.
29. R. Rossi, L. Brown, and A. Kim, “Temporal Knowledge Graph Models for Biomedical Evolution,” Journal of Biomedical Informatics, 2023.