Cargando…

An artificial neural network−pharmacokinetic model and its interpretation using Shapley additive explanations

We developed a method to apply artificial neural networks (ANNs) for predicting time‐series pharmacokinetics (PKs), and an interpretable the ANN‐PK model, which can explain the evidence of prediction by applying Shapley additive explanations (SHAP). A previous population PK (PopPK) model of cyclospo...

Descripción completa

Detalles Bibliográficos
Autores principales: Ogami, Chika, Tsuji, Yasuhiro, Seki, Hiroto, Kawano, Hideaki, To, Hideto, Matsumoto, Yoshiaki, Hosono, Hiroyuki
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley and Sons Inc. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8302242/
https://www.ncbi.nlm.nih.gov/pubmed/33955705
http://dx.doi.org/10.1002/psp4.12643
_version_ 1783726847902613504
author Ogami, Chika
Tsuji, Yasuhiro
Seki, Hiroto
Kawano, Hideaki
To, Hideto
Matsumoto, Yoshiaki
Hosono, Hiroyuki
author_facet Ogami, Chika
Tsuji, Yasuhiro
Seki, Hiroto
Kawano, Hideaki
To, Hideto
Matsumoto, Yoshiaki
Hosono, Hiroyuki
author_sort Ogami, Chika
collection PubMed
description We developed a method to apply artificial neural networks (ANNs) for predicting time‐series pharmacokinetics (PKs), and an interpretable the ANN‐PK model, which can explain the evidence of prediction by applying Shapley additive explanations (SHAP). A previous population PK (PopPK) model of cyclosporin A was used as the comparison model. The patients’ data were used for the ANN‐PK model input, and the output by ANN was the clearance (CL). The estimated CL value from the ANN were substituted into the one‐compartment with one‐order absorption model, the concentrations were calculated, and the parameters of ANN were updated by the back‐propagation method. Kernel SHAP was applied to the trained model and the SHAP value of each input was calculated. The root mean squared error for the PopPK model and the ANN‐PK model were 41.1 and 31.0 ng/ml, respectively. The goodness of fit plots for the ANN‐PK model represented more convergence to y = x compared with that for the PopPK model, with good model performance for the ANN‐PK model. The most influential factors on CL output were age and body weight from the evaluation using Kernel SHAP, and these factors were incorporated into the PopPK model as the significant covariates of CL. The ANN‐PK model could handle time‐series data and showed higher prediction accuracy then the conventional PopPK model, and the scientific validity for the model could be evaluated by applying SHAP. STUDY HIGHLIGHTS: WHAT IS THE CURRENT KNOWLEDGE ON THE TOPIC? WHAT QUESTION DID THIS STUDY ADDRESS? WHAT DOES THIS STUDY ADD TO OUR KNOWLEDGE? HOW MIGHT THIS CHANGE DRUG DISCOVERY, DEVELOPMENT, AND/OR THERAPEUTICS? We expect that our study will contribute to develop the interpretable ANN model, which can predict the time‐series PKs, drug efficacies, and side effects with high prediction performance.
format Online
Article
Text
id pubmed-8302242
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher John Wiley and Sons Inc.
record_format MEDLINE/PubMed
spelling pubmed-83022422021-07-28 An artificial neural network−pharmacokinetic model and its interpretation using Shapley additive explanations Ogami, Chika Tsuji, Yasuhiro Seki, Hiroto Kawano, Hideaki To, Hideto Matsumoto, Yoshiaki Hosono, Hiroyuki CPT Pharmacometrics Syst Pharmacol Research We developed a method to apply artificial neural networks (ANNs) for predicting time‐series pharmacokinetics (PKs), and an interpretable the ANN‐PK model, which can explain the evidence of prediction by applying Shapley additive explanations (SHAP). A previous population PK (PopPK) model of cyclosporin A was used as the comparison model. The patients’ data were used for the ANN‐PK model input, and the output by ANN was the clearance (CL). The estimated CL value from the ANN were substituted into the one‐compartment with one‐order absorption model, the concentrations were calculated, and the parameters of ANN were updated by the back‐propagation method. Kernel SHAP was applied to the trained model and the SHAP value of each input was calculated. The root mean squared error for the PopPK model and the ANN‐PK model were 41.1 and 31.0 ng/ml, respectively. The goodness of fit plots for the ANN‐PK model represented more convergence to y = x compared with that for the PopPK model, with good model performance for the ANN‐PK model. The most influential factors on CL output were age and body weight from the evaluation using Kernel SHAP, and these factors were incorporated into the PopPK model as the significant covariates of CL. The ANN‐PK model could handle time‐series data and showed higher prediction accuracy then the conventional PopPK model, and the scientific validity for the model could be evaluated by applying SHAP. STUDY HIGHLIGHTS: WHAT IS THE CURRENT KNOWLEDGE ON THE TOPIC? WHAT QUESTION DID THIS STUDY ADDRESS? WHAT DOES THIS STUDY ADD TO OUR KNOWLEDGE? HOW MIGHT THIS CHANGE DRUG DISCOVERY, DEVELOPMENT, AND/OR THERAPEUTICS? We expect that our study will contribute to develop the interpretable ANN model, which can predict the time‐series PKs, drug efficacies, and side effects with high prediction performance. John Wiley and Sons Inc. 2021-05-27 2021-07 /pmc/articles/PMC8302242/ /pubmed/33955705 http://dx.doi.org/10.1002/psp4.12643 Text en © 2021 The Authors. CPT: Pharmacometrics & Systems Pharmacology published by Wiley Periodicals LLC on behalf of American Society for Clinical Pharmacology and Therapeutics https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc-nd/4.0/ (https://creativecommons.org/licenses/by-nc-nd/4.0/) License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made.
spellingShingle Research
Ogami, Chika
Tsuji, Yasuhiro
Seki, Hiroto
Kawano, Hideaki
To, Hideto
Matsumoto, Yoshiaki
Hosono, Hiroyuki
An artificial neural network−pharmacokinetic model and its interpretation using Shapley additive explanations
title An artificial neural network−pharmacokinetic model and its interpretation using Shapley additive explanations
title_full An artificial neural network−pharmacokinetic model and its interpretation using Shapley additive explanations
title_fullStr An artificial neural network−pharmacokinetic model and its interpretation using Shapley additive explanations
title_full_unstemmed An artificial neural network−pharmacokinetic model and its interpretation using Shapley additive explanations
title_short An artificial neural network−pharmacokinetic model and its interpretation using Shapley additive explanations
title_sort artificial neural network−pharmacokinetic model and its interpretation using shapley additive explanations
topic Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8302242/
https://www.ncbi.nlm.nih.gov/pubmed/33955705
http://dx.doi.org/10.1002/psp4.12643
work_keys_str_mv AT ogamichika anartificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT tsujiyasuhiro anartificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT sekihiroto anartificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT kawanohideaki anartificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT tohideto anartificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT matsumotoyoshiaki anartificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT hosonohiroyuki anartificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT ogamichika artificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT tsujiyasuhiro artificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT sekihiroto artificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT kawanohideaki artificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT tohideto artificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT matsumotoyoshiaki artificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations
AT hosonohiroyuki artificialneuralnetworkpharmacokineticmodelanditsinterpretationusingshapleyadditiveexplanations