<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>62605</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1</pageFirst>
    <pageLast>11</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume>4</volume>
    <type>article</type>
    <publisherName>Frontiers Media SA</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Building virtual patients using simulation-based inference</title>
    <abstract language="eng">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 high-dimensional, 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 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 probability for alternative parametrizations. The learned distributions allow us to generate highly probable alternative virtual patient populations for rheumatoid arthritis, which could potentially enhance the assessment of drug candidates if used for in silico trials.</abstract>
    <parentTitle language="eng">Frontiers in Systems Biology</parentTitle>
    <identifier type="doi">10.3389/fsysb.2024.1444912</identifier>
    <identifier type="issn">2674-0702</identifier>
    <identifier type="urn">urn:nbn:de:kobv:b43-626050</identifier>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="opus_import_data">{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T00:50:13Z","timestamp":1726188613570},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T00:00:00Z","timestamp":1726099200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Syst. Biol."],"abstract":"&lt;jats:p&gt;In the context of &lt;jats:italic&gt;in silico&lt;\/jats:italic&gt; 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 high-dimensional, 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 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 probability for alternative parametrizations. The learned distributions allow us to generate highly probable alternative virtual patient populations for rheumatoid arthritis, which could potentially enhance the assessment of drug candidates if used for &lt;jats:italic&gt;in silico&lt;\/jats:italic&gt; trials.&lt;\/jats:p&gt;","DOI":"10.3389\/fsysb.2024.1444912","type":"journal-article","created":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T04:56:17Z","timestamp":1726116977000},"update-policy":"http:\/\/dx.doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Building virtual patients using simulation-based inference"],"prefix":"10.3389","volume":"4","author":[{"given":"Nathalie","family":"Paul","sequence":"first","affiliation":[]},{"given":"Venetia","family":"Karamitsou","sequence":"additional","affiliation":[]},{"given":"Clemens","family":"Giegerich","sequence":"additional","affiliation":[]},{"given":"Afshin","family":"Sadeghi","sequence":"additional","affiliation":[]},{"given":"Moritz","family":"L\u00fccke","sequence":"additional","affiliation":[]},{"given":"Britta","family":"Wagenhuber","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Kister","sequence":"additional","affiliation":[]},{"given":"Markus","family":"Rehberg","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2024,9,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10928-021-09790-9","article-title":"Recent applications of quantitative systems pharmacology and machine learning models across diseases","volume":"49","author":"Aghamiri","year":"2022","journal-title":"J. Pharmacokinet. Pharmacodyn."},{"key":"B2","doi-asserted-by":"publisher","first-page":"5576","DOI":"10.3390\/app11125576","article-title":"A digital twins machine learning model for forecasting disease progression in stroke patients","volume":"11","author":"Allen","year":"2021","journal-title":"Appl. Sci."},{"key":"B3","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1002\/psp4.12063","article-title":"Efficient generation and selection of virtual populations in quantitative systems pharmacology models","volume":"5","author":"Allen","year":"2016","journal-title":"CPT Pharmacometrics Syst. Pharmacol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"eabq4419","DOI":"10.1126\/scitranslmed.abq4419","article-title":"Additive efficacy of a bispecific anti\u2013TNF\/IL-6 nanobody compound in translational models of rheumatoid arthritis","volume":"15","author":"Biesemann","year":"2023","journal-title":"Sci. Transl. Med."},{"key":"B5","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s13073-019-0701-3","article-title":"Digital twins to personalize medicine","volume":"12","author":"Bj\u00f6rnsson","year":"2019","journal-title":"Genome Med."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1011406","article-title":"Simulation-based inference for efficient identification of generative models in connectomics","author":"Boelts","year":"2023","journal-title":"bioRxiv"},{"key":"B7","doi-asserted-by":"crossref","DOI":"10.1109\/IVWorkshops54471.2021.9669252","article-title":"Identification of vehicle dynamics parameters using simulation-based inference","volume-title":"2021 IEEE intelligent vehicles symposium workshops (IV workshops)","author":"Boyali","year":"2021"},{"key":"B8","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1002\/psp4.12463","article-title":"Applications of quantitative systems pharmacology in model-informed drug discovery: perspective on impact and opportunities","volume":"8","author":"Bradshaw","year":"2019","journal-title":"CPT Pharmacometrics Syst. Pharmacol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1136\/annrheumdis-2016-210310","article-title":"Efficacy and safety of sarilumab monotherapy versus adalimumab monotherapy for the treatment of patients with active rheumatoid arthritis (MONARCH): a randomised, double-blind, parallel-group phase III trial","volume":"76","author":"Burmester","year":"2017","journal-title":"Ann. Rheum. Dis."},{"key":"B10","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/pl00011391","article-title":"A trust region method based on interior point techniques for nonlinear programming","volume":"89","author":"Byrd","year":"2000","journal-title":"Math. Program."},{"key":"B11","doi-asserted-by":"publisher","first-page":"2486:129","DOI":"10.1007\/978-1-0716-2265-0_8","article-title":"Virtual populations for quantitative systems pharmacology models","author":"Cheng","year":"2022","journal-title":"Methods Mol. Biol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"30055","DOI":"10.1073\/pnas.1912789117","article-title":"The frontier of simulation-based inference","volume":"117","author":"Cranmer","year":"2020","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1430","DOI":"10.1111\/bcp.14451","article-title":"A framework for simplification of quantitative systems pharmacology models in clinical pharmacology","volume":"88","author":"Derbalah","year":"2022","journal-title":"Br. J. Clin. Pharmacol."},{"key":"B14","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1109\/tsmc.1979.4310090","article-title":"Pattern recognition with partly missing data","volume":"9","author":"Dixon","year":"1979","journal-title":"IEEE Trans. Syst. Man. Cybern. Syst."},{"key":"B15","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1002\/psp4.12559","article-title":"Potential issues with virtual populations when applied to nonlinear quantitative systems pharmacology models","volume":"9","author":"Duffull","year":"2020","journal-title":"CPT Pharmacometrics Syst. Pharmacol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/s10898-007-9172-y","article-title":"Improved scatter search for the global optimization of computationally expensive dynamic models","volume":"43","author":"Egea","year":"2009","journal-title":"J. Glob. Optim."},{"key":"B17","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1002\/psp4.12056","article-title":"A model qualification method for mechanistic physiological QSP models to support model-informed drug development","volume":"5","author":"Friedrich","year":"2016","journal-title":"CPT Pharmacometrics and Syst. Pharmacol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1136\/annrheumdis-2017-eular.4534","article-title":"FRI0227 Sarilumab significantly suppresses circulating biomarkers of bone resorption and cardiovascular risk compared with adalimumab: biomarker analysis from the phase 3 monarch study","volume":"76","author":"Gabay","year":"2017","journal-title":"Ann. Rheum. Dis."},{"key":"B19","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1186\/s13075-020-02163-6","article-title":"Sarilumab and adalimumab differential effects on bone remodelling and cardiovascular risk biomarkers, and predictions of treatment outcomes","volume":"22","author":"Gaby","year":"2020","journal-title":"Arthritis Res. and Ther."},{"key":"B20","article-title":"Automatic posterior transformation for likelihood-free inference","volume-title":"International conference on machine learning","author":"Greenberg","year":"2019"},{"key":"B21","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/s10928-012-9266-0","article-title":"In vitro to in vivo extrapolation and species response comparisons for drug-induced liver injury (DILI) using DILIsym\u2122: a mechanistic, mathematical model of DILI","volume":"39","author":"Howell","year":"2012","journal-title":"J. Pharmacokinet. Pharmacodyn."},{"key":"B22","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s10439-007-9410-y","article-title":"Integrating epidemiological data into a mechanistic model of type 2 diabetes: validating the prevalence of virtual patients","volume":"36","author":"Klinke","year":"2008","journal-title":"Ann. Biomed. Eng."},{"key":"B23","volume-title":"Bayesian statistics","author":"Lee","year":"1989"},{"key":"B24","article-title":"Benchmarking simulation-based inference","volume-title":"International conference on artificial intelligence and statistics","author":"Lueckmann","year":"2021"},{"key":"B25","doi-asserted-by":"publisher","first-page":"793908","DOI":"10.3389\/fonc.2022.793908","article-title":"From fitting the average to fitting the individual: a cautionary tale for mathematical modelers","volume":"12","author":"Luo","year":"2022","journal-title":"Front. Oncol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s10928-021-09786-5","article-title":"Machine learning-guided, big data-enabled, biomarker-based systems pharmacology: modeling the stochasticity of natural history and disease progression","volume":"49","author":"McComb","year":"2022","journal-title":"J. Pharmacokinet. Pharmacodyn."},{"key":"B27","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s10928-021-09787-4","article-title":"Generative adversarial networks for construction of virtual populations of mechanistic models: simulations to study Omecamtiv Mecarbil action","volume":"49","author":"Parikh","year":"2022","journal-title":"J. Pharmacokinet. Pharmacodyn."},{"key":"B28","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1007\/s40744-021-00361-5","article-title":"Identification of a rule to predict response to sarilumab in patients with rheumatoid arthritis using machine learning and clinical trial data","volume":"8","author":"Rehberg","year":"2021","journal-title":"Rheumatol. Ther."},{"key":"B29","article-title":"Estimating cosmological constraints from galaxy cluster abundance using simulation-based inference","volume-title":"ICML 2022 workshop on machine learning for astrophysics","author":"Reza","year":"2022"},{"key":"B30","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.pbiomolbio.2018.06.002","article-title":"Improving the generation and selection of virtual populations in quantitative systems pharmacology models","volume":"139","author":"Rieger","year":"2018","journal-title":"Prog. Biophys. Molec Bio"},{"key":"B31","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1186\/1471-2105-14-221","article-title":"Alternate virtual populations elucidate the type I interferon signature predictive of the response to rituximab in rheumatoid arthritis","volume":"14","author":"Schmidt","year":"2013","journal-title":"BMC Bioinforma."},{"key":"B32","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/S0378-4754(00)00270-6","article-title":"Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates","volume":"55","author":"Sobol","year":"2001","journal-title":"Math. Comput. SIMULAT"},{"key":"B33","volume-title":"Quantitative and systems pharmacology in the post-genomic era: new approaches to discovering drugs and understanding therapeutic","author":"Sorger","year":"2011"},{"key":"B34","first-page":"54","article-title":"Bootstrap methods for standard errors, confidence","volume":"27","author":"Tibshirani","year":"1986","journal-title":"Stat. Sci."},{"key":"B35","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1038\/clpt.2009.87","article-title":"A comprehensive model for the humoral coagulation network in humans","volume":"86","author":"Wajima","year":"2009","journal-title":"Clin. Pharmacol. Ther."},{"key":"B36","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s10928-022-09805-z","article-title":"Two heads are better than one: current landscape of integrating QSP and machine learning: an ISoP QSP SIG white paper by the working group on the integration of quantitative systems pharmacology and machine learning","volume":"49","author":"Zhang","year":"2022","journal-title":"J. Pharmacokinet. Pharmacodyn."}],"container-title":["Frontiers in Systems Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fsysb.2024.1444912\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T04:56:25Z","timestamp":1726116985000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fsysb.2024.1444912\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,12]]},"references-count":36,"alternative-id":["10.3389\/fsysb.2024.1444912"],"URL":"https:\/\/doi.org\/10.3389\/fsysb.2024.1444912","relation":{},"ISSN":["2674-0702"],"issn-type":[{"value":"2674-0702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,12]]}}}</enrichment>
    <enrichment key="local_crossrefDocumentType">journal-article</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="date_peer_review">24.02.2025</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Nathalie Paul</author>
    <author>Venetia Karamitsou</author>
    <author>Clemens Giegerich</author>
    <author>Afshin Sadeghi</author>
    <author>Moritz Lücke</author>
    <author>Britta Wagenhuber</author>
    <author>Alexander Kister</author>
    <author>Markus Rehberg</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Simulation-based inference</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Machine learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Artificial intelligence</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Virtual patients</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Pathophysiology</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Pharmacology</value>
    </subject>
    <collection role="ddc" number="628">Sanitär- und Kommunaltechnik; Umwelttechnik</collection>
    <collection role="themenfelder" number="">Umwelt</collection>
    <collection role="themenfelder" number="">Umwelt-Material-Interaktionen</collection>
    <collection role="literaturgattung" number="">Verlagsliteratur</collection>
    <collection role="fulltextaccess" number="">Datei für die Öffentlichkeit verfügbar ("Open Access")</collection>
    <collection role="unnumberedseries" number="">Wissenschaftliche Artikel der BAM</collection>
    <collection role="institutes" number="">VP Vizepräsident</collection>
    <collection role="institutes" number="">VP.1 eScience</collection>
    <thesisPublisher>Bundesanstalt für Materialforschung und -prüfung (BAM)</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-bam/files/62605/fsysb-04-1444912.pdf</file>
  </doc>
</export-example>
