Low‐dimensional neural ordinary differential equations accounting for inter‐individual variability implemented in Monolix and NONMEM
Abstract Neural ordinary differential equations (NODEs) are an emerging machine learning (ML) method to model pharmacometric (PMX) data. Combining mechanism‐based components to describe “known parts” and neural networks to learn “unknown parts” is a promising ML‐based PMX approach. In this work, the...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | CPT: Pharmacometrics & Systems Pharmacology |
| Online Access: | https://doi.org/10.1002/psp4.13265 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841555893542453248 |
|---|---|
| author | Dominic Stefan Bräm Bernhard Steiert Marc Pfister Britta Steffens Gilbert Koch |
| author_facet | Dominic Stefan Bräm Bernhard Steiert Marc Pfister Britta Steffens Gilbert Koch |
| author_sort | Dominic Stefan Bräm |
| collection | DOAJ |
| description | Abstract Neural ordinary differential equations (NODEs) are an emerging machine learning (ML) method to model pharmacometric (PMX) data. Combining mechanism‐based components to describe “known parts” and neural networks to learn “unknown parts” is a promising ML‐based PMX approach. In this work, the implementation of low‐dimensional NODEs in two widely applied PMX software packages (Monolix and NONMEM) is explained. Inter‐individual variability is introduced to NODEs and proposals for the practical implementation of NODEs in such software are presented. The potential of such implementations is shown on various demonstrational datasets available in the Monolix model library, including pharmacokinetic (PK), pharmacodynamic (PD), target‐mediated drug disposition (TMDD), and survival analyses. All datasets were fitted with NODEs in Monolix and NONMEM and showed comparable results to classical modeling approaches. Model codes for demonstrated PK, PKPD, TMDD applications are made available, allowing a reproducible and straight‐forward implementation of NODEs in available PMX software packages. |
| format | Article |
| id | doaj-art-503cc0d687884a82b88b54637a4e5df6 |
| institution | Kabale University |
| issn | 2163-8306 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | CPT: Pharmacometrics & Systems Pharmacology |
| spelling | doaj-art-503cc0d687884a82b88b54637a4e5df62025-01-07T20:48:59ZengWileyCPT: Pharmacometrics & Systems Pharmacology2163-83062025-01-0114151610.1002/psp4.13265Low‐dimensional neural ordinary differential equations accounting for inter‐individual variability implemented in Monolix and NONMEMDominic Stefan Bräm0Bernhard Steiert1Marc Pfister2Britta Steffens3Gilbert Koch4Pediatric Pharmacology and Pharmacometrics, University Children's Hospital Basel (UKBB) University of Basel Basel SwitzerlandRoche Pharma Research and Early Development, Pharmaceutical Sciences Roche Innovation Center Basel, F. Hoffmann‐La Roche Ltd. Basel SwitzerlandPediatric Pharmacology and Pharmacometrics, University Children's Hospital Basel (UKBB) University of Basel Basel SwitzerlandPediatric Pharmacology and Pharmacometrics, University Children's Hospital Basel (UKBB) University of Basel Basel SwitzerlandPediatric Pharmacology and Pharmacometrics, University Children's Hospital Basel (UKBB) University of Basel Basel SwitzerlandAbstract Neural ordinary differential equations (NODEs) are an emerging machine learning (ML) method to model pharmacometric (PMX) data. Combining mechanism‐based components to describe “known parts” and neural networks to learn “unknown parts” is a promising ML‐based PMX approach. In this work, the implementation of low‐dimensional NODEs in two widely applied PMX software packages (Monolix and NONMEM) is explained. Inter‐individual variability is introduced to NODEs and proposals for the practical implementation of NODEs in such software are presented. The potential of such implementations is shown on various demonstrational datasets available in the Monolix model library, including pharmacokinetic (PK), pharmacodynamic (PD), target‐mediated drug disposition (TMDD), and survival analyses. All datasets were fitted with NODEs in Monolix and NONMEM and showed comparable results to classical modeling approaches. Model codes for demonstrated PK, PKPD, TMDD applications are made available, allowing a reproducible and straight‐forward implementation of NODEs in available PMX software packages.https://doi.org/10.1002/psp4.13265 |
| spellingShingle | Dominic Stefan Bräm Bernhard Steiert Marc Pfister Britta Steffens Gilbert Koch Low‐dimensional neural ordinary differential equations accounting for inter‐individual variability implemented in Monolix and NONMEM CPT: Pharmacometrics & Systems Pharmacology |
| title | Low‐dimensional neural ordinary differential equations accounting for inter‐individual variability implemented in Monolix and NONMEM |
| title_full | Low‐dimensional neural ordinary differential equations accounting for inter‐individual variability implemented in Monolix and NONMEM |
| title_fullStr | Low‐dimensional neural ordinary differential equations accounting for inter‐individual variability implemented in Monolix and NONMEM |
| title_full_unstemmed | Low‐dimensional neural ordinary differential equations accounting for inter‐individual variability implemented in Monolix and NONMEM |
| title_short | Low‐dimensional neural ordinary differential equations accounting for inter‐individual variability implemented in Monolix and NONMEM |
| title_sort | low dimensional neural ordinary differential equations accounting for inter individual variability implemented in monolix and nonmem |
| url | https://doi.org/10.1002/psp4.13265 |
| work_keys_str_mv | AT dominicstefanbram lowdimensionalneuralordinarydifferentialequationsaccountingforinterindividualvariabilityimplementedinmonolixandnonmem AT bernhardsteiert lowdimensionalneuralordinarydifferentialequationsaccountingforinterindividualvariabilityimplementedinmonolixandnonmem AT marcpfister lowdimensionalneuralordinarydifferentialequationsaccountingforinterindividualvariabilityimplementedinmonolixandnonmem AT brittasteffens lowdimensionalneuralordinarydifferentialequationsaccountingforinterindividualvariabilityimplementedinmonolixandnonmem AT gilbertkoch lowdimensionalneuralordinarydifferentialequationsaccountingforinterindividualvariabilityimplementedinmonolixandnonmem |