Background Voriconazole (VCZ) is a first-line treatment drug for invasive fungal disease, with narrow therapeutic window and significant inter-individual variability. VCZ is primarily metabolized by liver, which declines with age. For elderly patients, physiological and pathological factors lead to more pronounced fluctuations in VCZ plasma concentrations. Thus, it is crucial to establish a model that accurately predicts VCZ plasma concentration in elderly patients. Methods A retrospective study was performed incorporating 32 variables, including population pharmacokinetics (PPK) parameters derived from the PPK model. Recursive Feature Elimination with Cross-Validation was used for feature selection. Multiple algorithms were selected and combined into an ensemble model, and the model was interpreted by Shapley Additive exPlanations. Results The predictive performance of machine learning was greatly improved after inclusion of PPK parameters. The composition of XGBoost, RF, and CatBoost (1:1:8) with the highest R2 (0.828) was determined as the final ensemble model. Feature selection greatly simplified the model from 31 variables to 9 variables without compromising its performance. The R2, mean square error, mean absolute error, and accuracy (± 30%) of external validation were 0.633, 1.094, 2.286, and 71.05%, respectively. Conclusions Our study is the first to include PPK parameters as new factors for machine learning modeling to predict VCZ plasma concentrations in elderly patients. The model underwent optimization through feature selection. Our model provides a reference for individualized dosing of VCZ in clinical practice, enhancing the efficacy and safety of VCZ treatment in elderly patients. Keywords: voriconazole, elderly patients, machine learning, population pharmacokinetics, precision medicine

Abstract Aim: Enasidenib, an isocitrate dehydrogenase inhibitor (IDHI) that selectively inhibits IDHI-2, is currently approved for treating Acute Myelogenous Leukemia(AML). This study identified and characterized adverse events (AEs) significantly related to IDHI in treating AML and compared the differences of subgroups to provide clinical reference. Methods: AEs reports were collected from the United States Food and Drug Administration Adverse Event Reporting System(FAERS). Enasidenib’s AEs were collected from the third quarter of 2017 to the third quarter of 2024. The reporting odds ratio (ROR) and Bayesian confidence propagation neural network(BCPNN) were used to assess the reporting of AEs induced by enasidenib in treating AML. When the lower limit of the 95% confidence interval (CI) of ROR > 1.0 and (IC-2SD)＞0 was considered the threshold for a signal. Results: A total of 2098 AE reports were retrieved from FAERS. Reports for males were higher than females, and patients aged 65-85 years reported the highest number of AEs. Interestingly, 52 PTs in at least 3 cases were classified as unexpected AEs, such as fatigue, asthenia, platelet count decreased, full blood count decreased, dizziness, constipation, etc. There are similarities and differences in the presentation of enasidenib-related AEs in subgroups of different genders and ages. Conclusion: Gender-specific and age-specific patients should be concerned about the occurrence of appropriate AEs when taking enasidenib for AML. Our study provided evidence for enasidenib in the treatment of AML.