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

Comparison of Machine Learning Algorithms and Bayesian Estimation in Predicting Tacrolimus Concentration in Tunisian Kidney Transplant Patients During the Early Post-Transplant Period

BACKGROUND AND OBJECTIVE

Model-informed precision dosing (MIPD), based on a Bayesian approach and machine learning (ML) algorithms, is a suitable approach to personalize dosage recommendations and to improve the concentration target attainment for each patient. The objective of this study is to compare the predictive performance of two ML approaches, XGBoost and LSTM, with a previously developed Bayesian model of tacrolimus (Tac) in a cohort of Tunisian kidney transplant patients during the early post-transplant period (0-3 months) METHOD: This was a cross-sectional study conducted at the Pharmacology department in Fattouma Bourguiba's hospital in Monastir, Tunisia. We included patients who had undergone kidney transplantation in the Nephrology department of Monastir Hospital and received the Tac immunosuppressant protocol, for whom routine therapeutic drug monitoring (TDM) during the early post-transplant period (0-3 months) had been performed in our department.

RESULTS

A total of 187 Tac predose concentration (C0) issued from 56 adult renal transplant patients were included in the present study. The whole population was divided into building (n = 39 patients, 119 C0) and validation groups (n = 17 patients, 68 C0). In the validation dataset, the RMSE was 0.76, 0.19, and 0.01, and the MAE was 0.55, 0.36, and 0.06, respectively, for the Bayesian approach, XGBoost, and LSTM.

CONCLUSION

Our study demonstrates that the LSTM approach outperforms XGBoost and Bayesian estimation in predicting tacrolimus concentration in Tunisian kidney transplant patients. Implementing TDM-based LSTM models during the first PT 3 months in clinical practice can significantly enhance patient outcomes and prevent acute kidney rejection in this population.

Development and Validation of a Nomogram for Predicting Subtherapeutic Tacrolimus Blood Levels in Renal Transplant Recipients: A Multivariate Logistic Regression Analysis

This study constructs a nomogram risk prediction model to identify factors affecting subtherapeutic tacrolimus (FK506) blood concentrations in postrenal transplant patients, enhancing clinical management. Data from renal transplant patients treated with tacrolimus from January to December 2023 were analyzed using multivariate logistic regression to identify risk factors. A nomogram model was constructed and validated through cross-validation and bootstrapping. Predictive performance was assessed via receiver operating characteristic curve and Hosmer- Lemeshow test. Among 340 patients, 224 achieved target FK506 concentrations (5-15 ng/mL). Independent risk factors for subtherapeutic levels included white blood cell count ≤4 × 10^9/L, total bilirubin >20 μmol/L, creatinine >73 μmol/L, and blood urea nitrogen ≤7.1 mmol/L. The model's receiver operating characteristic area under the curve was 0.84, with a Hosmer- Lemeshow test P-value of .386, indicating high predictive accuracy and good calibration. The nomogram effectively predicts subtherapeutic FK506 levels, providing a valuable tool for personalized patient management. Future research should refine and externally validate the model.

Optimizing tacrolimus dosage in post-renal transplantation using DoseOptimal framework: profiling CYP3A5 genetic variants for interpretability

BACKGROUND

Achieving optimal tacrolimus dosing is vital for effectively balancing therapeutic efficacy and safety, as CYP3A5 genetic variants and inter-patient variability emphasize the need for precision strategies.

AIM

This study aimed to optimize tacrolimus dosage prediction for renal transplant recipients by incorporating genetic polymorphisms, specifically profiling CYP3A5 genetic variants, within the DoseOptimal framework to enhance interpretability and accuracy of dosing decisions.

METHOD

The dataset comprised clinical, demographic, and CYP3A5 genetic variants information from 1045 stable tacrolimus-treated patients. The DoseOptimal framework was developed by integrating the strengths of the most effective algorithms from fifteen machine learning models. SHapley Additive exPlanations (SHAP) and decision tree insights were incorporated to enhance the framework's interpretability. The framework's performance was assessed using mean absolute error (MAE) and the coefficient of determination (R2 score). The F-statistic and p value were calculated to validate the framework's statistical significance.

RESULTS

The DoseOptimal framework demonstrated robust performance with an R2 score of 0.884 in the training set and 0.830 in the testing set. The MAE was 0.40 mg/day (95% CI 0.38-0.43) in the training set and 0.41 mg/day (95% CI 0.38-0.45) in the testing set. The framework predicted the ideal tacrolimus dosage in 87.6% (n = 275) of the test cohort, with 3.2% (n = 10) underestimation and 9.2% (n = 29) overestimation. The framework's statistical significance was confirmed with an F-statistic of 266.095 and a p value < 0.001.

CONCLUSION

The framework provides precision medicine-based dosing solutions tailored to individual genetic profiles, minimizing dosing errors and enhancing patient outcomes.

Advancements in Artificial Intelligence for Kidney Transplantology: A Comprehensive Review of Current Applications and Predictive Models

Background: Artificial intelligence is rapidly advancing within the domains of medicine and transplantology. In this comprehensive review, we provide an in-depth exploration of current AI methodologies, with a particular emphasis on machine learning and deep learning techniques, and their diverse subtypes. These technologies are revolutionizing how data are processed, analyzed, and applied in clinical decision making. Methods: A meticulous literature review was conducted with a focus on the application of artificial intelligence in kidney transplantation. Four research questions were formulated to establish the aim of the review. Results: We thoroughly examined the general applications of AI in the medical field, such as feature selection, dimensionality reduction, and clustering, which serve as foundational tools for complex data analysis. This includes the development of predictive models for transplant rejection, the optimization of personalized immunosuppressive therapies, the algorithmic matching of donors and recipients based on multidimensional criteria, and the sophisticated analysis of histopathological images to improve the diagnostic accuracy. Moreover, we present a detailed comparison of existing AI-based algorithms designed to predict kidney graft survival in transplant recipients. In this context, we focus on the variables incorporated into these predictive models, providing a critical analysis of their relative importance and contribution to model performance. Conclusions: This review highlights the significant advancements made possible through AI and underscores its potential to enhance both clinical outcomes and the precision of medical interventions in the field of transplantology.

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.