Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892939285> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2892939285 endingPage "275" @default.
- W2892939285 startingPage "265" @default.
- W2892939285 abstract "Abstract Objective We explored how judgements provided by physicians can be used to learn relevance models that enhance the quality of patient cohorts retrieved from Electronic Health Records (EHRs) collections. Methods A very large number of features were extracted from patient cohort descriptions as well as EHR collections. The features were used to investigate retrieving (1) neurology-specific patient cohorts from the de-identified Temple University Hospital electroencephalography (EEG) Corpus as well as (2) the more general cohorts evaluated in the TREC Medical Records Track (TRECMed) from the de-identified hospital records provided by the University of Pittsburgh Medical Center. The features informed a learning relevance model (LRM) that took advantage of relevance judgements provided by physicians. The LRM implements a pairwise learning-to-rank framework, which enables our learning patient cohort retrieval (L-PCR) system to learn from physicians’ feedback. Results and Discussion We evaluated the L-PCR system against state-of-the-art traditional patient cohort retrieval systems, and observed a 27% improvement when operating on EEGs and a 53% improvement when operating on TRECMed EHRs, showing the promise of the L-PCR system. We also performed extensive feature analyses to reveal the most effective strategies for representing cohort descriptions as queries, encoding EHRs, and measuring cohort relevance. Conclusion The L-PCR system has significant promise for reliably retrieving patient cohorts from EHRs in multiple settings when trained with relevance judgments. When provided with additional cohort descriptions, the L-PCR system will continue to learn, thus offering a potential solution to the performance barriers of current cohort retrieval systems." @default.
- W2892939285 created "2018-10-05" @default.
- W2892939285 creator A5026143426 @default.
- W2892939285 creator A5051583244 @default.
- W2892939285 date "2018-09-28" @default.
- W2892939285 modified "2023-09-24" @default.
- W2892939285 title "Learning relevance models for patient cohort retrieval" @default.
- W2892939285 cites W1483357098 @default.
- W2892939285 cites W1550258693 @default.
- W2892939285 cites W1808652302 @default.
- W2892939285 cites W2007636979 @default.
- W2892939285 cites W2007815473 @default.
- W2892939285 cites W2012030884 @default.
- W2892939285 cites W2104542816 @default.
- W2892939285 cites W2109341018 @default.
- W2892939285 cites W2126166543 @default.
- W2892939285 cites W2134137358 @default.
- W2892939285 cites W2139865360 @default.
- W2892939285 cites W2162311237 @default.
- W2892939285 cites W2345279893 @default.
- W2892939285 cites W2406492869 @default.
- W2892939285 cites W2620790279 @default.
- W2892939285 cites W2768114048 @default.
- W2892939285 cites W2911964244 @default.
- W2892939285 cites W4213009331 @default.
- W2892939285 cites W4302313152 @default.
- W2892939285 doi "https://doi.org/10.1093/jamiaopen/ooy010" @default.
- W2892939285 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6241510" @default.
- W2892939285 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30474078" @default.
- W2892939285 hasPublicationYear "2018" @default.
- W2892939285 type Work @default.
- W2892939285 sameAs 2892939285 @default.
- W2892939285 citedByCount "10" @default.
- W2892939285 countsByYear W28929392852019 @default.
- W2892939285 countsByYear W28929392852020 @default.
- W2892939285 countsByYear W28929392852022 @default.
- W2892939285 countsByYear W28929392852023 @default.
- W2892939285 crossrefType "journal-article" @default.
- W2892939285 hasAuthorship W2892939285A5026143426 @default.
- W2892939285 hasAuthorship W2892939285A5051583244 @default.
- W2892939285 hasBestOaLocation W28929392851 @default.
- W2892939285 hasConcept C126322002 @default.
- W2892939285 hasConcept C154945302 @default.
- W2892939285 hasConcept C158154518 @default.
- W2892939285 hasConcept C160735492 @default.
- W2892939285 hasConcept C162324750 @default.
- W2892939285 hasConcept C17744445 @default.
- W2892939285 hasConcept C184898388 @default.
- W2892939285 hasConcept C189430467 @default.
- W2892939285 hasConcept C195910791 @default.
- W2892939285 hasConcept C199539241 @default.
- W2892939285 hasConcept C23123220 @default.
- W2892939285 hasConcept C3020144179 @default.
- W2892939285 hasConcept C41008148 @default.
- W2892939285 hasConcept C50522688 @default.
- W2892939285 hasConcept C71924100 @default.
- W2892939285 hasConcept C72563966 @default.
- W2892939285 hasConceptScore W2892939285C126322002 @default.
- W2892939285 hasConceptScore W2892939285C154945302 @default.
- W2892939285 hasConceptScore W2892939285C158154518 @default.
- W2892939285 hasConceptScore W2892939285C160735492 @default.
- W2892939285 hasConceptScore W2892939285C162324750 @default.
- W2892939285 hasConceptScore W2892939285C17744445 @default.
- W2892939285 hasConceptScore W2892939285C184898388 @default.
- W2892939285 hasConceptScore W2892939285C189430467 @default.
- W2892939285 hasConceptScore W2892939285C195910791 @default.
- W2892939285 hasConceptScore W2892939285C199539241 @default.
- W2892939285 hasConceptScore W2892939285C23123220 @default.
- W2892939285 hasConceptScore W2892939285C3020144179 @default.
- W2892939285 hasConceptScore W2892939285C41008148 @default.
- W2892939285 hasConceptScore W2892939285C50522688 @default.
- W2892939285 hasConceptScore W2892939285C71924100 @default.
- W2892939285 hasConceptScore W2892939285C72563966 @default.
- W2892939285 hasFunder F4320332161 @default.
- W2892939285 hasIssue "2" @default.
- W2892939285 hasLocation W28929392851 @default.
- W2892939285 hasLocation W28929392852 @default.
- W2892939285 hasLocation W28929392853 @default.
- W2892939285 hasLocation W28929392854 @default.
- W2892939285 hasOpenAccess W2892939285 @default.
- W2892939285 hasPrimaryLocation W28929392851 @default.
- W2892939285 hasRelatedWork W1589134610 @default.
- W2892939285 hasRelatedWork W1934841634 @default.
- W2892939285 hasRelatedWork W2041353081 @default.
- W2892939285 hasRelatedWork W2294459391 @default.
- W2892939285 hasRelatedWork W2513723017 @default.
- W2892939285 hasRelatedWork W2581240705 @default.
- W2892939285 hasRelatedWork W3048366122 @default.
- W2892939285 hasRelatedWork W3080126616 @default.
- W2892939285 hasRelatedWork W4287690154 @default.
- W2892939285 hasRelatedWork W4289552663 @default.
- W2892939285 hasVolume "1" @default.
- W2892939285 isParatext "false" @default.
- W2892939285 isRetracted "false" @default.
- W2892939285 magId "2892939285" @default.
- W2892939285 workType "article" @default.