The final, formatted version of the article will be published soon.
METHODS article
Front. Syst. Biol.
Sec. Translational Systems Biology and In Silico Trials
Volume 4 - 2024 |
doi: 10.3389/fsysb.2024.1444912
This article is part of the Research Topic Insights in Translational Systems Biology and In Silico Trials: 2023 View all 3 articles
Building Virtual Patients Using Simulation-Based Inference
Provisionally accepted- 1 Fraunhofer Institute for Intelligent Analysis and Information Systems, Sankt Augustin, North Rhine-Westphalia, Germany
- 2 Sanofi (Germany), Frankfurt, Hesse, Germany
- 3 Federal Institute for Materials Research and Testing (BAM), Berlin, Berlin, Germany
In the context of in silico clinical trials, mechanistic computer models for pathophysiology and pharmacology (here quantitative systems pharmacology models, QSP) can greatly support the decision making for drug candidates and elucidate the (potential) response of patients to existing and novel treatments. These models are built on disease mechanisms and then parametrized using (clinical study) data. Clinical variability among patients is represented by alternative model parameterizations, called virtual patients. Despite the complexity of disease modeling itself, using individual patient data to build these virtual patients is particularly challenging given the highdimensional, potentially sparse and noisy clinical trial data.In this work, we investigate the applicability of simulation-based inference (SBI), an advanced probabilistic machine learning approach, for virtual patient generation from individual patient data and we develop and evaluate the concept of nearest patient fits (SBI NPF), which further enhances the fitting performance. At the example of rheumatoid arthritis (RA), where prediction of treatment response is notoriously difficult, our experiments demonstrate that the SBI approaches can capture large inter-patient variability in clinical data and can compete with standard fitting methods in the field. Moreover, since SBI learns a probability distribution over the virtual patient parametrization, it naturally provides the probabilitylikelihood for alternative parametrizations. The learned distributions allow us to generate highly probable alternative virtual patient populations for rheumatoid arthritis, which could potentially enhance greatly improves a robustthe assessment of drug candiatecandidates predictions if used forin in silico clinical trials.
Keywords: Virtual patients, QSP modeling, individual patient fitting, machine learning, artificial intelligence, Simulation-based inference
Received: 06 Jun 2024; Accepted: 29 Aug 2024.
Copyright: © 2024 Paul, Karamitsou, Giegerich, Sadeghi, Lücke, Wagenhuber, Kister and Rehberg. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Markus Rehberg, Sanofi (Germany), Frankfurt, 65926, Hesse, Germany
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.