Toward unsupervised outbreak detection through visual perception of new patterns.
Identifieur interne : 000488 ( Main/Corpus ); précédent : 000487; suivant : 000489Toward unsupervised outbreak detection through visual perception of new patterns.
Auteurs : Pierre P. Lévy ; Alain-Jacques ValleronSource :
- BMC public health [ 1471-2458 ] ; 2009.
English descriptors
- KwdEn :
- Databases, Factual (MeSH), Disease (classification), Disease Outbreaks (MeSH), Emergency Service, Hospital (MeSH), Family Practice (MeSH), Female (MeSH), France (epidemiology), Humans (MeSH), Male (MeSH), Natural Language Processing (MeSH), Pattern Recognition, Visual (MeSH), Population Surveillance (methods), Retrospective Studies (MeSH), Sentinel Surveillance (MeSH), Vocabulary, Controlled (MeSH).
- MESH :
- geographic , epidemiology : France.
- classification : Disease.
- methods : Population Surveillance.
- Databases, Factual, Disease Outbreaks, Emergency Service, Hospital, Family Practice, Female, Humans, Male, Natural Language Processing, Pattern Recognition, Visual, Retrospective Studies, Sentinel Surveillance, Vocabulary, Controlled.
Abstract
BACKGROUND
Statistical algorithms are routinely used to detect outbreaks of well-defined syndromes, such as influenza-like illness. These methods cannot be applied to the detection of emerging diseases for which no preexisting information is available.This paper presents a method aimed at facilitating the detection of outbreaks, when there is no a priori knowledge of the clinical presentation of cases.
METHODS
The method uses a visual representation of the symptoms and diseases coded during a patient consultation according to the International Classification of Primary Care 2nd version (ICPC-2). The surveillance data are transformed into color-coded cells, ranging from white to red, reflecting the increasing frequency of observed signs. They are placed in a graphic reference frame mimicking body anatomy. Simple visual observation of color-change patterns over time, concerning a single code or a combination of codes, enables detection in the setting of interest.
RESULTS
The method is demonstrated through retrospective analyses of two data sets: description of the patients referred to the hospital by their general practitioners (GPs) participating in the French Sentinel Network and description of patients directly consulting at a hospital emergency department (HED).Informative image color-change alert patterns emerged in both cases: the health consequences of the August 2003 heat wave were visualized with GPs' data (but passed unnoticed with conventional surveillance systems), and the flu epidemics, which are routinely detected by standard statistical techniques, were recognized visually with HED data.
CONCLUSION
Using human visual pattern-recognition capacities to detect the onset of unexpected health events implies a convenient image representation of epidemiological surveillance and well-trained "epidemiology watchers". Once these two conditions are met, one could imagine that the epidemiology watchers could signal epidemiological alerts, based on "image walls" presenting the local, regional and/or national surveillance patterns, with specialized field epidemiologists assigned to validate the signals detected.
DOI: 10.1186/1471-2458-9-179
PubMed: 19515246
PubMed Central: PMC2706246
Links to Exploration step
pubmed:19515246Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Toward unsupervised outbreak detection through visual perception of new patterns.</title>
<author><name sortKey="Levy, Pierre P" sort="Levy, Pierre P" uniqKey="Levy P" first="Pierre P" last="Lévy">Pierre P. Lévy</name>
<affiliation><nlm:affiliation>Assistance Publique-Hôpitaux de Paris, Hôpital Tenon, Département de Santé Publique, Paris, France. levy@u707.jussieu.fr</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Valleron, Alain Jacques" sort="Valleron, Alain Jacques" uniqKey="Valleron A" first="Alain-Jacques" last="Valleron">Alain-Jacques Valleron</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2009">2009</date>
<idno type="RBID">pubmed:19515246</idno>
<idno type="pmid">19515246</idno>
<idno type="doi">10.1186/1471-2458-9-179</idno>
<idno type="pmc">PMC2706246</idno>
<idno type="wicri:Area/Main/Corpus">000488</idno>
<idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Corpus" wicri:corpus="PubMed">000488</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Toward unsupervised outbreak detection through visual perception of new patterns.</title>
<author><name sortKey="Levy, Pierre P" sort="Levy, Pierre P" uniqKey="Levy P" first="Pierre P" last="Lévy">Pierre P. Lévy</name>
<affiliation><nlm:affiliation>Assistance Publique-Hôpitaux de Paris, Hôpital Tenon, Département de Santé Publique, Paris, France. levy@u707.jussieu.fr</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Valleron, Alain Jacques" sort="Valleron, Alain Jacques" uniqKey="Valleron A" first="Alain-Jacques" last="Valleron">Alain-Jacques Valleron</name>
</author>
</analytic>
<series><title level="j">BMC public health</title>
<idno type="eISSN">1471-2458</idno>
<imprint><date when="2009" type="published">2009</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Databases, Factual (MeSH)</term>
<term>Disease (classification)</term>
<term>Disease Outbreaks (MeSH)</term>
<term>Emergency Service, Hospital (MeSH)</term>
<term>Family Practice (MeSH)</term>
<term>Female (MeSH)</term>
<term>France (epidemiology)</term>
<term>Humans (MeSH)</term>
<term>Male (MeSH)</term>
<term>Natural Language Processing (MeSH)</term>
<term>Pattern Recognition, Visual (MeSH)</term>
<term>Population Surveillance (methods)</term>
<term>Retrospective Studies (MeSH)</term>
<term>Sentinel Surveillance (MeSH)</term>
<term>Vocabulary, Controlled (MeSH)</term>
</keywords>
<keywords scheme="MESH" type="geographic" qualifier="epidemiology" xml:lang="en"><term>France</term>
</keywords>
<keywords scheme="MESH" qualifier="classification" xml:lang="en"><term>Disease</term>
</keywords>
<keywords scheme="MESH" qualifier="methods" xml:lang="en"><term>Population Surveillance</term>
</keywords>
<keywords scheme="MESH" xml:lang="en"><term>Databases, Factual</term>
<term>Disease Outbreaks</term>
<term>Emergency Service, Hospital</term>
<term>Family Practice</term>
<term>Female</term>
<term>Humans</term>
<term>Male</term>
<term>Natural Language Processing</term>
<term>Pattern Recognition, Visual</term>
<term>Retrospective Studies</term>
<term>Sentinel Surveillance</term>
<term>Vocabulary, Controlled</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en"><p><b>BACKGROUND</b>
</p>
<p>Statistical algorithms are routinely used to detect outbreaks of well-defined syndromes, such as influenza-like illness. These methods cannot be applied to the detection of emerging diseases for which no preexisting information is available.This paper presents a method aimed at facilitating the detection of outbreaks, when there is no a priori knowledge of the clinical presentation of cases.</p>
</div>
<div type="abstract" xml:lang="en"><p><b>METHODS</b>
</p>
<p>The method uses a visual representation of the symptoms and diseases coded during a patient consultation according to the International Classification of Primary Care 2nd version (ICPC-2). The surveillance data are transformed into color-coded cells, ranging from white to red, reflecting the increasing frequency of observed signs. They are placed in a graphic reference frame mimicking body anatomy. Simple visual observation of color-change patterns over time, concerning a single code or a combination of codes, enables detection in the setting of interest.</p>
</div>
<div type="abstract" xml:lang="en"><p><b>RESULTS</b>
</p>
<p>The method is demonstrated through retrospective analyses of two data sets: description of the patients referred to the hospital by their general practitioners (GPs) participating in the French Sentinel Network and description of patients directly consulting at a hospital emergency department (HED).Informative image color-change alert patterns emerged in both cases: the health consequences of the August 2003 heat wave were visualized with GPs' data (but passed unnoticed with conventional surveillance systems), and the flu epidemics, which are routinely detected by standard statistical techniques, were recognized visually with HED data.</p>
</div>
<div type="abstract" xml:lang="en"><p><b>CONCLUSION</b>
</p>
<p>Using human visual pattern-recognition capacities to detect the onset of unexpected health events implies a convenient image representation of epidemiological surveillance and well-trained "epidemiology watchers". Once these two conditions are met, one could imagine that the epidemiology watchers could signal epidemiological alerts, based on "image walls" presenting the local, regional and/or national surveillance patterns, with specialized field epidemiologists assigned to validate the signals detected.</p>
</div>
</front>
</TEI>
<pubmed><MedlineCitation Status="MEDLINE" Owner="NLM"><PMID Version="1">19515246</PMID>
<DateCompleted><Year>2009</Year>
<Month>09</Month>
<Day>28</Day>
</DateCompleted>
<DateRevised><Year>2018</Year>
<Month>11</Month>
<Day>13</Day>
</DateRevised>
<Article PubModel="Electronic"><Journal><ISSN IssnType="Electronic">1471-2458</ISSN>
<JournalIssue CitedMedium="Internet"><Volume>9</Volume>
<PubDate><Year>2009</Year>
<Month>Jun</Month>
<Day>10</Day>
</PubDate>
</JournalIssue>
<Title>BMC public health</Title>
<ISOAbbreviation>BMC Public Health</ISOAbbreviation>
</Journal>
<ArticleTitle>Toward unsupervised outbreak detection through visual perception of new patterns.</ArticleTitle>
<Pagination><MedlinePgn>179</MedlinePgn>
</Pagination>
<ELocationID EIdType="doi" ValidYN="Y">10.1186/1471-2458-9-179</ELocationID>
<Abstract><AbstractText Label="BACKGROUND" NlmCategory="BACKGROUND">Statistical algorithms are routinely used to detect outbreaks of well-defined syndromes, such as influenza-like illness. These methods cannot be applied to the detection of emerging diseases for which no preexisting information is available.This paper presents a method aimed at facilitating the detection of outbreaks, when there is no a priori knowledge of the clinical presentation of cases.</AbstractText>
<AbstractText Label="METHODS" NlmCategory="METHODS">The method uses a visual representation of the symptoms and diseases coded during a patient consultation according to the International Classification of Primary Care 2nd version (ICPC-2). The surveillance data are transformed into color-coded cells, ranging from white to red, reflecting the increasing frequency of observed signs. They are placed in a graphic reference frame mimicking body anatomy. Simple visual observation of color-change patterns over time, concerning a single code or a combination of codes, enables detection in the setting of interest.</AbstractText>
<AbstractText Label="RESULTS" NlmCategory="RESULTS">The method is demonstrated through retrospective analyses of two data sets: description of the patients referred to the hospital by their general practitioners (GPs) participating in the French Sentinel Network and description of patients directly consulting at a hospital emergency department (HED).Informative image color-change alert patterns emerged in both cases: the health consequences of the August 2003 heat wave were visualized with GPs' data (but passed unnoticed with conventional surveillance systems), and the flu epidemics, which are routinely detected by standard statistical techniques, were recognized visually with HED data.</AbstractText>
<AbstractText Label="CONCLUSION" NlmCategory="CONCLUSIONS">Using human visual pattern-recognition capacities to detect the onset of unexpected health events implies a convenient image representation of epidemiological surveillance and well-trained "epidemiology watchers". Once these two conditions are met, one could imagine that the epidemiology watchers could signal epidemiological alerts, based on "image walls" presenting the local, regional and/or national surveillance patterns, with specialized field epidemiologists assigned to validate the signals detected.</AbstractText>
</Abstract>
<AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Lévy</LastName>
<ForeName>Pierre P</ForeName>
<Initials>PP</Initials>
<AffiliationInfo><Affiliation>Assistance Publique-Hôpitaux de Paris, Hôpital Tenon, Département de Santé Publique, Paris, France. levy@u707.jussieu.fr</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Valleron</LastName>
<ForeName>Alain-Jacques</ForeName>
<Initials>AJ</Initials>
</Author>
</AuthorList>
<Language>eng</Language>
<PublicationTypeList><PublicationType UI="D003160">Comparative Study</PublicationType>
<PublicationType UI="D016428">Journal Article</PublicationType>
<PublicationType UI="D013485">Research Support, Non-U.S. Gov't</PublicationType>
</PublicationTypeList>
<ArticleDate DateType="Electronic"><Year>2009</Year>
<Month>06</Month>
<Day>10</Day>
</ArticleDate>
</Article>
<MedlineJournalInfo><Country>England</Country>
<MedlineTA>BMC Public Health</MedlineTA>
<NlmUniqueID>100968562</NlmUniqueID>
<ISSNLinking>1471-2458</ISSNLinking>
</MedlineJournalInfo>
<CitationSubset>IM</CitationSubset>
<MeshHeadingList><MeshHeading><DescriptorName UI="D016208" MajorTopicYN="N">Databases, Factual</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D004194" MajorTopicYN="N">Disease</DescriptorName>
<QualifierName UI="Q000145" MajorTopicYN="N">classification</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D004196" MajorTopicYN="Y">Disease Outbreaks</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D004636" MajorTopicYN="N">Emergency Service, Hospital</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D005194" MajorTopicYN="N">Family Practice</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D005260" MajorTopicYN="N">Female</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D005602" MajorTopicYN="N" Type="Geographic">France</DescriptorName>
<QualifierName UI="Q000453" MajorTopicYN="N">epidemiology</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D006801" MajorTopicYN="N">Humans</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D008297" MajorTopicYN="N">Male</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D009323" MajorTopicYN="N">Natural Language Processing</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D010364" MajorTopicYN="Y">Pattern Recognition, Visual</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D011159" MajorTopicYN="N">Population Surveillance</DescriptorName>
<QualifierName UI="Q000379" MajorTopicYN="Y">methods</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D012189" MajorTopicYN="N">Retrospective Studies</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D018571" MajorTopicYN="N">Sentinel Surveillance</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D018875" MajorTopicYN="N">Vocabulary, Controlled</DescriptorName>
</MeshHeading>
</MeshHeadingList>
</MedlineCitation>
<PubmedData><History><PubMedPubDate PubStatus="received"><Year>2009</Year>
<Month>01</Month>
<Day>24</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="accepted"><Year>2009</Year>
<Month>06</Month>
<Day>10</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="entrez"><Year>2009</Year>
<Month>6</Month>
<Day>12</Day>
<Hour>9</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="pubmed"><Year>2009</Year>
<Month>6</Month>
<Day>12</Day>
<Hour>9</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="medline"><Year>2009</Year>
<Month>9</Month>
<Day>29</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
</History>
<PublicationStatus>epublish</PublicationStatus>
<ArticleIdList><ArticleId IdType="pubmed">19515246</ArticleId>
<ArticleId IdType="pii">1471-2458-9-179</ArticleId>
<ArticleId IdType="doi">10.1186/1471-2458-9-179</ArticleId>
<ArticleId IdType="pmc">PMC2706246</ArticleId>
</ArticleIdList>
<ReferenceList><Reference><Citation>MMWR Morb Mortal Wkly Rep. 2004 Sep 24;53 Suppl:112-6</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15714639</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Int J Med Inform. 2004 Sep;73(9-10):713-8</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15325328</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Nature. 2008 Apr 10;452(7188):750-4</Citation>
<ArticleIdList><ArticleId IdType="pubmed">18401408</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Ann Fam Med. 2006 Jul-Aug;4(4):351-8</Citation>
<ArticleIdList><ArticleId IdType="pubmed">16868239</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>MMWR Morb Mortal Wkly Rep. 2004 Sep 24;53 Suppl:28-31</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15714623</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>MMWR Morb Mortal Wkly Rep. 2004 Sep 24;53 Suppl:173-8</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15714648</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>BMC Med Inform Decis Mak. 2007;7:29</Citation>
<ArticleIdList><ArticleId IdType="pubmed">17937786</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>MMWR Recomm Rep. 2004 May 7;53(RR-5):1-11</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15129191</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>C R Biol. 2004 Dec;327(12):1125-41</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15656355</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Public Health Rep. 1963 Jun;78(6):494-506</Citation>
<ArticleIdList><ArticleId IdType="pubmed">19316455</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>MMWR Morb Mortal Wkly Rep. 2004 Sep 24;53 Suppl:101-5</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15714637</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Emerg Infect Dis. 2005 Feb;11(2):314-6</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15752454</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Artif Intell Med. 2005 Jan;33(1):31-40</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15617980</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Emerg Infect Dis. 2004 May;10(5):858-64</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15200820</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Proc AMIA Symp. 2000;:487-91</Citation>
<ArticleIdList><ArticleId IdType="pubmed">11079931</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Nature. 2005 Jul 7;436(7047):71-7</Citation>
<ArticleIdList><ArticleId IdType="pubmed">16001064</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Proc AMIA Symp. 2002;:345-9</Citation>
<ArticleIdList><ArticleId IdType="pubmed">12463844</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Stud Health Technol Inform. 2005;116:623-8</Citation>
<ArticleIdList><ArticleId IdType="pubmed">16160327</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Am J Public Health. 1991 Jan;81(1):97-9</Citation>
<ArticleIdList><ArticleId IdType="pubmed">1983924</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>MMWR Morb Mortal Wkly Rep. 2004 Sep 24;53 Suppl:159-65</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15714646</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Commun Dis Rep CDR Rev. 1993 May 21;3(6):R82-7</Citation>
<ArticleIdList><ArticleId IdType="pubmed">7693158</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Ann Emerg Med. 2004 Sep;44(3):235-41</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15332065</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Am J Public Health. 1986 Nov;76(11):1289-92</Citation>
<ArticleIdList><ArticleId IdType="pubmed">3766824</ArticleId>
</ArticleIdList>
</Reference>
</ReferenceList>
</PubmedData>
</pubmed>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Sante/explor/GrippeFranceV1/Data/Main/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000488 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Corpus/biblio.hfd -nk 000488 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Sante |area= GrippeFranceV1 |flux= Main |étape= Corpus |type= RBID |clé= pubmed:19515246 |texte= Toward unsupervised outbreak detection through visual perception of new patterns. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Corpus/RBID.i -Sk "pubmed:19515246" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Main/Corpus/biblio.hfd \ | NlmPubMed2Wicri -a GrippeFranceV1
![]() | This area was generated with Dilib version V0.6.35. | ![]() |