Small Language Models for Drug-Drug Interaction Extraction from Biomedical Text: A Systematic Literature Review
DOI:
https://doi.org/10.63158/journalisi.v8i1.1430Keywords:
Drug-Drug Interaction, Biomedical Text Mining, Small Language Models, Pharmacovigilance, Clinical NLPAbstract
Drug–drug interaction (DDI) extraction from biomedical text is central to pharmacovigilance but remains challenging in resource-constrained clinical environments. While large language models have shown promise, their computational cost and deployment complexity limit practical adoption. This study systematically reviews the role of small language models (SLMs) for DDI extraction and examines their effectiveness, efficiency, and deployability. A systematic literature review was conducted following PRISMA guidelines, covering empirical studies published between 2020 and 2025 in PubMed, IEEE Xplore, ACM and SpringerLink. Eligible studies were analysed with respect to model architectures, datasets, evaluation metrics, and deployment considerations. Quality assessment was applied to ensure methodological robustness. The synthesis indicates that SLM-based approaches, including CNN-, LSTM-, and lightweight transformer models, can achieve competitive F1-scores on benchmark DDI datasets while requiring substantially fewer computational resources than large language models. However, performance varies across datasets, and real-world clinical evaluations remain limited. These findings support the feasibility of deploying SLM-based DDI extraction systems in resource-constrained clinical and pharmacovigilance settings and provide a baseline for future benchmarking and comparative research in clinical natural language processing.
Downloads
References
[1] T. N. G. de Andrade Santos et al., “Prevalence of clinically manifested drug interactions in hospitalized patients: A systematic review and meta-analysis,” PLoS One, vol. 15, no. 7, 2020, doi: 10.1371/journal.pone.0235353.
[2] J. E. Hughes, C. Waldron, K. E. Bennett, and C. Cahir, “Prevalence of Drug–Drug Interactions in Older Community-Dwelling Individuals: A Systematic Review and Meta-analysis,” Drugs and Aging, vol. 40, no. 2, pp. 117–134, 2023, doi: 10.1007/s40266-022-01001-5.
[3] X. Li, Z. Xiong, W. Zhang, and S. Liu, “Deep learning for drug-drug interaction prediction: A comprehensive review,” Quant. Biol., vol. 12, no. 1, pp. 30–52, Mar. 2024, doi: 10.1002/qub2.32.
[4] Y. Xia, A. Xiong, Z. Zhang, Q. Zou, and F. Cui, “A comprehensive review of deep learning-based approaches for drug-drug interaction prediction,” Brief. Funct. Genomics, vol. 24, 2025, doi: 10.1093/bfgp/elae052.
[5] H. Luo et al., “Drug-drug interactions prediction based on deep learning and knowledge graph: A review,” iScience, vol. 27, no. 3, p. 109148, 2024, doi: 10.1016/j.isci.2024.109148.
[6] F.-I. Gheorghita, V.-I. Bocanet, and L. B. Iantovics, “Machine learning-based drug-drug interaction prediction: a critical review of models, limitations, and data challenges,” Front. Pharmacol., vol. 16, no. July, pp. 1–25, 2025, doi: 10.3389/fphar.2025.1632775.
[7] G. L. Swathi Mirthika and B. Sivakumar, “A Systematic Review on Drug Interaction Prediction Using Various Methods to Reduce Adverse Effects,” Int. J. Inf. Syst. Soc. Chang., vol. 14, no. 1, pp. 1–8, 2023, doi: 10.4018/ijissc.329233.
[8] K. Soni Sharmila, S. Thanga Revathi, and P. Kiran Sree, “A Systematic Review on Drug-to-Drug Interaction Prediction and Cryptographic Mechanism for Secure Drug Discovery Using AI Techniques,” Int. J. Artif. Intell. Tools, vol. 33, no. 08, p. 2450003, Jul. 2024, doi: 10.1142/S0218213024500039.
[9] R. Huang, W. Xu, X. Qi, and Y. Wang, “Protein-Protein Interaction Extraction based on Multi-feature Fusion and Entity Enhancement,” in Proceedings of the 4th International Conference on Biomedical and Intelligent Systems, in IC-BIS ’25. New York, NY, USA: Association for Computing Machinery, 2025, pp. 229–234. doi: 10.1145/3745034.3745070.
[10] C. Yu et al., “Drug–drug interaction extraction based on multimodal feature fusion by Transformer and BiGRU,” Front. Drug Discov., vol. 4, no. October, pp. 1–12, 2024, doi: 10.3389/fddsv.2024.1460672.
[11] H. Mondal et al., “A systematic mapping review on the capability of large language models in drug-drug interaction analysis,” Expert Rev. Clin. Pharmacol., vol. 18, no. 9, pp. 683–690, Sep. 2025, doi: 10.1080/17512433.2025.2568090.
[12] F. Busch et al., “Current applications and challenges in large language models for patient care: a systematic review,” Commun. Med., vol. 5, no. 1, Dec. 2025, doi: 10.1038/s43856-024-00717-2.
[13] X. H. Liu, Z. H. Lu, T. Wang, and F. Liu, “Large language models facilitating modern molecular biology and novel drug development,” 2024, Frontiers Media SA. doi: 10.3389/fphar.2024.1458739.
[14] N. H. M. S. E. S. M. Mysara, “A comprehensive landscape of AI applications in broad-spectrum drug interaction prediction: a systematic review,” J. Cheminform., 2025, doi: 10.1186/s13321-025-01093-2.
[15] A. Z. Al Meslamani and A. Abou Hajal, “Language models for drug-drug interactions: current applications, pitfalls, and future directions.,” Expert Opin. Drug Metab. Toxicol., vol. 21, no. 9, pp. 1083–1102, Sep. 2025, doi: 10.1080/17425255.2025.2551724.
[16] A. Liberati et al., “The PRISMA statement for reporting systematic reviews and meta-analyses of studies that evaluate healthcare interventions: explanation and elaboration.,” BMJ, vol. 339, 2009, doi: 10.1136/bmj.b2700.
[17] S. E. Group, “Guidelines for performing Systematic Literature Reviews in Software Engineering,” 2007.
[18] D. Moher, A. Liberati, J. Tetzlaff, and D. G. Altman, “Preferred reporting items for systematic reviews and meta-analyses: The PRISMA statement,” BMJ, vol. 339, no. 7716, pp. 332–336, 2009, doi: 10.1136/bmj.b2535.
[19] A. Ibrahim, A. Hosseini, S. Ibrahim, A. Sattar, and A. Serag, “D3: A Small Language Model for Drug-Drug Interaction prediction and comparison with Large Language Models,” Mach. Learn. with Appl., vol. 20, no. April, p. 100658, 2025, doi: 10.1016/j.mlwa.2025.100658.
[20] J. Machado, C. Rodrigues, R. Sousa, and L. M. Gomes, “Drug–drug interaction extraction-based system: An natural language processing approach,” Expert Syst., vol. 42, no. 1, pp. 1–12, 2025, doi: 10.1111/exsy.13303.
[21] M. T. Tahir, M. Ibrahim, N. Sarwar, A. Irshad, and G. Atteia, “Enhanced drug-drug interaction extraction from biomedical text using deep learning-based sentence representations,” Sci. Rep., vol. 15, no. 1, pp. 1–15, 2025, doi: 10.1038/s41598-025-21782-0.
[22] S. S. Roy and R. E. Mercer, “Extracting Drug-Drug and Protein-Protein Interactions from Text Using a Continuous Update of Tree-Transformers,” Proc. Annu. Meet. Assoc. Comput. Linguist., pp. 280–291, 2023, doi: 10.18653/v1/2023.bionlp-1.25.
[23] B. H. Tran, H. M. Hoang, B. N. Nguyen, D. C. Can, and H. Q. Le, “A multifaceted approach to drug–drug interaction extraction with fusion strategies,” J. Biomed. Inform., vol. 169, no. May, p. 104874, 2025, doi: 10.1016/j.jbi.2025.104874.
[24] L. Xiao, X. Wang, Z. Zhang, Y. Yao, and W. Zhu, “DyNAS-DDI: Dynamic Pairwise Architecture Search for Generalizable Drug-Drug Interaction LLM,” in Proceedings of the 33rd ACM International Conference on Multimedia, in MM ’25. New York, NY, USA: Association for Computing Machinery, 2025, pp. 2216–2225. doi: 10.1145/3746027.3755791.
[25] Q. Wen, J. Li, C. Zhang, and Y. Ye, “A Multi-Modality Framework for Drug-Drug Interaction Prediction by Harnessing Multi-source Data,” in Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, in CIKM ’23. New York, NY, USA: Association for Computing Machinery, 2023, pp. 2696–2705. doi: 10.1145/3583780.3614765.
[26] M. S. Malik, S. Jawad, S. A. Moqurrab, and G. Srivastava, “DeepMedFeature: An Accurate Feature Extraction and Drug-Drug Interaction Model for Clinical Text in Medical Informatics,” ACM Trans. Asian Low-Resour. Lang. Inf. Process., Mar. 2024, doi: 10.1145/3651159.
[27] Y. Jia, Z. Yuan, H. Wang, Y. Gong, H. Yang, and Z.-L. Xiang, “BBL-GAT: A Novel Method for Drug-Drug Interaction Extraction From Biomedical Literature,” IEEE Access, vol. 12, pp. 134167–134184, 2024, doi: 10.1109/ACCESS.2024.3462101.
[28] T. T. Datta, P. C. Shill, and Z. Al Nazi, “BERT-D2: Drug-Drug Interaction Extraction using BERT,” in 2022 International Conference for Advancement in Technology (ICONAT), 2022, pp. 1–6. doi: 10.1109/ICONAT53423.2022.9725979.
[29] M. A. Parameswara and R. Mandala, ““BIOGAN-BERT: BioGPT-2 Fine Tuned and GAN-BERT for Extracting Drug Interaction Based on Biomedical Texts.,” in 2024 11th International Conference on Advanced Informatics: Concept, Theory and Application (ICAICTA), 2024, pp. 1–6. doi: 10.1109/ICAICTA63815.2024.10762980.
[30] M. Kafikang and A. Hendawi, “Drug-Drug Interaction Extraction from Biomedical Text using Relation BioBERT with BLSTM,” MAKE, vol. 5, no. 2, Jun. 2023, doi: 10.1101/2022.08.31.506076.
[31] D. P. Nguyen and T. Ho, “Drug-Drug Interaction Extraction from Biomedical Texts via Relation BERT,” 2020 RIVF Int. Conf. Comput. Commun. Technol., vol. null, pp. 1–7, 2020, doi: 10.1109/RIVF48685.2020.9140783.
[32] A. Wen, X. Sun, K. Yu, Y. Wu, J. Zhang, and Z. Yuan, “Drug-Drug Interaction Extraction using Pre-training Model of Enhanced Entity Information,” in 2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics), 2020, pp. 527–532. doi: 10.1109/iThings-GreenCom-CPSCom-SmartData-Cybermatics50389.2020.00094.
[33] X. Jin, X. Sun, J. Chen, and R. Sutcliffe, “Extracting Drug-drug Interactions from Biomedical Texts using Knowledge Graph Embeddings and Multi-focal Loss,” in Proceedings of the 31st ACM International Conference on Information & Knowledge Management, in CIKM ’22. New York, NY, USA: Association for Computing Machinery, 2022, pp. 884–893. doi: 10.1145/3511808.3557318.
[34] Y. Zhu, L. Li, H. Lu, A. Zhou, and X. Qin, “Extracting drug-drug interactions from texts with BioBERT and multiple entity-aware attentions,” J. Biomed. Inform., vol. null, p. 103451, 2020, doi: 10.1016/j.jbi.2020.103451.
[35] I.-F. Gheorghita, V. Bocăneț, and L. B. Iantovics, “Fine-Tuning BiomedBERT with LoRA and Pseudo-Labeling for Accurate Drug–Drug Interactions Classification,” Appl. Sci., vol. null, p. null, 2025, doi: 10.3390/app15158653.
[36] S. Jung and S. Yoo, “Interpretable prediction of drug-drug interactions via text embedding in biomedical literature.,” Comput. Biol. Med., vol. 185, p. 109496, Feb. 2025, doi: 10.1016/j.compbiomed.2024.109496.
[37] P. Su and K. Vijay-Shanker, “Investigation of BERT Model on Biomedical Relation Extraction Based on Revised Fine-tuning Mechanism,” in 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2020, pp. 2522–2529. doi: 10.1109/BIBM49941.2020.9313160.
[38] P. S. Vijay-Shanker, “Investigation of improving the pre-training and fine-tuning of BERT model for biomedical relation extraction,” BMC Bioinformatics, 2022, doi: 10.1186/s12859-022-04642-w.
[39] Zhu Yuan, Shuailiang Zhang, Huiyun Zhang, A. Ping Xie, and Yaxun Jia, “Optimized Drug-Drug Interaction Extraction With BioGPT and Focal Loss-Based Attention,” IEEE J. Biomed. Heal. Informatics, vol. null, no. 6, p. null, Jun. 2025, doi: 10.1109/JBHI.2025.3540861.
[40] J. Podichetty, S. C. Ma, and K. Romero, “Optimizing Drug Development : Assessing Small Language Models for Efficient Drug-Drug Interaction Data Extraction,” p. 881, 2024.
[41] S. Z. Y. Zhang, “SCATrans: semantic cross-attention transformer for drug–drug interaction predication through multimodal biomedical data,” BMC Bioinformatics, 2025, doi: 10.1186/s12859-025-06165-6.
[42] Y. Shi, M. He, J. Chen, F. Han, Y. C. Id, and Y. Cai, “SubGE-DDI: A new prediction model for drug-drug interaction established through biomedical texts and drug-pairs knowledge subgraph enhancement,” PLOS Comput. Biol., vol. 20, p. null, 2024, doi: 10.1371/journal.pcbi.1011989.
[43] Z. Zhao et al., “TL-BERT: A Novel Biomedical Relation Extraction Approach,” in 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2021, pp. 797–800. doi: 10.1109/BIBM52615.2021.9669869.
[44] D. Zaikis and I. Vlahavas, “TP-DDI: Transformer-based pipeline for the extraction of Drug-Drug Interactions.,” Artif. Intell. Med., vol. 119, p. 102153, Sep. 2021, doi: 10.1016/j.artmed.2021.102153.
[45] D. Zaikis and I. Vlahavas, “TransformDDI: The Transformer-Based Joint Multi-Task Model for End-to-End Drug-Drug Interaction Extraction,” IEEE J. Biomed. Heal. Informatics, vol. 29, no. 4, pp. 3045–3056, 2025, doi: 10.1109/JBHI.2024.3507738.
[46] D. Zaikis, S. Kokkas, and I. Vlahavas, “Transforming Drug-Drug Interaction Extraction from Biomedical Literature,” in Proceedings of the 12th Hellenic Conference on Artificial Intelligence, in SETN ’22. New York, NY, USA: Association for Computing Machinery, 2022. doi: 10.1145/3549737.3549753.
[47] A. K and J. T. Podichetty, “Optimizing Drug Development: Assessing Small Language Models for Efficient Drug-Drug Interaction Data Extraction,” Proc. Am. Conf. Pharmacometrics 2024, vol. null, p. null, doi: 10.70534/gwsf3516.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors Declaration
- The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
- The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
- If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
- The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights
