Machine learning-based method for tacrolimus dose predictions in Chinese kidney transplant perioperative patients

Improving prediction of tacrolimus concentration using a combination of population pharmacokinetic modeling and machine learning in chinese renal transplant recipients

Aims

The population pharmacokinetic (PPK) model-based machine learning (ML) approach offers a novel perspective on individual concentration prediction. This study aimed to establish a PPK-based ML model for predicting tacrolimus (TAC) concentrations in Chinese renal transplant recipients.

Methods

Conventional TAC monitoring data from 127 Chinese renal transplant patients were divided into training (80%) and testing (20%) datasets. A PPK model was developed using the training group data. ML models were then established based on individual pharmacokinetic data derived from the PPK basic model. The prediction performances of the PPK-based ML model and Bayesian forecasting approach were compared using data from the test group.

Results

The final PPK model, incorporating hematocrit and CYP3A5 genotypes as covariates, was successfully established. Individual predictions of TAC using the PPK basic model, postoperative date, CYP3A5 genotype, and hematocrit showed improved rankings in ML model construction. XGBoost, based on the TAC PPK, exhibited the best prediction performance.

Conclusion

The PPK-based machine learning approach emerges as a superior option for predicting TAC concentrations in Chinese renal transplant recipients.

Machine Learning: A New Approach for Dose Individualization

The application of machine learning (ML) has shown promising results in precision medicine due to its exceptional performance in dealing with complex multidimensional data. However, using ML for individualized dosing of medicines is still in its early stage, meriting further exploration. A systematic review of study designs and modeling details of using ML for individualized dosing of different drugs was performed. We have summarized the status of the study populations, predictive targets, and data sources for ML modeling, the selection of ML algorithms and features, and the evaluation and validation of their predictive performance. We also used the Prediction model Risk of Bias Assessment Tool (PROBAST) to assess the risk of bias of included studies. Currently, ML can be used for both a priori and a posteriori dose selection and optimization, and it can also assist the implementation of therapeutic drug monitoring. However, studies are mainly focused on drugs with narrow therapeutic windows, predominantly immunosuppressants (N = 23, 35.9%) and anti-infectives (N = 21, 32.8%), and there is currently only very limited attention for special populations, such as children (N = 22, 34.4%). Most studies showed poor methodological quality and a high risk of bias. The lack of external validation and clinical utility evaluation currently limits the further clinical implementation of ML for dose individualization. We therefore have proposed several ways to improve the clinical relevance of the studies and facilitate the translation of ML models into clinical practice.

Individualized dosing algorithms for tacrolimus in kidney transplant recipients: current status and unmet needs

INTRODUCTION

Tacrolimus is a potent immunosuppressive drug with many side effects including nephrotoxicity and post-transplant diabetes mellitus. To limit its toxicity, therapeutic drug monitoring (TDM) is performed. However, tacrolimus' pharmacokinetics are highly variable within and between individuals, which complicates their clinical management. Despite TDM, many kidney transplant recipients will experience under- or overexposure to tacrolimus. Therefore, dosing algorithms have been developed to limit the time a patient is exposed to off-target concentrations.

AREAS COVERED

Tacrolimus starting dose algorithms and models for follow-up doses developed and/or tested since 2015, encompassing both adult and pediatric populations. Literature was searched in different databases, i.e. Embase, PubMed, Web of Science, Cochrane Register, and Google Scholar, from inception to February 2023.

EXPERT OPINION

Many algorithms have been developed, but few have been prospectively evaluated. These performed better than bodyweight-based starting doses, regarding the time a patient is exposed to off-target tacrolimus concentrations. No benefit in reduced tacrolimus toxicity has yet been observed. Most algorithms were developed from small datasets, contained only a few tacrolimus concentrations per person, and were not externally validated. Moreover, other matrices should be considered which might better correlate with tacrolimus toxicity than the whole-blood concentration, e.g. unbound plasma or intra-lymphocytic tacrolimus concentrations.

Prediction of tacrolimus and Wuzhi tablet pharmacokinetic interaction magnitude in renal transplant recipients

AIM

Wuzhi tablets are a dose-sparing agent for tacrolimus (TAC) in China and increase the bioavailability of TAC. The current study aimed to evaluate the pharmacokinetic interaction magnitude of Wuzhi and TAC and explore the potential determinants of this interaction.

METHODS

This study performed a retrospective, self-controlled study of 138 renal transplant recipients who were co-administered TAC and Wuzhi. The trough concentration (C0) of TAC at baseline and 3, 7, 14 and 21 days after Wuzhi co-therapy initiation was measured, and the CYP3A5 polymorphism was genotyped. The corresponding clinical factors were recorded. The ratio of dose-adjusted C0 (C0/D) post- and pre-combination therapy (ΔC0/D) indicates the interaction magnitude. Univariate and multivariate analyses were used to identify determinants and establish the prediction model.

RESULTS

ΔC0/D reached a steady state within 14 days. The geometrical mean ΔC0/D was 2.91 (range 1.02-9.49, IQR 2.13-3.80). ΔC0/D was blunted in CYP3A5 expressers (estimated effect: -39.8%, P = .001) and affected by hematocrit (Hct) (+24.0% per 10% increase, P = .005) and baseline C0/D (-31.9% per 1 ng·ml^-1 ·mg^-1 increase, P < .001). The prediction model was ΔC0/D = .319baseline C0/D × 1.398CYP3A5 (expressers = 0/non-expressers = 1) × 1.024Hct × 1.744, and it explained 28.1% of the variability.

CONCLUSION

Our study is the first attempt to date to give an assessment of the magnitude of pharmacokinetic interaction between TAC and Wuzhi in a cohort of renal transplant recipients, and CYP3A5 genotypes, baseline C0/D and Hct were identified as determinants of this interaction.

Effect of drug combination on tacrolimus target dose in renal transplant patients with different CYP3A5 genotypes

Various factors, including genetic polymorphisms, drug-drug interactions, and patient characteristics influence the blood concentrations of tacrolimus in renal transplant patients. In the present study, we established a population pharmacokinetic model to explore the effect of combined use of Wuzhi capsules/echinocandins and the patients' biochemical parameters such as hematocrit on blood concentrations and target doses of tacrolimus in renal transplant patients with different CYP3A5 genotypes. The aim of the study was to propose an individualized tacrolimus administration regimen for early renal transplant recipients.In this retrospective cohort study, we included 240 renal transplant recipients within 21 days of surgery (174 males and 66 females, mean age 39.4 years), who received tacrolimus alone (n = 54), in combination with Wuzhi capsules (99) or caspofungin (57) or micafungin (30). We collected demographic characteristics, clinical indicators, CYP3A5 genotypes, and 1950 steady-state trough concentrations of tacrolimus and included them in population pharmacokinetic model. An additional 110 renal transplant recipients and 625 steady-state trough concentrations of tacrolimus were included for external validation of the model. The population pharmacokinetic model was established and Monte Carlo was used to simulate probabilities for achieving the target concentration for individual tacrolimus administration.A two-compartment model of first-order absorption and elimination was developed to describe the population pharmacokinetics of tacrolimus. CYP3A5 genotypes and co-administration of Wuzhi capsules, as well as time after renal transplantation and hematocrit, were important factors affecting the clearance of tacrolimus. We found no obvious change in trend in the scatter plot of tacrolimus clearance rate vs. hematocrit. The Monte Carlo simulation indicated the following recommended doses of tacrolimus alone: 0.14 mg·kg^-1·d^-1 for genotype CYP3A5*1*1, 0.12 mg·kg^-1·d^-1 for CYP3A5*1*3, and 0.10 mg·kg^-1·d^-1 for CYP3A5*3*3. For patients receiving the combination with Wuzhi capsules, the recommended doses of tacrolimus were 0.10 mg·kg^-1·d^-1 for CYP3A5*1*1, 0.08 mg·kg^-1·d^-1 for CYP3A5*1*3, and 0.06 mg·kg^-1·d^-1 for CYP3A5*3*3 genotypes. Caspofungin or micafungin had no effect on the clearance of tacrolimus in renal transplant recipients.The population pharmacokinetics of tacrolimus in renal transplant patients was evaluated and the individual administration regimen of tacrolimus was simulated. For early kidney transplant recipients receiving tacrolimus treatment, not only body weight, but also CYP3A5 genotypes and drugs used in combination should be considered when determining the target dose of tacrolimus.