OutbreakFlow: Model-based Bayesian inference of disease outbreak dynamics with invertible neural networks and its application to the COVID-19 pandemics in Germany

Mathematical models in epidemiology are an indispensable tool to determine the dynamics and important characteristics of infectious diseases. Apart from their scientific merit, these models are often used to inform political decisions and interventional measures during an ongoing outbreak. However,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:PLoS computational biology 2021-10, Vol.17 (10), p.e1009472-e1009472
Hauptverfasser: Radev, Stefan T, Graw, Frederik, Chen, Simiao, Mutters, Nico T, Eichel, Vanessa M, Bärnighausen, Till, Köthe, Ullrich
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page e1009472
container_issue 10
container_start_page e1009472
container_title PLoS computational biology
container_volume 17
creator Radev, Stefan T
Graw, Frederik
Chen, Simiao
Mutters, Nico T
Eichel, Vanessa M
Bärnighausen, Till
Köthe, Ullrich
description Mathematical models in epidemiology are an indispensable tool to determine the dynamics and important characteristics of infectious diseases. Apart from their scientific merit, these models are often used to inform political decisions and interventional measures during an ongoing outbreak. However, reliably inferring the epidemical dynamics by connecting complex models to real data is still hard and requires either laborious manual parameter fitting or expensive optimization methods which have to be repeated from scratch for every application of a given model. In this work, we address this problem with a novel combination of epidemiological modeling with specialized neural networks. Our approach entails two computational phases: In an initial training phase, a mathematical model describing the epidemic is used as a coach for a neural network, which acquires global knowledge about the full range of possible disease dynamics. In the subsequent inference phase, the trained neural network processes the observed data of an actual outbreak and infers the parameters of the model in order to realistically reproduce the observed dynamics and reliably predict future progression. With its flexible framework, our simulation-based approach is applicable to a variety of epidemiological models. Moreover, since our method is fully Bayesian, it is designed to incorporate all available prior knowledge about plausible parameter values and returns complete joint posterior distributions over these parameters. Application of our method to the early Covid-19 outbreak phase in Germany demonstrates that we are able to obtain reliable probabilistic estimates for important disease characteristics, such as generation time, fraction of undetected infections, likelihood of transmission before symptom onset, and reporting delays using a very moderate amount of real-world observations.
doi_str_mv 10.1371/journal.pcbi.1009472
format Article
fullrecord <record><control><sourceid>gale_plos_</sourceid><recordid>TN_cdi_plos_journals_2598108576</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A681018464</galeid><doaj_id>oai_doaj_org_article_700dce7161f14b92b9338f3773914f5d</doaj_id><sourcerecordid>A681018464</sourcerecordid><originalsourceid>FETCH-LOGICAL-c715t-9e1c887d7d2784a8d7ce0c38bfced172d62228e66c3bca34c1ba8fd05a9a662f3</originalsourceid><addsrcrecordid>eNqVk99u0zAUxiMEYmPwBggscQMXKXGcxM4ukEZho9KgEv9uLcc-ad2ldrGdlb4OT4rbZtOKdoN8cSz7933H51gnSZ7jbIQJxW8XtndGdKOVbPQIZ1ld0PxBcozLkqSUlOzhnf1R8sT7RZbFbV09To5IUdUlxvg4-TPtQ-NAXJ13dn2KPlsFXdoIDwq9FxvwWhikTQsOjARkW6S0h3iN7KBDamPEUkuP1jrMI3sNLuimA2Sgd6KLIaytu_JIGIV0iHG16rQUQVuDgkVhDmg8_Tn5kOIarSIEOzdt0AW4pTCbp8mjVnQeng3xJPlx_vH7-FN6Ob2YjM8uU0lxGdIasGSMKqpyygrBFJWQScKaVoLCNFdVnucMqkqSRgpSSNwI1qqsFLWoqrwlJ8nLve-qs54P7fU8L2uGM1bSKhKTPaGsWPCV00vhNtwKzXcH1s24iMXLDjjNMiWB4gq3uGjqvKkJYS2hlNS4aEsVvd4N2fpmCZE1IXbrwPTwxug5n9lrzkpWUJpHg9eDgbO_evCBL7WX0HXCgO2372ZVUZKyLiL66h_0_uoGaiZiAfHTbcwrt6b8rIoQZkW19RrdQ8W1-zdroNXx_EDw5kAQmQC_w0z03vPJt6__wX45ZIs9K5313kF72zuc8e2E3BTJtxPChwmJshd3-34ruhkJ8hd7Lg5J</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2598108576</pqid></control><display><type>article</type><title>OutbreakFlow: Model-based Bayesian inference of disease outbreak dynamics with invertible neural networks and its application to the COVID-19 pandemics in Germany</title><source>MEDLINE</source><source>DOAJ Directory of Open Access Journals</source><source>Public Library of Science (PLoS) Journals Open Access</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><creator>Radev, Stefan T ; Graw, Frederik ; Chen, Simiao ; Mutters, Nico T ; Eichel, Vanessa M ; Bärnighausen, Till ; Köthe, Ullrich</creator><contributor>Tanaka, Mark M.</contributor><creatorcontrib>Radev, Stefan T ; Graw, Frederik ; Chen, Simiao ; Mutters, Nico T ; Eichel, Vanessa M ; Bärnighausen, Till ; Köthe, Ullrich ; Tanaka, Mark M.</creatorcontrib><description>Mathematical models in epidemiology are an indispensable tool to determine the dynamics and important characteristics of infectious diseases. Apart from their scientific merit, these models are often used to inform political decisions and interventional measures during an ongoing outbreak. However, reliably inferring the epidemical dynamics by connecting complex models to real data is still hard and requires either laborious manual parameter fitting or expensive optimization methods which have to be repeated from scratch for every application of a given model. In this work, we address this problem with a novel combination of epidemiological modeling with specialized neural networks. Our approach entails two computational phases: In an initial training phase, a mathematical model describing the epidemic is used as a coach for a neural network, which acquires global knowledge about the full range of possible disease dynamics. In the subsequent inference phase, the trained neural network processes the observed data of an actual outbreak and infers the parameters of the model in order to realistically reproduce the observed dynamics and reliably predict future progression. With its flexible framework, our simulation-based approach is applicable to a variety of epidemiological models. Moreover, since our method is fully Bayesian, it is designed to incorporate all available prior knowledge about plausible parameter values and returns complete joint posterior distributions over these parameters. Application of our method to the early Covid-19 outbreak phase in Germany demonstrates that we are able to obtain reliable probabilistic estimates for important disease characteristics, such as generation time, fraction of undetected infections, likelihood of transmission before symptom onset, and reporting delays using a very moderate amount of real-world observations.</description><identifier>ISSN: 1553-7358</identifier><identifier>ISSN: 1553-734X</identifier><identifier>EISSN: 1553-7358</identifier><identifier>DOI: 10.1371/journal.pcbi.1009472</identifier><identifier>PMID: 34695111</identifier><language>eng</language><publisher>United States: Public Library of Science</publisher><subject>Bayes Theorem ; Bayesian analysis ; Bayesian statistical decision theory ; Biology and Life Sciences ; Calibration ; Computer and Information Sciences ; Computer applications ; Control ; Coronaviruses ; COVID-19 ; COVID-19 - epidemiology ; Disease transmission ; Dynamics ; Epidemic models ; Epidemics ; Epidemiology ; Estimates ; Germany - epidemiology ; Humans ; Infectious diseases ; Knowledge acquisition ; Mathematical models ; Medicine and Health Sciences ; Methods ; Models, Biological ; Neural networks ; Neural Networks, Computer ; Optimization ; Ordinary differential equations ; Outbreaks ; Pandemics ; Parameter estimation ; Parameters ; People and places ; Public health ; Research and Analysis Methods ; Simulation ; Statistical inference ; Time series ; Uncertainty</subject><ispartof>PLoS computational biology, 2021-10, Vol.17 (10), p.e1009472-e1009472</ispartof><rights>COPYRIGHT 2021 Public Library of Science</rights><rights>2021 Radev et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2021 Radev et al 2021 Radev et al</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c715t-9e1c887d7d2784a8d7ce0c38bfced172d62228e66c3bca34c1ba8fd05a9a662f3</citedby><cites>FETCH-LOGICAL-c715t-9e1c887d7d2784a8d7ce0c38bfced172d62228e66c3bca34c1ba8fd05a9a662f3</cites><orcidid>0000-0002-1198-6632 ; 0000-0001-6036-1287 ; 0000-0002-4182-4212 ; 0000-0002-0156-9595 ; 0000-0003-3259-2920 ; 0000-0003-0555-2157 ; 0000-0002-6702-9559</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8584772/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8584772/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,864,885,2102,2928,23866,27924,27925,53791,53793,79600,79601</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/34695111$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><contributor>Tanaka, Mark M.</contributor><creatorcontrib>Radev, Stefan T</creatorcontrib><creatorcontrib>Graw, Frederik</creatorcontrib><creatorcontrib>Chen, Simiao</creatorcontrib><creatorcontrib>Mutters, Nico T</creatorcontrib><creatorcontrib>Eichel, Vanessa M</creatorcontrib><creatorcontrib>Bärnighausen, Till</creatorcontrib><creatorcontrib>Köthe, Ullrich</creatorcontrib><title>OutbreakFlow: Model-based Bayesian inference of disease outbreak dynamics with invertible neural networks and its application to the COVID-19 pandemics in Germany</title><title>PLoS computational biology</title><addtitle>PLoS Comput Biol</addtitle><description>Mathematical models in epidemiology are an indispensable tool to determine the dynamics and important characteristics of infectious diseases. Apart from their scientific merit, these models are often used to inform political decisions and interventional measures during an ongoing outbreak. However, reliably inferring the epidemical dynamics by connecting complex models to real data is still hard and requires either laborious manual parameter fitting or expensive optimization methods which have to be repeated from scratch for every application of a given model. In this work, we address this problem with a novel combination of epidemiological modeling with specialized neural networks. Our approach entails two computational phases: In an initial training phase, a mathematical model describing the epidemic is used as a coach for a neural network, which acquires global knowledge about the full range of possible disease dynamics. In the subsequent inference phase, the trained neural network processes the observed data of an actual outbreak and infers the parameters of the model in order to realistically reproduce the observed dynamics and reliably predict future progression. With its flexible framework, our simulation-based approach is applicable to a variety of epidemiological models. Moreover, since our method is fully Bayesian, it is designed to incorporate all available prior knowledge about plausible parameter values and returns complete joint posterior distributions over these parameters. Application of our method to the early Covid-19 outbreak phase in Germany demonstrates that we are able to obtain reliable probabilistic estimates for important disease characteristics, such as generation time, fraction of undetected infections, likelihood of transmission before symptom onset, and reporting delays using a very moderate amount of real-world observations.</description><subject>Bayes Theorem</subject><subject>Bayesian analysis</subject><subject>Bayesian statistical decision theory</subject><subject>Biology and Life Sciences</subject><subject>Calibration</subject><subject>Computer and Information Sciences</subject><subject>Computer applications</subject><subject>Control</subject><subject>Coronaviruses</subject><subject>COVID-19</subject><subject>COVID-19 - epidemiology</subject><subject>Disease transmission</subject><subject>Dynamics</subject><subject>Epidemic models</subject><subject>Epidemics</subject><subject>Epidemiology</subject><subject>Estimates</subject><subject>Germany - epidemiology</subject><subject>Humans</subject><subject>Infectious diseases</subject><subject>Knowledge acquisition</subject><subject>Mathematical models</subject><subject>Medicine and Health Sciences</subject><subject>Methods</subject><subject>Models, Biological</subject><subject>Neural networks</subject><subject>Neural Networks, Computer</subject><subject>Optimization</subject><subject>Ordinary differential equations</subject><subject>Outbreaks</subject><subject>Pandemics</subject><subject>Parameter estimation</subject><subject>Parameters</subject><subject>People and places</subject><subject>Public health</subject><subject>Research and Analysis Methods</subject><subject>Simulation</subject><subject>Statistical inference</subject><subject>Time series</subject><subject>Uncertainty</subject><issn>1553-7358</issn><issn>1553-734X</issn><issn>1553-7358</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><sourceid>DOA</sourceid><recordid>eNqVk99u0zAUxiMEYmPwBggscQMXKXGcxM4ukEZho9KgEv9uLcc-ad2ldrGdlb4OT4rbZtOKdoN8cSz7933H51gnSZ7jbIQJxW8XtndGdKOVbPQIZ1ld0PxBcozLkqSUlOzhnf1R8sT7RZbFbV09To5IUdUlxvg4-TPtQ-NAXJ13dn2KPlsFXdoIDwq9FxvwWhikTQsOjARkW6S0h3iN7KBDamPEUkuP1jrMI3sNLuimA2Sgd6KLIaytu_JIGIV0iHG16rQUQVuDgkVhDmg8_Tn5kOIarSIEOzdt0AW4pTCbp8mjVnQeng3xJPlx_vH7-FN6Ob2YjM8uU0lxGdIasGSMKqpyygrBFJWQScKaVoLCNFdVnucMqkqSRgpSSNwI1qqsFLWoqrwlJ8nLve-qs54P7fU8L2uGM1bSKhKTPaGsWPCV00vhNtwKzXcH1s24iMXLDjjNMiWB4gq3uGjqvKkJYS2hlNS4aEsVvd4N2fpmCZE1IXbrwPTwxug5n9lrzkpWUJpHg9eDgbO_evCBL7WX0HXCgO2372ZVUZKyLiL66h_0_uoGaiZiAfHTbcwrt6b8rIoQZkW19RrdQ8W1-zdroNXx_EDw5kAQmQC_w0z03vPJt6__wX45ZIs9K5313kF72zuc8e2E3BTJtxPChwmJshd3-34ruhkJ8hd7Lg5J</recordid><startdate>20211001</startdate><enddate>20211001</enddate><creator>Radev, Stefan T</creator><creator>Graw, Frederik</creator><creator>Chen, Simiao</creator><creator>Mutters, Nico T</creator><creator>Eichel, Vanessa M</creator><creator>Bärnighausen, Till</creator><creator>Köthe, Ullrich</creator><general>Public Library of Science</general><general>Public Library of Science (PLoS)</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>ISN</scope><scope>ISR</scope><scope>3V.</scope><scope>7QO</scope><scope>7QP</scope><scope>7TK</scope><scope>7TM</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8AL</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FH</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>CCPQU</scope><scope>COVID</scope><scope>DWQXO</scope><scope>FR3</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>K9.</scope><scope>LK8</scope><scope>M0N</scope><scope>M0S</scope><scope>M1P</scope><scope>M7P</scope><scope>P5Z</scope><scope>P62</scope><scope>P64</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope><scope>RC3</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-1198-6632</orcidid><orcidid>https://orcid.org/0000-0001-6036-1287</orcidid><orcidid>https://orcid.org/0000-0002-4182-4212</orcidid><orcidid>https://orcid.org/0000-0002-0156-9595</orcidid><orcidid>https://orcid.org/0000-0003-3259-2920</orcidid><orcidid>https://orcid.org/0000-0003-0555-2157</orcidid><orcidid>https://orcid.org/0000-0002-6702-9559</orcidid></search><sort><creationdate>20211001</creationdate><title>OutbreakFlow: Model-based Bayesian inference of disease outbreak dynamics with invertible neural networks and its application to the COVID-19 pandemics in Germany</title><author>Radev, Stefan T ; Graw, Frederik ; Chen, Simiao ; Mutters, Nico T ; Eichel, Vanessa M ; Bärnighausen, Till ; Köthe, Ullrich</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c715t-9e1c887d7d2784a8d7ce0c38bfced172d62228e66c3bca34c1ba8fd05a9a662f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Bayes Theorem</topic><topic>Bayesian analysis</topic><topic>Bayesian statistical decision theory</topic><topic>Biology and Life Sciences</topic><topic>Calibration</topic><topic>Computer and Information Sciences</topic><topic>Computer applications</topic><topic>Control</topic><topic>Coronaviruses</topic><topic>COVID-19</topic><topic>COVID-19 - epidemiology</topic><topic>Disease transmission</topic><topic>Dynamics</topic><topic>Epidemic models</topic><topic>Epidemics</topic><topic>Epidemiology</topic><topic>Estimates</topic><topic>Germany - epidemiology</topic><topic>Humans</topic><topic>Infectious diseases</topic><topic>Knowledge acquisition</topic><topic>Mathematical models</topic><topic>Medicine and Health Sciences</topic><topic>Methods</topic><topic>Models, Biological</topic><topic>Neural networks</topic><topic>Neural Networks, Computer</topic><topic>Optimization</topic><topic>Ordinary differential equations</topic><topic>Outbreaks</topic><topic>Pandemics</topic><topic>Parameter estimation</topic><topic>Parameters</topic><topic>People and places</topic><topic>Public health</topic><topic>Research and Analysis Methods</topic><topic>Simulation</topic><topic>Statistical inference</topic><topic>Time series</topic><topic>Uncertainty</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Radev, Stefan T</creatorcontrib><creatorcontrib>Graw, Frederik</creatorcontrib><creatorcontrib>Chen, Simiao</creatorcontrib><creatorcontrib>Mutters, Nico T</creatorcontrib><creatorcontrib>Eichel, Vanessa M</creatorcontrib><creatorcontrib>Bärnighausen, Till</creatorcontrib><creatorcontrib>Köthe, Ullrich</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Gale In Context: Canada</collection><collection>Gale In Context: Science</collection><collection>ProQuest Central (Corporate)</collection><collection>Biotechnology Research Abstracts</collection><collection>Calcium &amp; Calcified Tissue Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Nucleic Acids Abstracts</collection><collection>Health &amp; Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Computing Database (Alumni Edition)</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>Natural Science Collection</collection><collection>ProQuest One Community College</collection><collection>Coronavirus Research Database</collection><collection>ProQuest Central Korea</collection><collection>Engineering Research Database</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>ProQuest Health &amp; Medical Complete (Alumni)</collection><collection>ProQuest Biological Science Collection</collection><collection>Computing Database</collection><collection>Health &amp; Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Biological Science Database</collection><collection>Advanced Technologies &amp; Aerospace Database</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Collection</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>ProQuest Central Basic</collection><collection>Genetics Abstracts</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>PLoS computational biology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Radev, Stefan T</au><au>Graw, Frederik</au><au>Chen, Simiao</au><au>Mutters, Nico T</au><au>Eichel, Vanessa M</au><au>Bärnighausen, Till</au><au>Köthe, Ullrich</au><au>Tanaka, Mark M.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>OutbreakFlow: Model-based Bayesian inference of disease outbreak dynamics with invertible neural networks and its application to the COVID-19 pandemics in Germany</atitle><jtitle>PLoS computational biology</jtitle><addtitle>PLoS Comput Biol</addtitle><date>2021-10-01</date><risdate>2021</risdate><volume>17</volume><issue>10</issue><spage>e1009472</spage><epage>e1009472</epage><pages>e1009472-e1009472</pages><issn>1553-7358</issn><issn>1553-734X</issn><eissn>1553-7358</eissn><abstract>Mathematical models in epidemiology are an indispensable tool to determine the dynamics and important characteristics of infectious diseases. Apart from their scientific merit, these models are often used to inform political decisions and interventional measures during an ongoing outbreak. However, reliably inferring the epidemical dynamics by connecting complex models to real data is still hard and requires either laborious manual parameter fitting or expensive optimization methods which have to be repeated from scratch for every application of a given model. In this work, we address this problem with a novel combination of epidemiological modeling with specialized neural networks. Our approach entails two computational phases: In an initial training phase, a mathematical model describing the epidemic is used as a coach for a neural network, which acquires global knowledge about the full range of possible disease dynamics. In the subsequent inference phase, the trained neural network processes the observed data of an actual outbreak and infers the parameters of the model in order to realistically reproduce the observed dynamics and reliably predict future progression. With its flexible framework, our simulation-based approach is applicable to a variety of epidemiological models. Moreover, since our method is fully Bayesian, it is designed to incorporate all available prior knowledge about plausible parameter values and returns complete joint posterior distributions over these parameters. Application of our method to the early Covid-19 outbreak phase in Germany demonstrates that we are able to obtain reliable probabilistic estimates for important disease characteristics, such as generation time, fraction of undetected infections, likelihood of transmission before symptom onset, and reporting delays using a very moderate amount of real-world observations.</abstract><cop>United States</cop><pub>Public Library of Science</pub><pmid>34695111</pmid><doi>10.1371/journal.pcbi.1009472</doi><orcidid>https://orcid.org/0000-0002-1198-6632</orcidid><orcidid>https://orcid.org/0000-0001-6036-1287</orcidid><orcidid>https://orcid.org/0000-0002-4182-4212</orcidid><orcidid>https://orcid.org/0000-0002-0156-9595</orcidid><orcidid>https://orcid.org/0000-0003-3259-2920</orcidid><orcidid>https://orcid.org/0000-0003-0555-2157</orcidid><orcidid>https://orcid.org/0000-0002-6702-9559</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1553-7358
ispartof PLoS computational biology, 2021-10, Vol.17 (10), p.e1009472-e1009472
issn 1553-7358
1553-734X
1553-7358
language eng
recordid cdi_plos_journals_2598108576
source MEDLINE; DOAJ Directory of Open Access Journals; Public Library of Science (PLoS) Journals Open Access; EZB-FREE-00999 freely available EZB journals; PubMed Central
subjects Bayes Theorem
Bayesian analysis
Bayesian statistical decision theory
Biology and Life Sciences
Calibration
Computer and Information Sciences
Computer applications
Control
Coronaviruses
COVID-19
COVID-19 - epidemiology
Disease transmission
Dynamics
Epidemic models
Epidemics
Epidemiology
Estimates
Germany - epidemiology
Humans
Infectious diseases
Knowledge acquisition
Mathematical models
Medicine and Health Sciences
Methods
Models, Biological
Neural networks
Neural Networks, Computer
Optimization
Ordinary differential equations
Outbreaks
Pandemics
Parameter estimation
Parameters
People and places
Public health
Research and Analysis Methods
Simulation
Statistical inference
Time series
Uncertainty
title OutbreakFlow: Model-based Bayesian inference of disease outbreak dynamics with invertible neural networks and its application to the COVID-19 pandemics in Germany
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T13%3A24%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_plos_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=OutbreakFlow:%20Model-based%20Bayesian%20inference%20of%20disease%20outbreak%20dynamics%20with%20invertible%20neural%20networks%20and%20its%20application%20to%20the%20COVID-19%20pandemics%20in%20Germany&rft.jtitle=PLoS%20computational%20biology&rft.au=Radev,%20Stefan%20T&rft.date=2021-10-01&rft.volume=17&rft.issue=10&rft.spage=e1009472&rft.epage=e1009472&rft.pages=e1009472-e1009472&rft.issn=1553-7358&rft.eissn=1553-7358&rft_id=info:doi/10.1371/journal.pcbi.1009472&rft_dat=%3Cgale_plos_%3EA681018464%3C/gale_plos_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2598108576&rft_id=info:pmid/34695111&rft_galeid=A681018464&rft_doaj_id=oai_doaj_org_article_700dce7161f14b92b9338f3773914f5d&rfr_iscdi=true