A Hybrid Model Associating Population Pharmacokinetics with Machine Learning: A Case Study with Iohexol Clearance Estimation

Use of Artificial Intelligence in Current Fight Against Antimicrobial Resistance

Antimicrobial resistance (AMR) poses a significant global health threat, with projections indicating it could surpass cancer in mortality rates by 2050 if left unaddressed. Optimizing antimicrobial dosing is critical to mitigate resistance and improve clinical outcomes. Traditional approaches, including population pharmacokinetics (PK) models and Bayesian estimation, are limited by mechanistic hypothesis requirements and complexity. Artificial intelligence (AI) and machine learning (ML) offer transformative solutions by leveraging large datasets to predict drug exposure accurately, refine sampling strategies, and enable real-time dose adjustments through therapeutic drug monitoring. This review highlights the role of ML models, in managing PK and pharmacodynamic variability across diverse patient populations. AI models often equal or outperform traditional methods in achieving therapeutic targets while minimizing toxicity, as demonstrated in some case studies involving ganciclovir, vancomycin, and daptomycin. Despite challenges such as data quality, interpretability, and integration with clinical workflows, AI's dynamic adaptability and precision underscore its potential. Future directions emphasize integrating multi-omics data, developing bedside decision-support tools, and expanding AI applications to broader drug categories and populations. Continued research and clinical validation are essential to harness AI's full potential in advancing precision medicine and combating AMR effectively.

Machine Learning for Prediction of Drug Concentrations: Application and Challenges

With the advancements in algorithms and increased accessibility of multi-source data, machine learning in pharmacokinetics is gaining interest. This review summarizes studies on machine learning-based pharmacokinetics analysis up to September 2024, identified from the PubMed and IEEE Xplore databases. The main focus of this review is on the use of machine learning in predicting drug concentration. This review provides a comprehensive summary of the advances in the machine learning algorithms for pharmacokinetics analysis. Specifically, we describe the common practices in data preprocessing, the application scenarios of various algorithms, and the critical challenges that require attention. Most machine learning models show comparable performance to those of population pharmacokinetics models. Tree-based algorithms and neural networks have the most applications. Furthermore, the use of ensemble modeling techniques can improve the accuracy of these models' predictions of drug concentrations, especially the ensembles of machine learning and pharmacometrics.

Estimation of Ganciclovir Exposure in Adults Transplant Patients by Machine Learning

INTRODUCTION

Valganciclovir, a prodrug of ganciclovir (GCV), is used to prevent cytomegalovirus infection after transplantation, with doses adjusted based on creatinine clearance (CrCL) to target GCV AUC0-24 h of 40-60 mg*h/L. This sometimes leads to overexposure or underexposure. This study aimed to train, test and validate machine learning (ML) algorithms for accurate GCV AUC0-24 h estimation in solid organ transplantation.

METHODS

We simulated patients for different dosing regimen (900 mg/24 h, 450 mg/24 h, 450 mg/48 h, 450 mg/72 h) using two literature population pharmacokinetic models, allocating 75% for training and 25% for testing. Simulations from two other literature models and real patients provided validation datasets. Three independent sets of ML algorithms were created for each regimen, incorporating CrCL and 2 or 3 concentrations. We evaluated their performance on testing and validation datasets and compared them with MAP-BE.

RESULTS

XGBoost using 3 concentrations generated the most accurate predictions. In testing dataset, they exhibited a relative bias of -0.02 to 1.5% and a relative RMSE of 2.6 to 8.5%. In the validation dataset, a relative bias of 1.5 to 5.8% and 8.9 to 16.5%, and a relative RMSE of 8.5 to 9.6% and 10.7% to 19.7% were observed depending on the model used. XGBoost algorithms outperformed or matched MAP-BE, showing enhanced generalization and robustness in their estimates. When applied to real patients' data, algorithms using 2 concentrations showed relative bias of 1.26% and relative RMSE of 12.68%.

CONCLUSIONS

XGBoost ML models accurately estimated GCV AUC0-24 h from limited samples and CrCL, providing a strategy for optimized therapeutic drug monitoring.

Leveraging machine learning in limited sampling strategies for efficient estimation of the area under the curve in pharmacokinetic analysis: a review

OBJECTIVE

Limited sampling strategies are widely employed in clinical practice to minimize the number of blood samples required for the accurate area under the curve calculations, as obtaining these samples can be costly and challenging. Traditionally, the maximum a posteriori Bayesian estimation has been the standard method for the area under the curve estimation based on limited samples. However, machine learning is emerging as a promising alternative for this purpose. Here, we review studies that utilize machine learning approaches to develop limited sampling strategies and compare the strengths and weaknesses of these machine learning methods.

METHODS

We searched the literature for studies that used machine learning to estimate the area under the curve using a limited sampling strategy approach.

RESULTS

We identified ten studies that developed machine learning models to estimate the area under the curve for six different drugs. Several of these models demonstrated good accuracy and precision in area under the curve estimation in reference to the traditional Bayesian approach, highlighting the potential of machine learning models in precision dosing.

CONCLUSIONS

Despite these promising early results, the development of machine learning for limited sampling strategies is still in its early stages. Further research might be needed to validate machine learning models with larger, high-quality clinical datasets to ensure their reliability and applicability in clinical settings.

Another string to your bow: machine learning prediction of the pharmacokinetic properties of small molecules

INTRODUCTION

Prediction of pharmacokinetic (PK) properties is crucial for drug discovery and development. Machine-learning (ML) models, which use statistical pattern recognition to learn correlations between input features (such as chemical structures) and target variables (such as PK parameters), are being increasingly used for this purpose. To embed ML models for PK prediction into workflows and to guide future development, a solid understanding of their applicability, advantages, limitations, and synergies with other approaches is necessary.

AREAS COVERED

This narrative review discusses the design and application of ML models to predict PK parameters of small molecules, especially in light of established approaches including in vitro-in vivo extrapolation (IVIVE) and physiologically based pharmacokinetic (PBPK) models. The authors illustrate scenarios in which the three approaches are used and emphasize how they enhance and complement each other. In particular, they highlight achievements, the state of the art and potentials of applying machine learning for PK prediction through a comphrehensive literature review.

EXPERT OPINION

ML models, when carefully crafted, regularly updated, and appropriately used, empower users to prioritize molecules with favorable PK properties. Informed practitioners can leverage these models to improve the efficiency of drug discovery and development process.

A machine learning approach to predict daptomycin exposure from two concentrations based on Monte Carlo simulations

Daptomycin is a concentration-dependent lipopeptide antibiotic for which exposure/effect relationships have been shown. Machine learning (ML) algorithms, developed to predict the individual exposure to drugs, have shown very good performances in comparison to maximum a posteriori Bayesian estimation (MAP-BE). The aim of this work was to predict the area under the blood concentration curve (AUC) of daptomycin from two samples and a few covariates using XGBoost ML algorithm trained on Monte Carlo simulations. Five thousand one hundred fifty patients were simulated from two literature population pharmacokinetics models. Data from the first model were split into a training set (75%) and a testing set (25%). Four ML algorithms were built to learn AUC based on daptomycin blood concentration samples at pre-dose and 1 h post-dose. The XGBoost model (best ML algorithm) with the lowest root mean square error (RMSE) in a 10-fold cross-validation experiment was evaluated in both the test set and the simulations from the second population pharmacokinetic model (validation). The ML model based on the two concentrations, the differences between these concentrations, and five other covariates (sex, weight, daptomycin dose, creatinine clearance, and body temperature) yielded very good AUC estimation in the test (relative bias/RMSE = 0.43/7.69%) and validation sets (relative bias/RMSE = 4.61/6.63%). The XGBoost ML model developed allowed accurate estimation of daptomycin AUC using C0, C1h, and a few covariates and could be used for exposure estimation and dose adjustment. This ML approach can facilitate the conduct of future therapeutic drug monitoring (TDM) studies.

Predicting Pharmacokinetics of Drugs Using Artificial Intelligence Tools: A Systematic Review

BACKGROUND AND OBJECTIVE

Pharmacokinetic studies encompass the examination of the absorption, distribution, metabolism, and excretion of bioactive compounds. The pharmacokinetics of drugs exert a substantial influence on their efficacy and safety. Consequently, the investigation of pharmacokinetics holds great importance. However, laboratory-based assessment necessitates the use of numerous animals, various materials, and significant time. To mitigate these challenges, alternative methods such as artificial intelligence have emerged as a promising approach. This systematic review aims to review existing studies, focusing on the application of artificial intelligence tools in predicting the pharmacokinetics of drugs.

METHODS

A pre-prepared search strategy based on related keywords was used to search different databases (PubMed, Scopus, Web of Science). The process involved combining articles, eliminating duplicates, and screening articles based on their titles, abstracts, and full text. Articles were selected based on inclusion and exclusion criteria. Then, the quality of the included articles was assessed using an appraisal tool.

RESULTS

Ultimately, 23 relevant articles were included in this study. The clearance parameter received the highest level of investigation, followed by the  area under the concentration-time curve (AUC) parameter, in pharmacokinetic studies. Among the various models employed in the articles, Random Forest and eXtreme Gradient Boosting (XGBoost) emerged as the most commonly utilized ones. Generalized Linear Models and Elastic Nets (GLMnet) and Random Forest models showed the most performance in predicting clearance.

CONCLUSION

Overall, artificial intelligence tools offer a robust, rapid, and precise means of predicting various pharmacokinetic parameters based on a dataset containing information of patients or drugs.

Application of machine learning combined with population pharmacokinetics to improve individual prediction of vancomycin clearance in simulated adult patients

Background and aim

Vancomycin, a glycopeptide antimicrobial drug. PPK has problems such as difficulty in accurately reflecting inter-individual differences, and the PPK model may not be accurate enough to predict individual pharmacokinetic parameters. Therefore, the aim of this study is to investigate whether the application of machine learning combined with the PPK method can improve the prediction of vancomycin CL in adult Chinese patients.

Methods

In the first step, a vancomycin CL prediction model for Chinese adult patients is given by PPK and Hamilton Monte Carlo sampling is used to obtain the reference CL of 1,000 patients; the second step is to obtain the final prediction model by machine learning using an appropriate model for the predictive factor and the reference CL; and the third step is to randomly select, in the simulated data, a total of 250 patients for prediction effect evaluation.

Results

XGBoost model is selected as final machine learning model. More than four-fifths of the subjects' predictive values regarding vancomycin CL are improved by machine learning combined with PPK. Machine learning combined with PPK models is more stable in performance than the PPK method alone for predicting models.

Conclusion

The first combination of PPK and machine learning for predictive modeling of vancomycin clearance in adult patients. It provides a reference for clinical pharmacists or clinicians to optimize the initial dosage given to ensure the effectiveness and safety of drug therapy for each patient.

Optimization of Rituximab Therapy in Adult Patients With PLA2R1-Associated Membranous Nephropathy With Artificial Intelligence

Introduction

Rituximab is a first-line treatment for membranous nephropathy. Nephrotic syndrome limits rituximab exposure due to urinary drug loss. Rituximab underdosing (serum level <2 μg/ml at month-3) is a risk factor for treatment failure. We developed a machine learning algorithm to predict the risk of underdosing based on patients' characteristics at rituximab infusion. We investigated the relationship between the predicted risk of underdosing and the cumulative dose of rituximab required to achieve remission.

Methods

Rituximab concentrations were measured at month-3 in 92 sera from adult patients with primary membranous nephropathy, split into a training (75%) and a testing set (25%). A forward-backward machine-learning procedure determined the best combination of variables to predict rituximab underdosing in the training data set, which was tested in the test set. The performances were evaluated for accuracy, sensitivity, and specificity in 10-fold cross-validation training and test sets.

Results

The best variables combination to predict rituximab underdosing included age, gender, body surface area (BSA), anti-phospholipase A2 receptor type 1 (anti-PLA2R1) antibody titer on day-0, serum albumin on day-0 and day-15, and serum creatinine on day-0 and day-15. The accuracy, sensitivity, and specificity were respectively 79.4%, 78.7%, and 81.0% (training data set), and 79.2%, 84.6% and 72.7% (testing data set). In both sets, the algorithm performed significantly better than chance (P < 0.05). Patients with an initial high probability of underdosing experienced a longer time to remission with higher rituximab cumulative doses required to achieved remission.

Conclusion

This algorithm could allow for early intensification of rituximab regimen in patients at high estimated risk of underdosing to increase the likelihood of remission.

Clinical decision support for chemotherapy-induced neutropenia using a hybrid pharmacodynamic/machine learning model

Consensus guidelines recommend use of granulocyte colony stimulating factor in patients deemed at risk of chemotherapy-induced neutropenia, however, these risk models are limited in the factors they consider and miss some cases of neutropenia. Clinical decision making could be supported using models that better tailor their predictions to the individual patient using the wealth of data available in electronic health records (EHRs). Here, we present a hybrid pharmacokinetic/pharmacodynamic (PKPD)/machine learning (ML) approach that uses predictions and individual Bayesian parameter estimates from a PKPD model to enrich an ML model built on her data. We demonstrate this approach using models developed on a large real-world data set of 9121 patients treated for lymphoma, breast, or thoracic cancer. We also investigate the benefits of augmenting the training data using synthetic data simulated with the PKPD model. We find that PKPD-enrichment of ML models improves prediction of grade 3-4 neutropenia, as measured by higher precision (61%) and recall (39%) compared to PKPD model predictions (47%, 33%) or base ML model predictions (51%, 31%). PKPD augmentation of ML models showed minor improvements in recall (44%) but not precision (56%), and data augmentation required careful tuning to control overfitting its predictions to the PKPD model. PKPD enrichment of ML shows promise for leveraging both the physiology-informed predictions of PKPD and the ability of ML to learn predictor-outcome relationships from large data sets to predict patient response to drugs in a clinical precision dosing context.

Bridging the Worlds of Pharmacometrics and Machine Learning

Precision medicine requires individualized modeling of disease and drug dynamics, with machine learning-based computational techniques gaining increasing popularity. The complexity of either field, however, makes current pharmacological problems opaque to machine learning practitioners, and state-of-the-art machine learning methods inaccessible to pharmacometricians. To help bridge the two worlds, we provide an introduction to current problems and techniques in pharmacometrics that ranges from pharmacokinetic and pharmacodynamic modeling to pharmacometric simulations, model-informed precision dosing, and systems pharmacology, and review some of the machine learning approaches to address them. We hope this would facilitate collaboration between experts, with complementary strengths of principled pharmacometric modeling and flexibility of machine learning leading to synergistic effects in pharmacological applications.

Adapting physiologically-based pharmacokinetic models for machine learning applications

Both machine learning and physiologically-based pharmacokinetic models are becoming essential components of the drug development process. Integrating the predictive capabilities of physiologically-based pharmacokinetic (PBPK) models within machine learning (ML) pipelines could offer significant benefits in improving the accuracy and scope of drug screening and evaluation procedures. Here, we describe the development and testing of a self-contained machine learning module capable of faithfully recapitulating summary pharmacokinetic (PK) parameters produced by a full PBPK model, given a set of input drug-specific and regimen-specific information. Because of its widespread use in characterizing the disposition of orally administered drugs, the PBPK model chosen to demonstrate the methodology was an open-source implementation of a state-of-the-art compartmental and transit model called OpenCAT. The model was tested for drug formulations spanning a large range of solubility and absorption characteristics, and was evaluated for concordance against predictions of OpenCAT and relevant experimental data. In general, the values predicted by the ML models were within 20% of those of the PBPK model across the range of drug and formulation properties. However, summary PK parameter predictions from both the ML model and full PBPK model were occasionally poor with respect to those derived from experiments, suggesting deficiencies in the underlying PBPK model.

Predicting busulfan exposure in patients undergoing hematopoietic stem cell transplantation using machine learning techniques

PURPOSE

This study aimed to establish an optimal model to predict the busulfan (BU) area under the curve at steady state (AUCss) by using machine learning (ML).

PATIENTS AND METHODS

Seventy-nine adult patients (age ≥18 years) who received BU intravenously and underwent therapeutic drug monitoring from 2013 to 2021 at Fujian Medical University Union Hospital were enrolled in this retrospective study. The whole dataset was divided into a training group and test group at the ratio of 8:2. BU AUCss were considered as the target variable. Nine different ML algorithms and one population pharmacokinetic (pop PK) model were developed and validated, and their predictive performance was compared.

RESULTS

All ML models were superior to the pop PK model (R2 = 0.751, MSE = 0.722, 14 and RMSE = 0.830) in model fitting and had better predictive accuracy. The ML model of BU AUCss established through support vector regression (SVR) and gradient boosted regression trees (GBRT) had the best predictive ability (R2 = 0.953 and 0.953, MSE = 0.323 and 0.326, and RMSE = 0.423 and 0.425).

CONCLUSION

All the ML models can potentially be used to estimate BU AUCss with the aim of facilitating rational use of BU on the individualized level, especially models built by SVR and GBRT algorithms.

A Hybrid Algorithm Combining Population Pharmacokinetic and Machine Learning for Isavuconazole Exposure Prediction

OBJECTIVES

Maximum a posteriori Bayesian estimation (MAP-BE) based on a limited sampling strategy and a population pharmacokinetic (POPPK) model is used to estimate individual pharmacokinetic parameters. Recently, we proposed a methodology that combined population pharmacokinetic and machine learning (ML) to decrease the bias and imprecision in individual iohexol clearance prediction. The aim of this study was to confirm the previous results by developing a hybrid algorithm combining POPPK, MAP-BE and ML that accurately predicts isavuconazole clearance.

METHODS

A total of 1727 isavuconazole rich PK profiles were simulated using a POPPK model from the literature, and MAP-BE was used to estimate the clearance based on: (i) the full PK profiles (refCL); and (ii) C24h only (C24h-CL). Xgboost was trained to correct the error between refCL and C24h-CL in the training dataset (75%). C24h-CL as well as ML-corrected C24h-CL were evaluated in a testing dataset (25%) and then in a set of PK profiles simulated using another published POPPK model.

RESULTS

A strong decrease in mean predictive error (MPE%), imprecision (RMSE%) and the number of profiles outside ± 20% MPE% (n-out20%) was observed with the hybrid algorithm (decreased in MPE% by 95.8% and 85.6%; RMSE% by 69.5% and 69.0%; n-out20% by 97.4% and 100% in the training and testing sets, respectively. In the external validation set, the hybrid algorithm decreased MPE% by 96%, RMSE% by 68% and n-out20% by 100%.

CONCLUSION

The hybrid model proposed significantly improved isavuconazole AUC estimation over MAP-BE based on the sole C24h and may improve dose adjustment.

A HPLC-DAD method to facilitate large-scale therapeutic drug monitoring of dalbavancin

Dalbavancin, a long-acting lipoglycopeptide antibiotic targeting susceptible Gram-positive bacteria, is WHO critically important antibiotic, increasingly used in critical situations such as osteoarticular infections. To ensure its effectiveness and its safety, the therapeutic drug monitoring (TDM) of dalbavancin is strongly recommended. In the absence of an available minimum inhibitory concentration (MIC), the European Committee on Antimicrobial Susceptibility Testing (EUCAST) recommends a breakpoint of 0.125 mg/L for Staphylococcus aureus, corresponding to a trough target concentration of 25 mg/L. Nowadays, the TDM is usually performed using a high-performance liquid chromatography (HPLC) method coupled with a tandem mass spectrometry. However, this expensive and specialized equipment and reagents may be difficult to acquire for non-specialized laboratories. The use of HPLC coupled with diode array detector (DAD) facilitates TDM with a lower cost, while preserving the reliability of the results. Our aim was to provide a sensitive and specific method, relying on HPLC-DAD for extending the TDM of dalbavancin beyond non-specialized labs, therefore maximizing its efficiency and Benefit/risk ratio. Our method complied with the European Medicines Agency guidelines of bioanalytical validation. Irrespective of the concentrations of dalbavancin, the coefficient of variation < 10% confirmed the reliability of this analytical method, with a calibration curve ranging from 5 to 100 mg/L. No interferences nor carryover was observed. Our HPLC-DAD method, combined with a simple extraction, provides a widely usable, inexpensive and easy-to-implement new asset for the TDM of Dalbavancin.