Volume 12 • Issue 1 • PP: 11 – 17 • 2027
Comparative Explainable Machine Learning Framework for Multiclass Drug Classification
Open Access & Copyright
© 2027 The Author(s). Published by ASPG. This article is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
View PDF Abstract
Accurate drug classification is important for developing intelligent healthcare systems and supporting reliable medication-related decision-making. The relationships between patient characteristics and prescribed drug categories may be nonlinear and difficult to identify using conventional analytical procedures. This study presents a machine learning framework for multiclass drug classification using demographic and clinical patient attributes. The framework includes data cleaning, exploratory data analysis, numerical and categorical feature transformation, model training, comparative evaluation, and explainable artificial intelligence analysis. Nine classification models were investigated, including Random Forest, support vector machine, LightGBM, CatBoost, multilayer perceptron, one-dimensional convolutional neural network, long short-term memory network, gated recurrent unit network, and TabNet. The models were evaluated using accuracy, weighted precision, weighted recall, weighted F1-score, macro F1-score, and balanced accuracy. Random Forest achieved the best overall balance between predictive performance and interpretability, obtaining an accuracy of 97.50%, a macro F1-score of 98.51%, and a balanced accuracy of 98.18%. SHAP analysis identified the sodium-to-potassium ratio, blood-pressure categories, and age as the most influential variables affecting the classification decisions. The obtained results demonstrate that an explainable machine learning framework can provide accurate and transparent drug classification using a limited number of patient-related variables.
Keywords
References
[1] M. Picard, M. Leclercq, A. Bodein, M. P. Scott-Boyer, O. Perin, and A. Droit, “Improving drug repositioning with negative data labeling using large language models,” Journal of Cheminformatics, vol. 17, no. 1, p. 16, 2025.
[2] R. Tan, H. Hua, S. Zhou, Z. Yang, C. Yang, G. Huang, J. Zeng, and J. Zhao, “Current landscape of innovative drug development and regulatory support in china,” Signal Transduction and Targeted Therapy, vol. 10, no. 1, p. 220, 2025.
[3] K. Zhang, X. Yang, Y. Wang, Y. Yu, N. Huang, G. Li, X. Li, J. C. Wu, and S. Yang, “Artificial intelligence in drug development,” Nature Medicine, vol. 31, no. 1, pp. 45–59, 2025.
[4] A. Kumar, S. K. Gupta, and S. Kim, “AI-driven drug discovery using a context-aware hybrid model to optimize drug–target interactions,” Scientific Reports, vol. 15, no. 1, p. 35719, 2025.
[5] R. Rodríguez-Pérez and J. Bajorath, “Evolution of support vector machine and regression modeling in chemoinformatics and drug discovery,” Journal of Computer-Aided Molecular Design, vol. 36, no. 5, pp. 355–362, 2022.
[6] J. Kong, S. Park, T. H. Kim, J. E. Lee, H. Cho, J. Oh, S. Lee, H. Jo, H. Lee, K. Lee, J. Park, L. Jacob, D. Pizzol, S. Y. Rhee, S. Kim, and D. K. Yon, “Worldwide burden of antidiabetic drug-induced sarcopenia: An international pharmacovigilance study,” Archives of Gerontology and Geriatrics, vol. 129, p. 105656, 2025.
[7] D. Li, H. Wang, C. Qin, D. Du, Y. Wang, Q. Du, and S. Liu, “Drug-induced acute pancreatitis: A real-world pharmacovigilance study using the FDA adverse event reporting system database,” Clinical Pharmacology & Therapeutics, vol. 115, no. 3, pp. 535–544, 2024.
[8] R. Chelliah, M. Rubab, S. Vijayalakshmi, M. Karuvelan, K. Barathikannan, and D.-H. Oh, “Liposomes for drug delivery: Classification, therapeutic applications, and limitations,” Next Nanotechnology, vol. 8, p. 100209,
[9] P. Uttreja, I. Karnik, A. Adel Ali Youssef, N. Narala, R. M. Elkanayati, S. Baisa, N. D. Alshammari, S. Banda, S. K. Vemula, and M. A. Repka, “Self-emulsifying drug delivery systems (SEDDS): Transition from liquid to solid—a comprehensive review of formulation, characterization applications, and future trends,” Pharmaceutics, vol. 17, no. 1, p. 63, 2025.
[10] A. Simitopoulos, A. Tsekouras, and P. Macheras, “Coupling drug dissolution with BCS,” Pharmaceutical Research, vol. 41, no. 3, pp. 481–491, 2024.
[11] D. Benrimoh, C. Armstrong, J. Mehltretter, R. Fratila, K. Perlman, S. Israel, A. Kapelner, S. V. Parikh, J. F. Karp, K. Heller, and G. Turecki, “Development of the treatment prediction model in the artificial intelligence in depression–medication enhancement study,” npj Mental Health Research, vol. 4, no. 1, p. 26, 2025.
Cite This Article
Choose your preferred format
Publisher's Note
The statements, opinions, and data presented in this article are solely those of the author(s) and do not necessarily represent those of ASPG, the journal, or its editors. ASPG and the editors disclaim responsibility for any harm arising from the use of any ideas, methods, instructions, or products described in this article, to the fullest extent permitted by applicable law.