Nowcasting influenza epidemics using non‐homogeneous hidden Markov models
Identifieur interne : 001A76 ( Main/Exploration ); précédent : 001A75; suivant : 001A77Nowcasting influenza epidemics using non‐homogeneous hidden Markov models
Auteurs : Baltazar Nunes [Portugal] ; Isabel Natário [Portugal] ; M. Lucília Carvalho [Portugal]Source :
- Statistics in Medicine [ 0277-6715 ] ; 2013-07-10.
English descriptors
- Teeft :
- Activity state, Activity states, Algorithm, Available data, Bayesian, Bayesian approach, Bayesian inference, Carvalho, Carvalho table, Common part, Copyright, Countries upload, Covariates, Credible intervals, Current week, Diagonal matrix, Disease control, Disease surveillance, Early calculation, Early detection, Early estimate, Early information, Early observation, Early observations, Empirical knowledge, Entire data, Epidemic, Epidemic activity, Epidemic activity state, Epidemic period, Epidemic periods, Epidemic state, Epidemiological surveillance, European centre, European countries, European surveillance network, Family practice, Ffbs algorithm, Friday week, General practitioners, Generic terms, Gibbs algorithm, Gibbs sampler, Homogeneous model, Illness rate, Incidence rate, Incidence rates, Incomplete data, Initial distribution, Instituto nacional, Iteration, John wiley sons, Laboratorial component, Last panel, Lewis method, Logistic function, Main goal, Marginal likelihood, Markov, Markov chain, Markov chains, Markov model, Markov models, Matrix, Mcmc, Mcmc algorithm, Model parameters, Nasopharyngeal swabs, National health institute, Natural logarithm, Nonhomogeneous models, Normal distribution, Nowcast, Nowcasting, Nunes, Other hand, Oxford university press, Pandemic, Parameter, Portuguese surveillance system, Posterior distribution, Posterior probability, Present situation, Previous week, Prospective detection, Public health, Public health surveillance, Public health surveillance systems, Ricardo jorge, Same week, Sentinel networks, States sequence, Statist, Statistical methods, Surveillance, Surveillance data, Surveillance system, Surveillance systems, Time series, Timeliness, Total number, Transition probabilities, Wednesday week, Week figure, Week model, Weekly basis, Weekly number.
Abstract
Timeliness of a public health surveillance system is one of its most important characteristics. The process of predicting the present situation using available incomplete information from surveillance systems has received the term nowcasting and has high public health interest. Generally in Europe, general practitioners’ sentinel networks support the epidemiological surveillance of influenza activity, and each week's epidemiological bulletins are usually issued between Wednesday and Friday of the following week. In this work, we have developed a non‐homogeneous hidden Markov model (HMM) that, on a weekly basis, uses as covariates an early observation of influenza‐like illness (ILI) incidence rate and the number of ILI cases tested positive to nowcast the current week ILI rate and the probability that the influenza activity is in an epidemic state. We use Bayesian inference to find estimates of the model parameters and nowcasted quantities. The results obtained with data provided by the Portuguese influenza surveillance system show the additional value of using a non‐homogeneous HMM instead of a homogeneous one. The use of a non‐homogeneous HMM improves the surveillance system timeliness in 2 weeks. Copyright © 2012 John Wiley & Sons, Ltd.
Url:
DOI: 10.1002/sim.5670
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002103
- to stream Istex, to step Curation: 002103
- to stream Istex, to step Checkpoint: 000354
- to stream Main, to step Merge: 001A86
- to stream Main, to step Curation: 001A76
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Nowcasting influenza epidemics using non‐homogeneous hidden Markov models</title>
<author><name sortKey="Nunes, Baltazar" sort="Nunes, Baltazar" uniqKey="Nunes B" first="Baltazar" last="Nunes">Baltazar Nunes</name>
</author>
<author><name sortKey="Natario, Isabel" sort="Natario, Isabel" uniqKey="Natario I" first="Isabel" last="Natário">Isabel Natário</name>
</author>
<author><name sortKey="Lucilia Carvalho, M" sort="Lucilia Carvalho, M" uniqKey="Lucilia Carvalho M" first="M." last="Lucília Carvalho">M. Lucília Carvalho</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:C63BF2F9A2E209E3C945407AE95D51514A531272</idno>
<date when="2013" year="2013">2013</date>
<idno type="doi">10.1002/sim.5670</idno>
<idno type="url">https://api.istex.fr/ark:/67375/WNG-R4FT5ZX7-Z/fulltext.pdf</idno>
<idno type="wicri:Area/Istex/Corpus">002103</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">002103</idno>
<idno type="wicri:Area/Istex/Curation">002103</idno>
<idno type="wicri:Area/Istex/Checkpoint">000354</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000354</idno>
<idno type="wicri:doubleKey">0277-6715:2013:Nunes B:nowcasting:influenza:epidemics</idno>
<idno type="wicri:Area/Main/Merge">001A86</idno>
<idno type="wicri:Area/Main/Curation">001A76</idno>
<idno type="wicri:Area/Main/Exploration">001A76</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main">Nowcasting influenza epidemics using non‐homogeneous hidden Markov models</title>
<author><name sortKey="Nunes, Baltazar" sort="Nunes, Baltazar" uniqKey="Nunes B" first="Baltazar" last="Nunes">Baltazar Nunes</name>
<affiliation wicri:level="1"><country xml:lang="fr">Portugal</country>
<wicri:regionArea>Departmento de Epidemiologia, Instituto Nacional de Saúde Dr. Ricardo Jorge</wicri:regionArea>
<wicri:noRegion>Instituto Nacional de Saúde Dr. Ricardo Jorge</wicri:noRegion>
</affiliation>
<affiliation></affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Portugal</country>
</affiliation>
</author>
<author><name sortKey="Natario, Isabel" sort="Natario, Isabel" uniqKey="Natario I" first="Isabel" last="Natário">Isabel Natário</name>
<affiliation wicri:level="1"><country xml:lang="fr">Portugal</country>
<wicri:regionArea>CEAUL, Departmento de Matemática, Faculdade de Ciências e Tecnologia, Universidade Nova de Lisboa, 2829‐516, Caparica</wicri:regionArea>
<wicri:noRegion>Caparica</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Lucilia Carvalho, M" sort="Lucilia Carvalho, M" uniqKey="Lucilia Carvalho M" first="M." last="Lucília Carvalho">M. Lucília Carvalho</name>
<affiliation wicri:level="1"><country xml:lang="fr">Portugal</country>
<wicri:regionArea>CEAUL, Departamento de Estatística e Investigação Operacional, Faculdade de Ciências, Universidade de Lisboa</wicri:regionArea>
<wicri:noRegion>Universidade de Lisboa</wicri:noRegion>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j" type="main">Statistics in Medicine</title>
<title level="j" type="alt">STATISTICS IN MEDICINE</title>
<idno type="ISSN">0277-6715</idno>
<idno type="eISSN">1097-0258</idno>
<imprint><biblScope unit="vol">32</biblScope>
<biblScope unit="issue">15</biblScope>
<biblScope unit="page" from="2643">2643</biblScope>
<biblScope unit="page" to="2660">2660</biblScope>
<biblScope unit="page-count">18</biblScope>
<date type="published" when="2013-07-10">2013-07-10</date>
</imprint>
<idno type="ISSN">0277-6715</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0277-6715</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="Teeft" xml:lang="en"><term>Activity state</term>
<term>Activity states</term>
<term>Algorithm</term>
<term>Available data</term>
<term>Bayesian</term>
<term>Bayesian approach</term>
<term>Bayesian inference</term>
<term>Carvalho</term>
<term>Carvalho table</term>
<term>Common part</term>
<term>Copyright</term>
<term>Countries upload</term>
<term>Covariates</term>
<term>Credible intervals</term>
<term>Current week</term>
<term>Diagonal matrix</term>
<term>Disease control</term>
<term>Disease surveillance</term>
<term>Early calculation</term>
<term>Early detection</term>
<term>Early estimate</term>
<term>Early information</term>
<term>Early observation</term>
<term>Early observations</term>
<term>Empirical knowledge</term>
<term>Entire data</term>
<term>Epidemic</term>
<term>Epidemic activity</term>
<term>Epidemic activity state</term>
<term>Epidemic period</term>
<term>Epidemic periods</term>
<term>Epidemic state</term>
<term>Epidemiological surveillance</term>
<term>European centre</term>
<term>European countries</term>
<term>European surveillance network</term>
<term>Family practice</term>
<term>Ffbs algorithm</term>
<term>Friday week</term>
<term>General practitioners</term>
<term>Generic terms</term>
<term>Gibbs algorithm</term>
<term>Gibbs sampler</term>
<term>Homogeneous model</term>
<term>Illness rate</term>
<term>Incidence rate</term>
<term>Incidence rates</term>
<term>Incomplete data</term>
<term>Initial distribution</term>
<term>Instituto nacional</term>
<term>Iteration</term>
<term>John wiley sons</term>
<term>Laboratorial component</term>
<term>Last panel</term>
<term>Lewis method</term>
<term>Logistic function</term>
<term>Main goal</term>
<term>Marginal likelihood</term>
<term>Markov</term>
<term>Markov chain</term>
<term>Markov chains</term>
<term>Markov model</term>
<term>Markov models</term>
<term>Matrix</term>
<term>Mcmc</term>
<term>Mcmc algorithm</term>
<term>Model parameters</term>
<term>Nasopharyngeal swabs</term>
<term>National health institute</term>
<term>Natural logarithm</term>
<term>Nonhomogeneous models</term>
<term>Normal distribution</term>
<term>Nowcast</term>
<term>Nowcasting</term>
<term>Nunes</term>
<term>Other hand</term>
<term>Oxford university press</term>
<term>Pandemic</term>
<term>Parameter</term>
<term>Portuguese surveillance system</term>
<term>Posterior distribution</term>
<term>Posterior probability</term>
<term>Present situation</term>
<term>Previous week</term>
<term>Prospective detection</term>
<term>Public health</term>
<term>Public health surveillance</term>
<term>Public health surveillance systems</term>
<term>Ricardo jorge</term>
<term>Same week</term>
<term>Sentinel networks</term>
<term>States sequence</term>
<term>Statist</term>
<term>Statistical methods</term>
<term>Surveillance</term>
<term>Surveillance data</term>
<term>Surveillance system</term>
<term>Surveillance systems</term>
<term>Time series</term>
<term>Timeliness</term>
<term>Total number</term>
<term>Transition probabilities</term>
<term>Wednesday week</term>
<term>Week figure</term>
<term>Week model</term>
<term>Weekly basis</term>
<term>Weekly number</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract">Timeliness of a public health surveillance system is one of its most important characteristics. The process of predicting the present situation using available incomplete information from surveillance systems has received the term nowcasting and has high public health interest. Generally in Europe, general practitioners’ sentinel networks support the epidemiological surveillance of influenza activity, and each week's epidemiological bulletins are usually issued between Wednesday and Friday of the following week. In this work, we have developed a non‐homogeneous hidden Markov model (HMM) that, on a weekly basis, uses as covariates an early observation of influenza‐like illness (ILI) incidence rate and the number of ILI cases tested positive to nowcast the current week ILI rate and the probability that the influenza activity is in an epidemic state. We use Bayesian inference to find estimates of the model parameters and nowcasted quantities. The results obtained with data provided by the Portuguese influenza surveillance system show the additional value of using a non‐homogeneous HMM instead of a homogeneous one. The use of a non‐homogeneous HMM improves the surveillance system timeliness in 2 weeks. Copyright © 2012 John Wiley & Sons, Ltd.</div>
</front>
</TEI>
<affiliations><list><country><li>Portugal</li>
</country>
</list>
<tree><country name="Portugal"><noRegion><name sortKey="Nunes, Baltazar" sort="Nunes, Baltazar" uniqKey="Nunes B" first="Baltazar" last="Nunes">Baltazar Nunes</name>
</noRegion>
<name sortKey="Lucilia Carvalho, M" sort="Lucilia Carvalho, M" uniqKey="Lucilia Carvalho M" first="M." last="Lucília Carvalho">M. Lucília Carvalho</name>
<name sortKey="Natario, Isabel" sort="Natario, Isabel" uniqKey="Natario I" first="Isabel" last="Natário">Isabel Natário</name>
<name sortKey="Nunes, Baltazar" sort="Nunes, Baltazar" uniqKey="Nunes B" first="Baltazar" last="Nunes">Baltazar Nunes</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Sante/explor/SrasV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001A76 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001A76 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Sante |area= SrasV1 |flux= Main |étape= Exploration |type= RBID |clé= ISTEX:C63BF2F9A2E209E3C945407AE95D51514A531272 |texte= Nowcasting influenza epidemics using non‐homogeneous hidden Markov models }}
This area was generated with Dilib version V0.6.33. |