International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | A Retrieval-Augmented Generation (RAG) Framework for Clinical Decision Support, Drug Interaction Detection & Prescription Safety |
|---|---|
| ABSTRACT | This project proposes a Retrieval-Augmented Generation (RAG) based healthcare assistant that intelligently combines trusted medical knowledge sources with advanced language models to provide accurate, reliable, and context-aware healthcare responses [11][13][16]. Traditional large language models (LLMs) often generate hallucinated or outdated medical information due to lack of real-time domain-specific grounding, which can be risky in healthcare applications [4][5]. To address this limitation, the proposed system introduces a retrieval mechanism that searches verified healthcare sources such as PubMed, DrugBank, clinical guidelines, and medical databases before generating responses [10][11]. User queries are processed using Natural Language Processing techniques such as intent detection, entity recognition, and semantic embedding search to retrieve the most relevant medical information [1][4][20]. The retrieved knowledge is then combined with a Large Language Model to generate structured, evidence-based, and explainable responses [11][12]. A validation layer is incorporated to verify drug interactions, dosage risks, outdated information, and safety concerns, thereby reducing hallucinations and improving trustworthiness [14][15]. The system also supports multilingual interaction in languages such as English, Hindi, Marathi, and Gujarati to improve accessibility [2] [8]. The system is implemented using Python, FastAPI/Flask, LangChain, vector databases such as FAISS or Pinecone, and backend databases such as MongoDB or PostgreSQL. It will be evaluated using healthcare question-answering benchmarks and retrieval performance metrics, demonstrating improved accuracy, reliability, and usability compared to traditional healthcare chatbot systems [6][11][17]. |
| TITLE | |
| AUTHOR | BHUMI KISHOR MAKDE, KETKI NARENDRA THAKRE, ABHYUDAYA AWARE, MD. SHAHANWAZ, DR. POORVA SABNIS Department of Computer Engineering, St. Vincent Pallotti College of Engineering and Technology, Nagpur, India Assistant Professor, Department of Computer Engineering, St. Vincent Pallotti College of Engineering and Technology, Nagpur, India |
| VOLUME | 186 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1407069 |
| pdf/69_A Retrieval-Augmented Generation (RAG) Framework for Clinical Decision Support, Drug Interaction Detection.pdf | |
| KEYWORDS | |
| References | [1] Yu Gu et al., “Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing, ” 2021. [2] Simran Khanuja et al., “MuRIL: Multilingual Representations for Indian Languages, ” 2021. [3] Alvin Rajkomar et al., “Scalable and Accurate Deep Learning with Electronic Health Records, ” npj Digital Medicine, 2018. [4] Jacob Devlin et al., “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, ” 2019. [5] Jinhyuk Lee et al., “BioBERT: a pre-trained biomedical language representation model, ” 2019. [6] D. Jin, E. Pan, N. Oufattole, W.-H. Weng, H. Fang, and P. Szolovits, “What Disease Does this Patient Have? A Largescale Open Domain Question Answering Dataset from Medical Exams, ” 2020. [7] Y. Wu, M. Schuster, Z. Chen, Q. V. Le, M. Norouzi, W. Macherey, et al., “Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation, ” 2016. [8] L. Xue, N. Constant, A. Roberts, M. Kale, R. Al-Rfou, A. Siddhant, et al., “mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer, ” 2021. [9] Z. Borsos, M. Mutný, M. Tagliasacchi, and A. Krause, “Data Summarization via Bilevel Optimization, ” 2021. [10] M. Kuhn, I. Letunic, L. J. Jensen, and P. Bork, “The SIDER Database of Drugs and Side Effects, ” Nucleic Acids Research, vol. 44, 2016. [11] F. Saidu and J. Wall, “Retrieval-Augmented Large Language Model for Clinical Decision Support with a Medical Knowledge Graph, ” Electronics, vol. 15, 2026. [12] D. S. W. Ting, J. C. L. Ong, L. Jin, et al., “Development and Testing of a Novel Large Language Model-Based Clinical Decision Support Systems for Medication Safety in 12 Clinical Specialties, ” 2024. [13] C. Huh, H. Hwang, J. H. Shin, et al., “PACE-RAG: Patient-Aware Contextual and Evidence-based Policy RAG for Clinical Drug Recommendation, ” arXiv preprint arXiv:2603.17356, 2026. [14] B. Yang, D. Song, Y. Li, and J. Wang, “Drug-drug interaction prediction of traditional Chinese medicine based on graph attention networks, ” Scientific Reports, vol. 15, 2025. [15] A. Alam, A. Saran, S. B. Sridhar, et al., “Artificial Intelligence in Drug Interaction Management: A Transformative Approach in Clinical Decision Support Systems, ” International Journal for Innovative Research in Multidisciplinary Field, vol. 11, no. 4, 2025 [16] Huh, C., et al., Policy-driven Prescription Refinement in RAG-based Clinical Systems, 2026. [17] E. Choi, M. T. Bahadori, A. Schuetz, W. F. Stewart, and J. Sun, “Doctor AI: Predicting clinical events via recurrent neural networks, ” Proceedings of Machine Learning for Healthcare, vol. 56, 2016. [18] A. Conneau, K. Khandelwal, N. Goyal, V. Chaudhary, G. Wenzek, F. Guzmán, E. Grave, M. Ott, L. Zettlemoyer, and V. Stoyanov, “Unsupervised cross-lingual representation learning at scale, ” arXiv preprint arXiv:1911.02116, 2020. [19] J. Xu, B. S. Glicksberg, C. Su, P. Walker, J. Bian, and F. Wang, “Federated learning for healthcare informatics, ” arXiv preprint arXiv:1911.06270, 2020. [20] N. Reimers and I. Gurevych, “Sentence-BERT: Sentence embeddings using Siamese BERT-networks, ” arXiv preprint arXiv:1908.10084, 2019. |
