Explore the vast range of titles available.

Pharmacometrics and the utilization of population pharmacokinetics play an integral role in model-informed drug discovery and development (MIDD). Recently, there has been a growth in the application of deep learning approaches to aid in areas within MIDD. In this study, a deep learning model, LSTM-ANN, was developed to predict olanzapine drug concentrations from the CATIE study. A total of 1527 olanzapine drug concentrations from 523 individuals along with 11 patient-specific covariates were used in model development. The hyperparameters of the LSTM-ANN model were optimized through a Bayesian optimization algorithm. A population pharmacokinetic model using the NONMEM model was constructed as a reference to compare to the performance of the LSTM-ANN model. The RMSE of the LSTM-ANN model was 29.566 in the validation set, while the RMSE of the NONMEM model was 31.129. Permutation importance revealed that age, sex, and smoking were highly influential covariates in the LSTM-ANN model. The LSTM-ANN model showed potential in the application of drug concentration predictions as it was able to capture the relationships within a sparsely sampled pharmacokinetic dataset and perform comparably to the NONMEM model.

We address the problem of model misspecification in population pharmacokinetics (PopPK), by modeling residual unexplained variability (RUV) by machine learning (ML) methods in a postprocessing step after conventional model building. The practical purpose of the method is the generation of realistic virtual patient profiles and the quantification of the extent of model misspecification, by introducing an appropriate metric, to be used as an additional diagnostic of model quality. The proposed methodology consists of the following steps: After developing a PopPK model, the individual residual errors IRES = DV–IPRED, are computed, where DV are the observations and IPRED the individual predictions and are modeled by ML to obtain IRESML. Correction of the IPREDs can then be carried out as DVML = IPRED + IRESML. The methodology was tested in a PK study of ropinirole, for which a PopPK model was developed while a second deliberately misspecified model was also considered. Various supervised ML algorithms were tested, among which Random Forest gave the best results. The ML model was able to correct individual predictions as inspected in diagnostic plots and most importantly it simulated realistic profiles that resembled the real data and canceled out the artifacts introduced by the elevated RUV, even in the case of the heavily misspecified model. Furthermore, a metric to quantify the extent of model misspecification was introduced based on the R2 between IRES and IRESML, following the rationale that the greater the extent of variability explained by the ML model, the higher the degree of model misspecification present in the original model.

Applying data mining and machine learning (ML) techniques to clinical data might identify predictive biomarkers for diabetic nephropathy (DN), a common complication of type 2 diabetes mellitus (T2DM). A retrospective analysis of the Action to Control Cardiovascular Risk in Diabetes (ACCORD) trial was intended to identify such factors using ML. The longitudinal data were stratified by time after patient enrollment to differentiate early and late predictors. Our results showed that Random Forest and Simple Logistic Regression methods exhibited the best performance among the evaluated algorithms. Baseline values for glomerular filtration rate (GFR), urinary creatinine, urinary albumin, potassium, cholesterol, low‐density lipoprotein, and urinary albumin to creatinine ratio were identified as DN predictors. Early predictors were the baseline values of GFR, systolic blood pressure, as well as fasting plasma glucose (FPG) and potassium at month 4. Changes per year in GFR, FPG, and triglycerides were recognized as predictors of late development. In conclusion, ML‐based methods successfully identified predictive factors for DN among patients with T2DM.

Purpose Although body composition has emerged as an important predictor of drug efficacy and toxicity, explanations for this association are unclear. Our goal was to investigate relationships between lean body mass (LBM), liver size/function and epirubicin pharmacokinetics (PK) and toxicity. Methods Data from a clinical study (n = 24) of patients with breast cancer receiving adjuvant intravenous FE₁₀₀C chemotherapy were used to examine relationships between LBM, liver size, and epirubicin clearance. Muscle tissue and liver mass were measured by analysis of computerized tomography cross-sectional images, and an extrapolation of muscle mass to total LBM compartment was employed. Population PK analysis of epirubicin was undertaken to test effects of body composition on epirubicin clearance and area under the curve (AUC). Results Estimated LBM was extremely variable in this cohort ranging from 32.9 to 67.3 kg. LBM was associated with neutrophil nadir (r = 0.5, P = 0.023), and mean LBM was lower for patients presenting with toxicity compared to those where toxicity was absent (41.6 vs. 56.2 kg, P = 0.002); 33% of variance in clearance was explained by LBM and aspartate aminotransferase (AST). Liver mass was not related to epirubicin clearance likely due to larger livers presenting with larger fat content, but liver attenuation (degree of fat infiltration) and AST were associated with AUC. Conclusion To our knowledge, this is the first study to examine relationships between LBM, liver mass/function and epirubicin PK and toxicity. This exploratory work investigates the notion of organs and tissues having distinctive contributions to the distribution and metabolism of antineoplastic drugs.

Clinical trial efficiency, defined as facilitating patient enrollment, and reducing the time to reach safety and efficacy decision points, is a critical driving factor for making improvements in therapeutic development. The present work evaluated a machine learning (ML) approach to improve phase II or proof‐of‐concept trials designed to address unmet medical needs in treating schizophrenia. Diagnostic data from the Clinical Antipsychotic Trials of Intervention Effectiveness (CATIE) trial were used to develop a binary classification ML model predicting individual patient response as either “improvement,” defined as greater than 20% reduction in total Positive and Negative Syndrome Scale (PANSS) score, or “no improvement,” defined as an inadequate treatment response (<20% reduction in total PANSS). A random forest algorithm performed best relative to other tree‐based approaches in model ability to classify patients after 6 months of treatment. Although model ability to identify true positives, a measure of model sensitivity, was poor (<0.2), its specificity, true negative rate, was high (0.948). A second model, adapted from the first, was subsequently applied as a proof‐of‐concept for the ML approach to supplement trial enrollment by identifying patients not expected to improve based on their baseline diagnostic scores. In three virtual trials applying this screening approach, the percentage of patients predicted to improve ranged from 46% to 48%, consistently approximately double the CATIE response rate of 22%. These results show the promising application of ML to improve clinical trial efficiency and, as such, ML models merit further consideration and development.

To assess ChatGPT 4.0 (ChatGPT) and Gemini Ultra 1.0 (Gemini) large language models on NONMEM coding tasks relevant to pharmacometrics and clinical pharmacology. ChatGPT and Gemini were assessed on tasks mimicking real-world applications of NONMEM. The tasks ranged from providing a curriculum for learning NONMEM, an overview of NONMEM code structure to generating code. Prompts in lay language to elicit NONMEM code for a linear pharmacokinetic (PK) model with oral administration and a more complex model with two parallel first-order absorption mechanisms were investigated. Reproducibility and the impact of “temperature” hyperparameter settings were assessed. The code was reviewed by two NONMEM experts. ChatGPT and Gemini provided NONMEM curriculum structures combining foundational knowledge with advanced concepts (e.g., covariate modeling and Bayesian approaches) and practical skills including NONMEM code structure and syntax. ChatGPT provided an informative summary of the NONMEM control stream structure and outlined the key NONMEM Translator (NM-TRAN) records needed. ChatGPT and Gemini were able to generate code blocks for the NONMEM control stream from the lay language prompts for the two coding tasks. The control streams contained focal structural and syntax errors that required revision before they could be executed without errors and warnings. The code output from ChatGPT and Gemini was not reproducible, and varying the temperature hyperparameter did not reduce the errors and omissions substantively. Large language models may be useful in pharmacometrics for efficiently generating an initial coding template for modeling projects. However, the output can contain errors and omissions that require correction.

Although clozapine is primarily used in a younger to mid-life population of patients with psychosis, there are limited data on the clinical pharmacology of clozapine later in life. The objective of this study was to assess the magnitude and variability of plasma concentrations of clozapine and norclozapine across the lifespan in a real-world clinical setting. A population pharmacokinetic study using nonlinear mixed effect modeling (NONMEM). Age, sex, height, weight, and dosage formulation were covariates. Inpatients and outpatients at the Centre for Addiction and Mental Health, Toronto, from 2001 to 2007. Patients ranging in ages from 11 to 79 with schizophrenia spectrum disorders and prescribed clozapine (Clozaril). A total of 1142 plasma clozapine and norclozapine concentrations (2,284 concentration measurements) from 391 patients with schizophrenia spectrum disorder. A one-compartment model with first-order absorption and elimination best described the data. The population predicted clearance of clozapine for females was 27.1 L/h (SE 11.1%) and 36.7 L/h (SE 9.7%) for males. For norclozapine, clearance in females was 48.6 L/h (SE 10.8%) and 63.1 L/h (SE 9.3%) in males. The only covariates with a significant effect on clearance were age and sex: clearance for both parent and metabolite decreased exponentially with age at least 39 years. Decreased clearance of clozapine and norclozapine with age results in increased blood concentrations and, hence, the potential for adverse drug reactions. These findings have particular clinical relevance for the dosing and safety monitoring of clozapine in older adults, highlighting a need for increased vigilance.

Authors’ Response to Letter to Editor from Hinpetch Daungsupawong and Viroj Wiwanitkit.

Relapsing-remitting dynamics are a hallmark of autoimmune diseases such as Multiple Sclerosis (MS). A clinical relapse in MS reflects an acute focal inflammatory event in the central nervous system that affects signal conduction by damaging myelinated axons. Those events are evident in T1-weighted post-contrast magnetic resonance imaging (MRI) as contrast enhancing lesions (CEL). CEL dynamics are considered unpredictable and are characterized by high intra- and inter-patient variability. Here, a population approach (nonlinear mixed-effects models) was applied to analyse of CEL progression, aiming to propose a model that adequately captures CEL dynamics. We explored several discrete distribution models to CEL counts observed in nine MS patients undergoing a monthly MRI for 48 months. All patients were enrolled in the study free of immunosuppressive drugs, except for intravenous methylprednisolone or oral prednisone taper for a clinical relapse. Analyses were performed with the nonlinear mixed-effect modelling software NONMEM 7.2. Although several models were able to adequately characterize the observed CEL dynamics, the negative binomial distribution model had the best predictive ability. Significant improvements in fitting were observed when the CEL counts from previous months were incorporated to predict the current month's CEL count. The predictive capacity of the model was validated using a second cohort of fourteen patients who underwent monthly MRIs during 6-months. This analysis also identified and quantified the effect of steroids for the relapse treatment. The model was able to characterize the observed relapsing-remitting CEL dynamic and to quantify the inter-patient variability. Moreover, the nature of the effect of steroid treatment suggested that this therapy helps resolve older CELs yet does not affect newly appearing active lesions in that month. This model could be used for design of future longitudinal studies and clinical trials, as well as for the evaluation of new therapies.