Population Pharmacokinetic Approach to the Use of Low Dose Cyclosporine in Patients with Connective Tissue Diseases

An artificial neural network-pharmacokinetic model and its interpretation using Shapley additive explanations

We developed a method to apply artificial neural networks (ANNs) for predicting time‐series pharmacokinetics (PKs), and an interpretable the ANN‐PK model, which can explain the evidence of prediction by applying Shapley additive explanations (SHAP). A previous population PK (PopPK) model of cyclosporin A was used as the comparison model. The patients’ data were used for the ANN‐PK model input, and the output by ANN was the clearance (CL). The estimated CL value from the ANN were substituted into the one‐compartment with one‐order absorption model, the concentrations were calculated, and the parameters of ANN were updated by the back‐propagation method. Kernel SHAP was applied to the trained model and the SHAP value of each input was calculated. The root mean squared error for the PopPK model and the ANN‐PK model were 41.1 and 31.0 ng/ml, respectively. The goodness of fit plots for the ANN‐PK model represented more convergence to y = x compared with that for the PopPK model, with good model performance for the ANN‐PK model. The most influential factors on CL output were age and body weight from the evaluation using Kernel SHAP, and these factors were incorporated into the PopPK model as the significant covariates of CL. The ANN‐PK model could handle time‐series data and showed higher prediction accuracy then the conventional PopPK model, and the scientific validity for the model could be evaluated by applying SHAP.

Multicenter-Based Population Pharmacokinetic Analysis of Ciclosporin in Hematopoietic Stem Cell Transplantation Patients

PURPOSE

To explore the contribution of physiological characteristics to variability in ciclosporin pharmacokinetics in hematopoietic stem cell transplantation patients.

METHODS

Clinical data from 563 patients were collected from centers in three regions. Ciclosporin concentrations were measured using immunoassays. The patients' demographics, hematological and biological indicators, coadministered drugs, region, and disease diagnosis were recorded from medical records. Data analysis was performed using NONMEM based on a one-compartment model to describe the pharmacokinetics of ciclosporin. The reliability and stability of the final model were evaluated using bootstrap resampling, goodness-of-fit plots, and prediction-corrected visual predictive checks.

RESULTS

The population estimate of the clearance (CL) was 30.4 L/h, the volume of distribution (V) was 874.0 L and the bioavailability (F) was 81.1%. The between-subject variability in these parameters was 26.3, 68.0, and 110.8%, respectively. Coadministration of fluconazole, itraconazole, or voriconazole decreased CL by 17.6%, 28.4%, and 29.2%, respectively. Females' CL increased by approximately 12.0%. In addition, CL and V decreased with hematocrit, total protein, and uric acid increase, and CL also decreased with age and aspartate aminotransferase increase. However, CL increased with creatinine clearance increase.

CONCLUSIONS

A multicenter-based population pharmacokinetic model of ciclosporin was established. The pharmacokinetics of ciclosporin exhibited discrepancies among different regions.