Deep‐NCA: A deep learning methodology for performing noncompartmental analysis of pharmacokinetic data

Abstract Noncompartmental analysis (NCA) is a model‐independent approach for assessing pharmacokinetics (PKs). Although the existing NCA algorithms are very well‐established and widely utilized, they suffer from low accuracies in the setting of sparse PK samples. In response, we developed Deep‐NCA,...

Full description

Saved in:
Bibliographic Details
Main Authors: Gengbo Liu, Logan Brooks, John Canty, Dan Lu, Jin Y. Jin, James Lu
Format: Article
Language:English
Published: Wiley 2024-05-01
Series:CPT: Pharmacometrics & Systems Pharmacology
Online Access:https://doi.org/10.1002/psp4.13124
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849421509846630400
author Gengbo Liu
Logan Brooks
John Canty
Dan Lu
Jin Y. Jin
James Lu
author_facet Gengbo Liu
Logan Brooks
John Canty
Dan Lu
Jin Y. Jin
James Lu
author_sort Gengbo Liu
collection DOAJ
description Abstract Noncompartmental analysis (NCA) is a model‐independent approach for assessing pharmacokinetics (PKs). Although the existing NCA algorithms are very well‐established and widely utilized, they suffer from low accuracies in the setting of sparse PK samples. In response, we developed Deep‐NCA, a deep learning (DL) model to improve the prediction of key noncompartmental PK parameters. Our methodology utilizes synthetic PK data for model training and uses an innovative patient‐specific normalization method for data preprocessing. Deep‐NCA demonstrated adequate performance across six previously unseen simulated drugs under multiple dosing, showcasing effective generalization. Compared to traditional NCA, Deep‐NCA exhibited superior performance for sparse PK data. This study advances the application of DL to PK studies and introduces an effective method for handling sparse PK data. With further validation and refinement, Deep‐NCA could significantly enhance the efficiency of drug development by providing more accurate NCA estimates while requiring fewer PK samples.
format Article
id doaj-art-0f1da517afe54d93b2c330aa4e23a06c
institution Kabale University
issn 2163-8306
language English
publishDate 2024-05-01
publisher Wiley
record_format Article
series CPT: Pharmacometrics & Systems Pharmacology
spelling doaj-art-0f1da517afe54d93b2c330aa4e23a06c2025-08-20T03:31:27ZengWileyCPT: Pharmacometrics & Systems Pharmacology2163-83062024-05-0113587087910.1002/psp4.13124Deep‐NCA: A deep learning methodology for performing noncompartmental analysis of pharmacokinetic dataGengbo Liu0Logan Brooks1John Canty2Dan Lu3Jin Y. Jin4James Lu5Modeling and Simulation/Clinical Pharmacology Genentech Inc. South San Francisco California USAModeling and Simulation/Clinical Pharmacology Genentech Inc. South San Francisco California USACancer Immunology Genentech Inc. South San Francisco California USAModeling and Simulation/Clinical Pharmacology Genentech Inc. South San Francisco California USAModeling and Simulation/Clinical Pharmacology Genentech Inc. South San Francisco California USAModeling and Simulation/Clinical Pharmacology Genentech Inc. South San Francisco California USAAbstract Noncompartmental analysis (NCA) is a model‐independent approach for assessing pharmacokinetics (PKs). Although the existing NCA algorithms are very well‐established and widely utilized, they suffer from low accuracies in the setting of sparse PK samples. In response, we developed Deep‐NCA, a deep learning (DL) model to improve the prediction of key noncompartmental PK parameters. Our methodology utilizes synthetic PK data for model training and uses an innovative patient‐specific normalization method for data preprocessing. Deep‐NCA demonstrated adequate performance across six previously unseen simulated drugs under multiple dosing, showcasing effective generalization. Compared to traditional NCA, Deep‐NCA exhibited superior performance for sparse PK data. This study advances the application of DL to PK studies and introduces an effective method for handling sparse PK data. With further validation and refinement, Deep‐NCA could significantly enhance the efficiency of drug development by providing more accurate NCA estimates while requiring fewer PK samples.https://doi.org/10.1002/psp4.13124
spellingShingle Gengbo Liu
Logan Brooks
John Canty
Dan Lu
Jin Y. Jin
James Lu
Deep‐NCA: A deep learning methodology for performing noncompartmental analysis of pharmacokinetic data
CPT: Pharmacometrics & Systems Pharmacology
title Deep‐NCA: A deep learning methodology for performing noncompartmental analysis of pharmacokinetic data
title_full Deep‐NCA: A deep learning methodology for performing noncompartmental analysis of pharmacokinetic data
title_fullStr Deep‐NCA: A deep learning methodology for performing noncompartmental analysis of pharmacokinetic data
title_full_unstemmed Deep‐NCA: A deep learning methodology for performing noncompartmental analysis of pharmacokinetic data
title_short Deep‐NCA: A deep learning methodology for performing noncompartmental analysis of pharmacokinetic data
title_sort deep nca a deep learning methodology for performing noncompartmental analysis of pharmacokinetic data
url https://doi.org/10.1002/psp4.13124
work_keys_str_mv AT gengboliu deepncaadeeplearningmethodologyforperformingnoncompartmentalanalysisofpharmacokineticdata
AT loganbrooks deepncaadeeplearningmethodologyforperformingnoncompartmentalanalysisofpharmacokineticdata
AT johncanty deepncaadeeplearningmethodologyforperformingnoncompartmentalanalysisofpharmacokineticdata
AT danlu deepncaadeeplearningmethodologyforperformingnoncompartmentalanalysisofpharmacokineticdata
AT jinyjin deepncaadeeplearningmethodologyforperformingnoncompartmentalanalysisofpharmacokineticdata
AT jameslu deepncaadeeplearningmethodologyforperformingnoncompartmentalanalysisofpharmacokineticdata