Artificial Intelligence in Dose Selection and Optimization: A Comprehensive Review on Transforming Modern Drug Development

Artificial Intelligence (AI) is bringing a major change in how drug doses are selected and optimized. It helps researchers and doctors understand complex data better and choose the most effective and safe dose for patients. Compared to traditional methods, AI makes the process faster, more accurate, and more reliable. AI also supports personalized medicine by considering individual patient differences such as age, genetics, and health condition. This leads to better treatment outcomes and fewer side effects. In addition, AI improves clinical trials, reduces costs, and increases the chances of successful drug development. Although there are some challenges like data quality, model transparency, and regulatory issues, continuous improvements in technology and proper guidelines can overcome these problems. In the future, AI will play an even bigger role in healthcare by making treatments more precise, adaptive, and patient-focused. Overall, AI has the potential to make drug development safer, smarter, and more effective for everyone.

[1] Varela-Rey I, Bandín-Vilar E, Toja-Camba FJ, Cañizo-Outeiriño A, Cajade-Pascual F, Ortega-Hortas M, et al. Artificial Intelligence and Machine Learning Applications to Pharmacokinetic Modeling and Dose Prediction of Antibiotics: A Scoping Review. Antibiotics 2024;13:1203. https://doi.org/10.3390/antibiotics13121203. [2] Ros H, Chan N, Cook MT, Shorthouse D. Artificial intelligence and machine learning guided optimization in drug delivery. Adv Drug Deliv Rev 2026;232:115781. https://doi.org/10.1016/j.addr.2026.115781. [3] Joshi S, Sheth S. Artificial Intelligence (AI) in Pharmaceutical Formulation and Dosage Calculations. Pharmaceutics 2025;17:1440. https://doi.org/10.3390/pharmaceutics17111440. [4] Agirbasli M. Influence of Diabetes on CABG Patency. J Am Coll Cardiol 2017;70:2604. https://doi.org/10.1016/j.jacc.2017.07.801. [5] Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med 2019;25:44–56. https://doi.org/10.1038/s41591-018-0300-7. [6] M M, S M, Kate SS, Taneja I, Jaiswal S, Pratap B, et al. A review on integrated machine learning and deep learning driven artificial intelligence models for pharmacokinetics and toxicokinetics predictions, and their application. Drug Metabolism and Disposition 2026;54:100240. https://doi.org/10.1016/j.dmd.2026.100240. [7] Sheiner LB, Steimer J-L. Pharmacokinetic/Pharmacodynamic Modeling in Drug Development. Annu Rev Pharmacol   2000;40:67–95. https://doi.org/10.1146/annurev.pharmtox.40.1.67. [8] Tao R, Chan S, Wang J, Wang X, Shi L, Lan X, et al. Pharmacokinetic-pharmacodynamic target attainment analyses as support for meropenem dosing regimens in critically ill adult and elderly patients with Pseudomonas aeruginosa infections. Front Pharmacol 2025;16. https://doi.org/10.3389/fphar.2025.1643553. [9] Sheiner LB, Steimer J-L. Pharmacokinetic/Pharmacodynamic Modeling in Drug Development. Annu Rev Pharmacol Toxicol2000;40:67–95. https://doi.org/10.1146/annurev.pharmtox.40.1.67. [10]      Erratum. Clin Pharmacol Ther 1981;29:670–670. https://doi.org/10.1038/clpt.1981.93.