An Intelligent Medicine Recommendation System Using NLP, BERT, and Medical Knowledge Graph

Healthcare systems generate large volumes of unstructured data such as patient reviews, prescriptions, and clinical notes, making it challenging to extract meaningful insights for decision-making. This paper proposes a medicine recommendation system using Natural Language Processing (NLP) combined with advanced deep learning techniques to improve accuracy and reliability. The system utilizes Bidirectional Encoder Representations from Transformers (BERT) to perform context-aware sentiment analysis of patient reviews, enabling better understanding of drug effectiveness and side effects. Additionally, a medical knowledge graph is integrated to ensure clinically safe recommendations by validating drug–disease relationships and identifying contraindications.
To enhance usability, the system incorporates personalization based on patient-specific factors such as age, medical history, and allergies. The proposed model follows a structured pipeline including data preprocessing, feature extraction, sentiment analysis, safety validation, and recommendation generation. Experimental evaluation demonstrates that the system outperforms traditional machine learning approaches in terms of accuracy, precision, and recommendation quality.
The proposed approach provides a reliable, efficient, and scalable solution for intelligent medicine recommendation, with potential applications in telemedicine and digital healthcare systems.

NA

1. G. V. R. Reddy, M. Y., and T. B. Reddy, “Transformer-Based Healthcare Recommendation Systems,” Computer Research and Development, 2026. Available: https://journalcrd.org/wp-content/uploads/3-CRD3442.pdf [Google Scholar] [Crossref]

2. J. Jayapradha et al., “Treatment Recommendation Using BERT Personalization (PharmaBERT),” 2024. Available: https://journals.mmupress.com/index.php/jiwe/article/view/1041 [Google Scholar] [Crossref]

3. E. Hassan et al., “Optimizing Disease Prediction Using BERT and Deep Learning,” Scientific Reports, 2024. Available: https://www.nature.com/articles/s41598-024-51615-5 [Google Scholar] [Crossref]

4. X. Zhang et al., “Health Recommender Systems in Healthcare: A Review,” 2023. Available: https://journals.lww.com/inr/fulltext/2023/02000/the_application_of_health_recommender_systems.7.aspx [Google Scholar] [Crossref]

5. S. Lee et al., “Clinical Decision Transformer for Treatment Recommendation,” 2023. Available: https://arxiv.org/abs/2302.00612 [Google Scholar] [Crossref]

6. M. Nguyen et al., “ALGNet: Graph-Based Medical Recommendation System,” 2023. Available: https://arxiv.org/abs/2312.08377 [Google Scholar] [Crossref]

7. S. Reddy and M. Nair, “AI-Based Healthcare Systems Using NLP,” IEEE Access, 2022. Available: https://ieeexplore.ieee.org/document/9775318 [Google Scholar] [Crossref]

8. S. Wang et al., “Clinical Information Extraction Using BERT,” 2019. Available: https://arxiv.org/abs/1904.03323 [Google Scholar] [Crossref]

9. J. Lee et al., “BioBERT: A Pre-trained Biomedical Language Representation Model,” 2020. Available: https://arxiv.org/abs/1901.08746 [Google Scholar] [Crossref]

10. K. Huang et al., “ClinicalBERT: Modeling Clinical Notes Using BERT,” 2019. Available: https://arxiv.org/abs/1904.05342 [Google Scholar] [Crossref]

11. K. Liang et al., “Medical Knowledge Assisted Models for Healthcare NLP,” 2023. Available: https://arxiv.org/abs/2312.02496 [Google Scholar] [Crossref]

12. F. Rotmensch et al., “Learning a Health Knowledge Graph from EMR Data,” Scientific Reports, 2017. Available: https://www.nature.com/articles/s41598-017-05778-z [Google Scholar] [Crossref]

13. S. Zhang et al., “Deep Learning-Based Recommender Systems: A Survey,” ACM Computing Surveys, 2019. Available: https://arxiv.org/abs/1707.07435 [Google Scholar] [Crossref]

14. G. Adomavicius and A. Tuzhilin, “Toward the Next Generation of Recommender Systems,” IEEE Transactions on Knowledge and Data Engineering, 2005. Available: https://ieeexplore.ieee.org/document/1423975 [Google Scholar] [Crossref]

15. Y. Koren et al., “Matrix Factorization Techniques for Recommender Systems,” IEEE Computer, 2009. Available: https://ieeexplore.ieee.org/document/5197422 [Google Scholar] [Crossref]

16. H. Wang et al., “Knowledge Graph Convolutional Networks for Recommender Systems,” 2019. Available: https://arxiv.org/abs/1904.12575 [Google Scholar] [Crossref]

17. S. Min et al., “Knowledge Graphs for NLP: A Survey,” 2020. Available: https://arxiv.org/abs/2003.02320 [Google Scholar] [Crossref]

18. Q. Liu et al., “LLM-Based Medication Recommendation Model,” 2024. Available: https://arxiv.org/abs/2402.02803 [Google Scholar] [Crossref]

19. “A Comprehensive Survey of Recommender Systems (2017–2024),” 2025. Available: https://arxiv.org/html/2407.13699v4 [Google Scholar] [Crossref]

20. D. Rajkomar et al., “Machine Learning in Medicine,” New England Journal of Medicine, 2019. Available: https://www.nejm.org/doi/full/10.1056/NEJMra1814259 [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet