Search

Natural language processing (NLP) is a branch of artificial intelligence, which combines computational linguistics, machine learning, and deep learning models to process human language. Although there is a surge in NLP usage across various industries in recent years, NLP has not been widely evaluated and utilized to support drug development. To demonstrate how advanced NLP can expedite the extraction and analyses of information to help address clinical pharmacology questions, inform clinical trial designs, and support drug development, three use cases are described in this article: (1) dose optimization strategy in oncology, (2) common covariates on pharmacokinetic (PK) parameters in oncology, and (3) physiologically‐based PK (PBPK) analyses for regulatory review and product label. The NLP workflow includes (1) preparation of source files, (2) NLP model building, and (3) automation of data extraction. The Clinical Pharmacology and Biopharmaceutics Summary Basis of Approval (SBA) documents, US package inserts (USPI), and approval letters from the US Food and Drug Administration (FDA) were used as our source data. As demonstrated in the three example use cases, advanced NLP can expedite the extraction and analyses of large amounts of information from regulatory review documents to help address important clinical pharmacology questions. Although this has not been adopted widely, integrating advanced NLP into the clinical pharmacology workflow can increase efficiency in extracting impactful information to advance drug development. [ABSTRACT FROM AUTHOR]

There is strong interest in developing predictive models to better understand individual heterogeneity and disease progression in Alzheimer's disease (AD). We have built upon previous longitudinal AD progression models, using a nonlinear, mixed‐effect modeling approach to predict Clinical Dementia Rating Scale – Sum of Boxes (CDR‐SB) progression. Data from the Alzheimer's Disease Neuroimaging Initiative (observational study) and placebo arms from four interventional trials (N = 1093) were used for model building. The placebo arms from two additional interventional trials (N = 805) were used for external model validation. In this modeling framework, CDR‐SB progression over the disease trajectory timescale was obtained for each participant by estimating disease onset time (DOT). Disease progression following DOT was described by both global progression rate (RATE) and individual progression rate (α). Baseline Mini‐Mental State Examination and CDR‐SB scores described the interindividual variabilities in DOT and α well. This model successfully predicted outcomes in the external validation datasets, supporting its suitability for prospective prediction and use in design of future trials. By predicting individual participants' disease progression trajectories using baseline characteristics and comparing these against the observed responses to new agents, the model can help assess treatment effects and support decision making for future trials. [ABSTRACT FROM AUTHOR]

Tocilizumab is a humanized anti-interleukin-6 receptor antibody for treating rheumatoid arthritis. Pharmacokinetic/pharmacodynamic analysis was performed on the 24-week double-blind parts of 2 randomized, controlled trials: SUMMACTA and BREVACTA. SUMMACTA compared subcutaneous tocilizumab 162 mg every week to intravenous tocilizumab 8 mg/kg every 4 weeks, whereas BREVACTA evaluated 162 mg subcutaneous tocilizumab every 2 weeks versus placebo. In addition to noncompartmental analysis, a 2-compartment population pharmacokinetic model, with first-order absorption (for subcutaneous) and linear and Michaelis-Menten elimination was used. Mean observed steady-state predose tocilizumab concentrations in week 24 were 40 and 7.4 μg/mL for subcutaneous every-week and every-2-week dosing, respectively, and 18 μg/mL for intravenous dosing. In the population PK model, body weight was an important covariate affecting clearance and volume of distribution. Mean ± SD population-predicted predose concentration for patients ≥100 kg was 23.0 ± 13.5 μg/mL for subcutaneous tocilizumab every week and 1.0 ± 1.6 μg/mL for every 2 weeks. Efficacy was lowest with subcutaneous every-2-week dosing in patients > 100 kg, reflecting lower exposure. The subcutaneous every-2-week regimen is not recommended for these patients. Pharmacodynamic responses were comparable for the every-week subcutaneous and every-4-week intravenous regimens and less pronounced with the every-2-week subcutaneous regimen. No trend was observed for increased adverse events with increasing tocilizumab exposure. The results of this analysis are consistent with the noninferiority of efficacy of the every-week subcutaneous regimen to the every-4-week intravenous regimen and the superiority of the every-2-week subcutaneous regimen to placebo. These results support the label recommendations for subcutaneous dosing of tocilizumab in rheumatoid arthritis patients. [ABSTRACT FROM AUTHOR]

Objectives: To determine s.c. tocilizumab (s.c.-TCZ) dosing regimens for systemic JIA (sJIA) and polyarticular JIA (pJIA)., Methods: In two 52-week phase 1 b trials, s.c.-TCZ (162 mg/dose) was administered to sJIA patients every week or every 2 weeks (every 10 days before interim analysis) and to pJIA patients every 2 weeks or every 3 weeks with body weight ≥30 kg or <30 kg, respectively. Primary end points were pharmacokinetics, pharmacodynamics and safety; efficacy was exploratory. Comparisons were made to data from phase 3 trials with i.v. tocilizumab (i.v.-TCZ) in sJIA and pJIA., Results: Study participants were 51 sJIA patients and 52 pJIA patients aged 1-17 years who received s.c.-TCZ. Steady-state minimum TCZ concentration (Ctrough) >5th percentile of that achieved with i.v.-TCZ was achieved by 49 (96%) sJIA and 52 (100%) pJIA patients. In both populations, pharmacodynamic markers of disease were similar between body weight groups. Improvements in Juvenile Arthritis DAS-71 were comparable between s.c.-TCZ and i.v.-TCZ. By week 52, 53% of sJIA patients and 31% of pJIA patients achieved clinical remission on treatment. Safety was consistent with that of i.v.-TCZ except for injection site reactions, reported by 41.2% and 28.8% of sJIA and pJIA patients, respectively. Infections were reported in 78.4% and 69.2% of patients, respectively. Two sJIA patients died; both deaths were considered to be related to TCZ., Conclusion: s.c.-TCZ provides exposure and risk/benefit profiles similar to those of i.v.-TCZ. S.c. administration provides an alternative administration route that is more convenient for patients and caregivers and that has potential for in-home use., Trial Registration: ClinicalTrials.gov, http://clinicaltrials.gov, NCT01904292 and NCT01904279., (© The Author(s) 2021. Published by Oxford University Press on behalf of the British Society for Rheumatology.)