Building Structured Personal Health Records from Photographs of Printed Medical Records
Identifieur interne : 000051 ( Main/Merge ); précédent : 000050; suivant : 000052Building Structured Personal Health Records from Photographs of Printed Medical Records
Auteurs : Xiang Li [République populaire de Chine] ; Gang Hu [République populaire de Chine] ; Xiaofei Teng [République populaire de Chine] ; Guotong Xie [République populaire de Chine]Source :
- AMIA Annual Symposium Proceedings [ 1942-597X ] ; 2015.
Abstract
Personal health records (PHRs) provide patient-centric healthcare by making health records accessible to patients. In China, it is very difficult for individuals to access electronic health records. Instead, individuals can easily obtain the printed copies of their own medical records, such as prescriptions and lab test reports, from hospitals. In this paper, we propose a practical approach to extract structured data from printed medical records photographed by mobile phones. An optical character recognition (OCR) pipeline is performed to recognize text in a document photo, which addresses the problems of low image quality and content complexity by image pre-processing and multiple OCR engine synthesis. A series of annotation algorithms that support flexible layouts are then used to identify the document type, entities of interest, and entity correlations, from which a structured PHR document is built. The proposed approach was applied to real world medical records to demonstrate the effectiveness and applicability.
Url:
PubMed: 26958219
PubMed Central: 4765700
Links toward previous steps (curation, corpus...)
- to stream Pmc, to step Corpus: 000022
- to stream Pmc, to step Curation: 000022
- to stream Pmc, to step Checkpoint: 000029
- to stream PubMed, to step Corpus: 000009
- to stream PubMed, to step Curation: 000009
- to stream PubMed, to step Checkpoint: 000009
- to stream Ncbi, to step Merge: 000252
- to stream Ncbi, to step Curation: 000252
- to stream Ncbi, to step Checkpoint: 000252
Links to Exploration step
PMC:4765700Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Building Structured Personal Health Records from Photographs of Printed Medical Records</title>
<author><name sortKey="Li, Xiang" sort="Li, Xiang" uniqKey="Li X" first="Xiang" last="Li">Xiang Li</name>
<affiliation wicri:level="1"><nlm:aff id="af1-2246610">IBM Research Beijing, China</nlm:aff>
<country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>IBM Research Beijing</wicri:regionArea>
</affiliation>
</author>
<author><name sortKey="Hu, Gang" sort="Hu, Gang" uniqKey="Hu G" first="Gang" last="Hu">Gang Hu</name>
<affiliation wicri:level="1"><nlm:aff id="af1-2246610">IBM Research Beijing, China</nlm:aff>
<country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>IBM Research Beijing</wicri:regionArea>
</affiliation>
</author>
<author><name sortKey="Teng, Xiaofei" sort="Teng, Xiaofei" uniqKey="Teng X" first="Xiaofei" last="Teng">Xiaofei Teng</name>
<affiliation wicri:level="1"><nlm:aff id="af1-2246610">IBM Research Beijing, China</nlm:aff>
<country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>IBM Research Beijing</wicri:regionArea>
</affiliation>
</author>
<author><name sortKey="Xie, Guotong" sort="Xie, Guotong" uniqKey="Xie G" first="Guotong" last="Xie">Guotong Xie</name>
<affiliation wicri:level="1"><nlm:aff id="af1-2246610">IBM Research Beijing, China</nlm:aff>
<country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>IBM Research Beijing</wicri:regionArea>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PMC</idno>
<idno type="pmid">26958219</idno>
<idno type="pmc">4765700</idno>
<idno type="url">http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4765700</idno>
<idno type="RBID">PMC:4765700</idno>
<date when="2015">2015</date>
<idno type="wicri:Area/Pmc/Corpus">000022</idno>
<idno type="wicri:Area/Pmc/Curation">000022</idno>
<idno type="wicri:Area/Pmc/Checkpoint">000029</idno>
<idno type="wicri:source">PubMed</idno>
<idno type="wicri:Area/PubMed/Corpus">000009</idno>
<idno type="wicri:Area/PubMed/Curation">000009</idno>
<idno type="wicri:Area/PubMed/Checkpoint">000009</idno>
<idno type="wicri:Area/Ncbi/Merge">000252</idno>
<idno type="wicri:Area/Ncbi/Curation">000252</idno>
<idno type="wicri:Area/Ncbi/Checkpoint">000252</idno>
<idno type="wicri:Area/Main/Merge">000051</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a" type="main">Building Structured Personal Health Records from Photographs of Printed Medical Records</title>
<author><name sortKey="Li, Xiang" sort="Li, Xiang" uniqKey="Li X" first="Xiang" last="Li">Xiang Li</name>
<affiliation wicri:level="1"><nlm:aff id="af1-2246610">IBM Research Beijing, China</nlm:aff>
<country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>IBM Research Beijing</wicri:regionArea>
</affiliation>
</author>
<author><name sortKey="Hu, Gang" sort="Hu, Gang" uniqKey="Hu G" first="Gang" last="Hu">Gang Hu</name>
<affiliation wicri:level="1"><nlm:aff id="af1-2246610">IBM Research Beijing, China</nlm:aff>
<country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>IBM Research Beijing</wicri:regionArea>
</affiliation>
</author>
<author><name sortKey="Teng, Xiaofei" sort="Teng, Xiaofei" uniqKey="Teng X" first="Xiaofei" last="Teng">Xiaofei Teng</name>
<affiliation wicri:level="1"><nlm:aff id="af1-2246610">IBM Research Beijing, China</nlm:aff>
<country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>IBM Research Beijing</wicri:regionArea>
</affiliation>
</author>
<author><name sortKey="Xie, Guotong" sort="Xie, Guotong" uniqKey="Xie G" first="Guotong" last="Xie">Guotong Xie</name>
<affiliation wicri:level="1"><nlm:aff id="af1-2246610">IBM Research Beijing, China</nlm:aff>
<country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>IBM Research Beijing</wicri:regionArea>
</affiliation>
</author>
</analytic>
<series><title level="j">AMIA Annual Symposium Proceedings</title>
<idno type="eISSN">1942-597X</idno>
<imprint><date when="2015">2015</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en"><p>Personal health records (PHRs) provide patient-centric healthcare by making health records accessible to patients. In China, it is very difficult for individuals to access electronic health records. Instead, individuals can easily obtain the printed copies of their own medical records, such as prescriptions and lab test reports, from hospitals. In this paper, we propose a practical approach to extract structured data from printed medical records photographed by mobile phones. An optical character recognition (OCR) pipeline is performed to recognize text in a document photo, which addresses the problems of low image quality and content complexity by image pre-processing and multiple OCR engine synthesis. A series of annotation algorithms that support flexible layouts are then used to identify the document type, entities of interest, and entity correlations, from which a structured PHR document is built. The proposed approach was applied to real world medical records to demonstrate the effectiveness and applicability.</p>
</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000051 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 000051 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Merge |type= RBID |clé= PMC:4765700 |texte= Building Structured Personal Health Records from Photographs of Printed Medical Records }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Merge/RBID.i -Sk "pubmed:26958219" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Main/Merge/biblio.hfd \ | NlmPubMed2Wicri -a OcrV1
This area was generated with Dilib version V0.6.32. |