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]

Drug development for idiopathic pulmonary fibrosis (IPF) has been challenging due to poorly understood disease etiology, unpredictable disease progression, highly heterogeneous patient populations, and a lack of robust pharmacodynamic biomarkers. Moreover, because lung biopsy is invasive and dangerous, making the extent of fibrosis as a direct longitudinal measurement of IPF disease progression unfeasible, most clinical trials studying IPF can only assess progression of fibrosis indirectly through surrogate measures. This review discusses current state-of-art practices, identifies knowledge gaps, and brainstorms development opportunities for preclinical to clinical translation, clinical populations, pharmacodynamic endpoints, and dose optimization strategies. This article highlights clinical pharmacology perspectives in leveraging real-world data as well as modeling and simulation, special population considerations, and patient-centric approaches for designing future studies. [ABSTRACT FROM AUTHOR]

Purpose: This study aimed at evaluating if pharmacokinetic and pharmacodynamic data from the first few patients treated with an investigational monoclonal antibody in a dose-escalation study can be used to guide the early initiation of potentially more efficacious combination regimens.Methods: Emerging pharmacokinetic and pharmacodynamic data from the first nine patients treated with lumretuzumab (a glycoengineered anti-HER3 monoclonal antibody) monotherapy at doses from 100 to 400 mg q2w were used along with a pharmacokinetic model that incorporated target-mediated drug disposition to guide the selection of the starting dose for use in combination regimens.Results: The dose-escalation study investigated lumretuzumab doses up to 2000 mg q2w and a maximum tolerated dose was not reached. However, the model described in this report predicted linear lumretuzumab pharmacokinetics and >95% target saturation at doses ≥400 mg q2w. These data, along with safety data, contributed to the decision to begin dose-escalation studies in combination with cetuximab and erlotinib using a starting dose of 400 mg lumretuzumab. Pharmacokinetic data from patients treated with lumretuzumab 400-2000 mg q2w in combination regimens were consistent with the model predictions.Conclusion: PK/PD modelling of emerging clinical data might accelerate development programs by enabling additional parts of a trial to commence before completion of the monotherapy part. The dose and schedule of lumretuzumab were optimised for concomitant therapy at doses substantially below the highest dose investigated. [ABSTRACT FROM AUTHOR]