Enhancing pharmacokinetic modeling with the Upadhyaya transform and machine learning: A synergistic approach
DOI:
https://doi.org/10.65112/tcmis.10024Keywords:
Upadhyaya transform, inverse Upadhyaya transform, pharmacokinetics, machine learning approachAbstract
In this study, the integration of the Upadhyaya Transform and machine learning for the creation of individualized pharmacokinetic models is examined. A synthetic pharmacokinetic dataset with 500 samples was created by varying the parameters and controlling the noise conditions. The dataset was split into a training set and a testing set, with 80:20 being the ratio, and the model reliability was analyzed further through k-fold cross-validation. A multilayer perceptron neural network was set up to take advantage of the analytically informed features obtained from the Upadhyaya Transform for predicting the drug concentration profiles. The model's performance was measured in terms of the usual metrics, which include the mean squared error, mean absolute error, precision, recall, and accuracy. The findings indicate that the integration of analytical transformations with data-driven learning results in greater efficiency in the pharmacokinetic modeling process and provides a scalable proof-of-concept framework for drug discovery and therapeutic monitoring.
Downloads
References
[1] A. Mousa, ”Application of the Upadhyaya transform to Volterra integral equations of the first kind,” Bulletin of Pure and Applied Sciences Section E: Mathematics & Statistics, vol. 40E, no. 2, pp. 140-148, 2021. https://doi.org/10.5958/2320-3226.2021.00016.3 DOI: https://doi.org/10.5958/2320-3226.2021.00016.3
[2] D. Patil, ”Application of integral transform (Laplace and Shehu) in chemical sciences,” Aayushi International Interdisciplinary Research Journal, vol. 88, pp. 437-441, 2022. DOI: https://doi.org/10.2139/ssrn.4006213
[3] S. Kulkarni and P. Mahagaonkar, ”Study on motion of an electron in a physical system by using some integral transforms,” Eur. Chem. Bull., vol. 12, no. 8, pp. 967-974, 2023.
[4] D. Thakur and E. A. Kuffi, ”Exact solutions of cardiovascular models by using Upadhyaya Transform,” Journal of Kufa for Mathematics and Computer, vol. 11, no. 1, pp. 37-42, 2024. https://doi.org/10.31642/JoKMC/2018/110107 DOI: https://doi.org/10.31642/JoKMC/2018/110107
[5] D. Thakur, P. Raghavendran, T. Gunasekar, P. C. Thakur, B. Krishan, and S. Kumar, ”Solving the chemical reaction models with the Upadhyaya Transform,” Oriental Journal of Chemistry, vol. 40, no. 3, pp. 767-772, 2024. https://doi.org/10.13005/ojc/400318 DOI: https://doi.org/10.13005/ojc/400318
[6] P. Raghavendran, T. Gunasekar, D. Thakur, P. C. Thakur, and B. Krishan, ”Predictive modeling of chemical processes using differential equations and machine learning synergy,” Oriental Journal of Chemistry, vol. 41, no. 2, 2025. https://doi.org/10.13005/ojc/410206 DOI: https://doi.org/10.13005/ojc/410206
[7] P. Raghavendran, T. Gunasekar, and S. Gochhait, ”A new approach for solving fractional differential equations incorporating Ramadan Group Transform and machine learning,” EAI Endorsed Trans IoT, vol. 11, pp. 1-12, 2025. https://doi.org/10.4108/eetiot.7134 DOI: https://doi.org/10.4108/eetiot.7134
[8] H. Jafari, S. Aggarwal, A. Kumar, and S. Bansal, ”Anuj Integral Transform to solving Abel’s integral equation of classical mechanics,” National Academy Science Letters, pp. 1-5, 2025. DOI: https://doi.org/10.1007/s40009-024-01597-9
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Prabakaran Raghavendran, Yamini Parthiban, Dinesh Thakur, Jothivelu Thiravidarani
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All open access articles published in Transactions on Computational Modelling and Intelligent Systems (http://tcmis.org) are distributed under the terms of the CC BY-NC 4.0 license (Creative Commons Attribution Non-Commercial 4.0 International Public License as currently displayed at http://creativecommons.org/licenses/by-nc/4.0/legalcode) which permits unrestricted use, distribution, and reproduction in any medium, for non-commercial purposes, provided the original work is properly cited.
