Applying machine learning to the pharmacokinetic modeling of cyclosporine in adult renal transplant recipients: a multi-method comparison

Abstract

Objective: The aim of this study was to identify the important factors affecting cyclosporine (CsA) blood concentration and estimate CsA concentration using seven different machine learning (ML) algorithms. We also assessed the predictability of established ML models and previously built population pharmacokinetic (popPK) model. Finally, the most suitable ML model and popPK model to guide precision dosing were determined.Methods: In total, 3,407 whole-blood trough and peak concentrations of CsA were obtained from 183 patients who underwent initial renal transplantation. These samples were divided into model-building and evaluation sets. The model-building set was analyzed using seven different ML algorithms. The effects of potential covariates were evaluated using the least absolute shrinkage and selection operator algorithms. A separate evaluation set was used to assess the ability of all models to predict CsA blood concentration. R squared (R2) scores, median prediction error (MDPE), median absolute prediction error (MAPE), and the percentages of PE within 20% (F20) and 30% (F30) were calculated to assess the predictive performance of these models. In addition, previously built popPK model was included for comparison.Results: Sixteen variables were selected as important covariates. Among ML models, the predictive performance of nonlinear-based ML models was superior to that of linear regression (MDPE: 3.27%, MAPE: 34.21%, F20: 30.63%, F30: 45.03%, R2 score: 0.68). The ML model built with the artificial neural network algorithm was considered the most suitable (MDPE: −0.039%, MAPE: 25.60%, F20: 39.35%, F30: 56.46%, R2 score: 0.75). Its performance was superior to that of the previously built popPK model (MDPE: 5.26%, MAPE: 29.22%, F20: 33.94%, F30: 51.22%, R2 score: 0.68). Furthermore, the application of the most suitable model and the popPK model in clinic showed that most dose regimen recommendations were reasonable.Conclusion: The performance of these ML models indicate that a nonlinear relationship for covariates may help to improve model predictability. These results might facilitate the application of ML models in clinic, especially for patients with unstable status or during initial dose optimization.

Machine Learning: A New Approach for Dose Individualization

“…After removing duplicated articles, 3,346 studies were screened by the title and/or abstract, 3,175 irrelevant studies were excluded and 171 articles were included for full‐text review. Finally, 64 articles related to precision dosing using ML were included for analysis 11–74 . The PRISMA flow diagram representing the study selection process and review results is presented in Figure .…”

Modeling Pharmacokinetics in Individual Patients Using Therapeutic Drug Monitoring and Artificial Population Quasi-Models: A Study with Piperacillin

“…Such efforts can be supported further by employing models augmented by computer algorithms. Mao et al demonstrated the efficiency of models based on machine learning (ML), specifically of those built using an artificial neural network algorithm, to be superior to that of population pharmacokinetic models when estimating cyclosporin A concentrations [ 8 ]. Hybrid pop-PK-ML models have been shown to have a performance superior to that of pop-PK models alone with iohexol and isavuconazole [ 26 , 27 ].…”

Advancing Precision Medicine: A Review of Innovative In Silico Approaches for Drug Development, Clinical Pharmacology and Personalized Healthcare

“…By considering individual patient characteristics, data-driven approaches enable the tailoring of drug dosages to maximize therapeutic benefits while minimizing side effects [ 152 , 153 ]. In contrast to traditional approaches, which often require extensive trial-and-error adjustments to find optimal dosages [ 154 , 155 ], these methods accelerate this process, reducing costs and risks, and can be used in early drug development stages to predict PK parameters, facilitating decision-making and dose selection [ 156 , 157 ]. These approaches support adaptive dosing strategies that can be modified in real time based on a patient’s response and changing clinical conditions [ 158 , 159 ].…”

“…However, it is imperative that a fundamental understanding of these algorithms and their limitations is retained. Interestingly, Kolluri et al emphasize the importance of recognizing that the scientific method is not obsolete when making inferences about data and that informed decision-making on the optimal use of AI/ML in drug development is necessary [ 157 ]. A landscape analysis of regulatory submissions to the FDA reveals a rapid increase in AI and ML applications since 2016, with a particularly significant rise in 2021.…”