A model based on machine learning for the prediction of cyclosporin A trough concentration in Chinese allo-HSCT patients.

BACKGROUND: Cyclosporin A is a calcineurin inhibitor which has a narrow therapeutic window and high interindividual variability. Various population pharmacokinetic models have been reported; however, professional software and technical personnel were needed and the variables of the models were limited. Therefore, the aim of this study was to establish a model based on machine learning to predict CsA trough concentrations in Chinese allo-HSCT patients. METHODS: A total of 7874 cases of CsA therapeutic drug monitoring data from 2069 allo-HSCT patients were retrospectively included. Sequential forward selection was used to select variable subsets, and eight different algorithms were applied to establish the prediction model. RESULTS: XGBoost exhibited the highest prediction ability. Except for the variables that were identified by previous studies, some rarely reported variables were found, such as norethindrone, WBC, PAB, and hCRP. The prediction accuracy within ±30% of the actual trough concentration was above 0.80, and the predictive ability of the models was demonstrated to be effective in external validation. CONCLUSION: In this study, models based on machine learning technology were established to predict CsA levels 3-4 days in advance during the early inpatient phase after HSCT. A new perspective for CsA clinical application is provided.

Development of Physiology Based Pharmacokinetic Model to Predict the Drug Interactions of Voriconazole and Venetoclax.

PURPOSE: Venetoclax (VEN), an anti-tumor drug that is a substrate of cytochrome P450 3A enzyme (CYP3A4), is used to treat leukemia. Voriconazole (VCZ) is an antifungal medication that inhibits CYP3A4. The goal of this study is to predict the effect of VCZ on VEN exposure. METHOD: Two physiological based pharmacokinetics (PBPK) models were developed for VCZ and VEN using the bottom-up and top-down method. VCZ model was also developed to describe the effect of CYP2C19 polymorphism on its pharmacokinetics (PK). The reversible inhibition constant (Ki) of VCZ for CYP3A4 was calibrated using drug-drug interaction (DDI) data of midazolam and VCZ. The clinical verified VCZ and VEN model were used to predict the DDI of VCZ and VEN at clinical dosing scenario. RESULT: VCZ model predicted VCZ exposure in the subjects of different CYP2C19 genotype and DDI related fold changes of sensitive CYP3A substrate with acceptable prediction error. VEN model can capture PK of VEN with acceptable prediction error. The DDI PBPK model predicted that VCZ increased the exposure of VEN by 4.5-9.6 fold. The increase in VEN exposure by VCZ was influenced by subject's CYP2C19 genotype. According to the therapeutic window, VEN dose should be reduced to 100 mg when co-administered with VCZ. CONCLUSION: The PBPK model developed here could support individual dose adjustment of VEN and DDI risk assessment. Predictions using the robust PBPK model confirmed that the 100 mg dose adjustment is still applicable in the presence of VCZ with high inter-individual viability.

Theory-based pharmacokinetics and pharmacodynamics of S- and R-warfarin and effects on international normalized ratio: influence of body size, composition and genotype in cardiac surgery patients.

AIMS: The aims of this study are to apply a theory-based mechanistic model to describe the pharmacokinetics (PK) and pharmacodynamics (PD) of S- and R-warfarin. METHODS: Clinical data were obtained from 264 patients. Total concentrations for S- and R-warfarin were measured by ultra-high performance liquid tandem mass spectrometry. Genotypes were measured using pyrosequencing. A sequential population PK parameter with data method was used to describe the international normalized ratio (INR) time course. Data were analyzed with NONMEM. Model evaluation was based on parameter plausibility and prediction-corrected visual predictive checks. RESULTS: Warfarin PK was described using a one-compartment model. CYP2C9 *1/*3 genotype had reduced clearance for S-warfarin, but increased clearance for R-warfarin. The in vitro parameters for the relationship between prothrombin complex activity (PCA) and INR were markedly different (A = 0.560, B = 0.386) from the theory-based values (A = 1, B = 0). There was a small difference between healthy subjects and patients. A sigmoid Emax PD model inhibiting PCA synthesis as a function of S-warfarin concentration predicted INR. Small R-warfarin effects was described by competitive antagonism of S-warfarin inhibition. Patients with VKORC1 AA and CYP4F2 CC or CT genotypes had lower C50 for S-warfarin. CONCLUSION: A theory-based PKPD model describes warfarin concentrations and clinical response. Expected PK and PD genotype effects were confirmed. The role of predicted fat free mass with theory-based allometric scaling of PK parameters was identified. R-warfarin had a minor effect compared with S-warfarin on PCA synthesis. INR is predictable from 1/PCA in vivo.

Development and validation of a sensitive quantification method for hematoporphyrin monomethyl ether in plasma using high-performance liquid chromatography with fluorescence detection.

A rapid, sensitive, precise and specific method for determination of hematoporphyrin monomethyl ether (HMME), a novel photodynamic therapy (PDT) drug, was developed and validated using high-performance liquid chromatography (HPLC) with fluorescence detection. HMME was isolated from the plasma by a single-step liquid-liquid extraction with ethyl acetate. The analyte and internal standard fluorescein were baseline separated on a Diamonsil C(18) analytical column (4.6 x 150 mm, 5 microm) and analyzed using a fluorescence detector with the excitation and emission wavelengths set at 395 and 613 nm, respectively. The method was linear in the concentration range 0.025-5 microg/mL with a lower limit of quantitation (LLOQ) of 10 ng/mL. The inter- and intra-day accuracies and precisions were all within 10% and the mean recoveries of HMME and fluorescein were 95 +/- 3.7 and 90 +/- 2.3%, respectively. The analyte was stable during all sample storage, preparation and analysis periods. This method was successfully applied to a pharmacokinetic study after a single-dose intravenous administration of HMME (5 mg/kg) to beagle dogs. This method was reproducible and sensitive enough for the pharmacokinetic study of HMME. Based on the results of the pharmacokinetic study, we suggest that a rather long light-avoiding time is essential for patients under HMME therapy.

Development of a HPLC-MS assay for ginsenoside Rh2, a new anti-tumor substance from natural product and its pharacokinetic study in dogs.

To develop a HPLC-MS method of determining ginsenoside Rh2 in dog plasma based on solid-phase extraction for pharmacokinetic studies. Six dogs were randomly assigned to two groups, either given 0.1 mg/kg dose intravenously or 1 mg/kg dose through oral gavage. Analysis using high performance liquid chromatography (HPLC) with ODS column, followed by detection with electrospray ionization(ESI) mass spectrometry(MS) in negative ion mode with 500 microM ammonium chloride in the mobile phase. The assays were validated over the concentration range of 2.0-1250.0 ng/ml in dog plasma. The intra- and inter- day precision were less than 10% in terms of RSD. The overall recovery was more than 80%. The validated assay was suitable for pharmacokinetic studies of ginsenoside Rh2 and the observed oral bioavailabilities of Rh2 were 17.6% and 24.8% for male and female dogs respectively.