No abstract

The pharmacokinetic variability of lamotrigine (LTG) plays a significant role in its dosing requirements. Our goal here was to use noninvasive clinical parameters to predict the dose-adjusted concentrations (C/D ratio) of LTG based on machine learning (ML) algorithms. A total of 1141 therapeutic drug-monitoring measurements were used, 80% of which were randomly selected as the "derivation cohort" to develop the prediction algorithm, and the remaining 20% constituted the "validation cohort" to test the finally selected model. Fifteen ML models were optimized and evaluated by tenfold cross-validation on the "derivation cohort,” and were filtered by the mean absolute error (MAE). On the whole, the nonlinear models outperformed the linear models. The extra-trees’ regression algorithm delivered good performance, and was chosen to establish the predictive model. The important features were then analyzed and parameters of the model adjusted to develop the best prediction model, which accurately described the C/D ratio of LTG, especially in the intermediate-to-high range (≥ 22.1 μg mL−1 g−1 day), as illustrated by a minimal bias (mean relative error (%) =  + 3%), good precision (MAE = 8.7 μg mL−1 g−1 day), and a high percentage of predictions within ± 20% of the empirical values (60.47%). This is the first study, to the best of our knowledge, to use ML algorithms to predict the C/D ratio of LTG. The results here can help clinicians adjust doses of LTG administered to patients to minimize adverse reactions.

Lamotrigine (LTG) is a second-generation anti-epileptic drug widely used for focal and generalized seizures in adults and children, and as a first-line medication in pregnant women and women of childbearing age. However, LTG pharmacokinetics shows high inter-individual variability, thus potentially leading to therapeutic failure or side effects in patients. This prospective study aimed to establish a population pharmacokinetics model for LTG in Chinese patients with epilepsy and to investigate the effects of genetic variants in uridine diphosphate glucuronosyltransferase (UGT) 1A4, UGT2B7, MDR1, ABCG2, ABCC2, and SLC22A1, as well as non-genetic factors, on LTG pharmacokinetics. The study population consisted of 89 patients with epilepsy, with 419 concentrations of LTG. A nonlinear mixed effects model was implemented in NONMEM software. A one-compartment model with first-order input and first-order elimination was found to adequately characterize LTG concentration. The population estimates of the apparent volume of distribution (V/F) and apparent clearance (CL/F) were 12.7 L and 1.12 L/h, respectively. The use of valproic acid decreased CL/F by 38.5%, whereas the co-administration of rifampicin caused an increase in CL/F of 64.7%. The CL/F decreased by 52.5% in SLC22A1 -1222AA carriers. Patients with the ABCG2 -34AA genotype had a 42.0% decrease in V/F, whereas patients with the MDR1 -2677TT and C3435TT genotypes had a 136% increase in V/F. No obvious genetic effect of UGT enzymes was found relative to the concentrations of LTG in Chinese patients. Recommended dose regimens for patients with different gene polymorphisms and comedications were estimated on the basis of Monte Carlo simulations and the established model. These findings should be valuable for developing individualized dosage regimens in adult and adolescent Chinese patients 13–65 years of age.

No abstract

In article number 2000644, Changhu Xue, Xiangzhao Mao, and co‐workers develop a macroporous hydrogel dressing with antibacterial and anti‐inflammatory properties for accelerated wound healing. The hydrogel matrix is formed by hydrogen bonding and supramolecular complexation. The hydrogel shows outstanding biocompatibility and can significantly accelerate skin tissue regeneration and wound closure.