Objective: The aim of this study was to identify the important factors affecting cyclosporine (CsA) blood concentration and estimate CsA concentration using seven different machine learning (ML) algorithms. We also assessed the predictability of established ML models and previously built population pharmacokinetic (popPK) model. Finally, the most suitable ML model and popPK model to guide precision dosing were determined.Methods: In total, 3,407 whole-blood trough and peak concentrations of CsA were obtained from 183 patients who underwent initial renal transplantation. These samples were divided into model-building and evaluation sets. The model-building set was analyzed using seven different ML algorithms. The effects of potential covariates were evaluated using the least absolute shrinkage and selection operator algorithms. A separate evaluation set was used to assess the ability of all models to predict CsA blood concentration. R squared (R²) scores, median prediction error (MDPE), median absolute prediction error (MAPE), and the percentages of PE within 20% (F₂₀) and 30% (F₃₀) were calculated to assess the predictive performance of these models. In addition, previously built popPK model was included for comparison.Results: Sixteen variables were selected as important covariates. Among ML models, the predictive performance of nonlinear-based ML models was superior to that of linear regression (MDPE: 3.27%, MAPE: 34.21%, F₂₀: 30.63%, F₃₀: 45.03%, R² score: 0.68). The ML model built with the artificial neural network algorithm was considered the most suitable (MDPE: −0.039%, MAPE: 25.60%, F₂₀: 39.35%, F₃₀: 56.46%, R² score: 0.75). Its performance was superior to that of the previously built popPK model (MDPE: 5.26%, MAPE: 29.22%, F₂₀: 33.94%, F₃₀: 51.22%, R² score: 0.68). Furthermore, the application of the most suitable model and the popPK model in clinic showed that most dose regimen recommendations were reasonable.Conclusion: The performance of these ML models indicate that a nonlinear relationship for covariates may help to improve model predictability. These results might facilitate the application of ML models in clinic, especially for patients with unstable status or during initial dose optimization.

Human carboxylesterase 2 (CES2), one of the most abundant hydrolases distributed in the small intestine, has been validated as a key therapeutic target to ameliorate the intestinal toxicity caused by irinotecan. This study aims to discover efficacious CES2 inhibitors from natural products and to characterize the inhibition potentials and inhibitory mechanisms of the newly identified CES2 inhibitors. Following high-throughput screening and evaluation of the inhibition potency of more than 100 natural products against CES2, it was found that the biflavones isolated from Ginkgo biloba displayed extremely potent CES2 inhibition activities and high specificity over CES1 (>1000-fold). Further investigation showed that ginkgetin, bilobetin, sciadopitysin and isoginkgetin potently inhibited CES2-catalyzed hydrolysis of various substrates, including the CES2 substrate-drug irinotecan. Notably, the inhibition potentials of four biflavones against CES2 were more potent than that of loperamide, a marketed anti-diarrhea agent used for alleviating irinotecan-induced intestinal toxicity. Inhibition kinetic analyses demonstrated that ginkgetin, bilobetin, sciadopitysin and isoginkgetin potently inhibited CES2-catalyzed fluorescein diacetate hydrolysis via a reversible and mixed inhibition manner, with K_i values of less than 100 nM. Ensemble docking and molecular dynamics revealed that these biflavones could tightly and stably bind on the catalytic cavity of CES2 via hydrogen bonding and π-π stacking interactions, while the interactions with CES1 were awfully poor. Collectively, this study reports that the biflavones isolated from Ginkgo biloba are potent and highly specific CES2 inhibitors, which offers several promising lead compounds for developing novel anti-diarrhea agent to alleviate irinotecan-induced diarrhea.

Objective: Several population pharmacokinetic (popPK) models have been developed to determine the sources of methotrexate (MTX) PK variability. It remains unknown if these published models are precise enough for use or if a new model needs to be built. The aims of this study were to 1) assess the predictability of published models and 2) analyze the potential risk factors for delayed MTX elimination.Methods: A total of 1458 MTX plasma concentrations, including 377 courses (1–17 per patient), were collected from 77 patients who were receiving high-dose MTX for the treatment of primary central nervous system lymphoma in Huashan Hospital. PopPK analysis was performed using the NONMEM® software package. Previously published popPK models were selected and rebuilt. A new popPK model was then constructed to screen potential covariates using a stepwise approach. The covariates were included based on the combination of theoretical mechanisms and data properties. Goodness-of-fit plots, bootstrap, and prediction- and simulation-based diagnostics were used to determine the stability and predictive performance of both the published and newly built models. Monte Carlo simulations were conducted to qualify the influence of risk factors on the incidence of delayed elimination.Results: Among the eight evaluated published models, none presented acceptable values of bias or inaccuracy. A two-compartment model was employed in the newly built model to describe the PK of MTX. The estimated mean clearance (CL/F) was 4.91 L h⁻¹ (relative standard error: 3.7%). Creatinine clearance, albumin, and age were identified as covariates of MTX CL/F. The median and median absolute prediction errors of the final model were -10.2 and 36.4%, respectively. Results of goodness-of-fit plots, bootstrap, and prediction-corrected visual predictive checks indicated the high predictability of the final model.Conclusions: Current published models are not sufficiently reliable for cross-center use. The elderly patients and those with renal dysfunction, hypoalbuminemia are at higher risk of delayed elimination.

Background. Functional health literacy (FHL) is increasingly recognized as a useful predictor of health outcomes in different populations. However, the effect of FHL on medication knowledge and medication discrepancy in Chinese Americans is not well defined. Objectives. To examine the effects of FHL on medication knowledge and medication discrepancy in Chinese American patients. Methods. This was a cross-sectional study conducted at an academic internal medicine clinic. The Short Test of Functional Health Literacy in Adults was used to assess participants’ FHL. Data for patients’ demographic information, medication knowledge, and medication discrepancy (direction discrepancy and name discrepancy) were collected through patient interviews and chart reviews. The primary outcome was medication knowledge of purpose and the secondary outcomes included medication direction discrepancy and medication name discrepancy. Results. Of the 158 Chinese American patients who participated in the study, 54% had adequate FHL. More participants with adequate FHL had correct medication knowledge compared to participants with inadequate FHL (87% vs 56%, respectively, odds ratio = 3.4, 95% confidence interval = 1.2-9.7). Fewer participants with adequate FHL had medication direction discrepancy compared to those with inadequate FHL (42% vs 62%, odds ratio = 0.18, 95% confidence interval = 0.06-0.55). Both adequate and inadequate FHL groups had high prevalence of medication name discrepancy (77% vs 89%) even though the between-group difference was insignificant. Conclusions. Adequate FHL among Chinese American patients is significantly associated with increased medication knowledge of purpose and decreased medication direction discrepancy. Both adequate and inadequate FHL groups had high prevalence of medication name discrepancy.