Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092788897> ?p ?o ?g. }
- W3092788897 abstract "The electronic medical record contains a wealth of information buried in free text. We created a natural language processing algorithm to identify patients with atrial fibrillation (AF) using text alone.We created 3 data sets from patients with at least one AF billing code from 2010 to 2017: a training set (n=886), an internal validation set from site no. 1 (n=285), and an external validation set from site no. 2 (n=276). A team of clinicians reviewed and adjudicated patients as AF present or absent, which served as the reference standard. We trained 54 algorithms to classify each patient, varying the model, number of features, number of stop words, and the method used to create the feature set. The algorithm with the highest F-score (the harmonic mean of sensitivity and positive predictive value) in the training set was applied to the validation sets. F-scores and area under the receiver operating characteristic curves were compared between site no. 1 and site no. 2 using bootstrapping. Adjudicated AF prevalence was 75.1% at site no. 1 and 86.2% at site no. 2. Among 54 algorithms, the best performing model was logistic regression, using 1000 features, 100 stop words, and term frequency-inverse document frequency method to create the feature set, with sensitivity 92.8%, specificity 93.9%, and an area under the receiver operating characteristic curve of 0.93 in the training set. The performance at site no. 1 was sensitivity 92.5%, specificity 88.7%, with an area under the receiver operating characteristic curve of 0.91. The performance at site no. 2 was sensitivity 89.5%, specificity 71.1%, with an area under the receiver operating characteristic curve of 0.80. The F-score was lower at site no. 2 compared with site no. 1 (92.5% [SD, 1.1%] versus 94.2% [SD, 1.1%]; P<0.001).We developed a natural language processing algorithm to identify patients with AF using text alone, with >90% F-score at 2 separate sites. This approach allows better use of the clinical narrative and creates an opportunity for precise, high-throughput cohort identification." @default.
- W3092788897 created "2020-10-22" @default.
- W3092788897 creator A5000655566 @default.
- W3092788897 creator A5014706132 @default.
- W3092788897 creator A5016268965 @default.
- W3092788897 creator A5017418373 @default.
- W3092788897 creator A5017968102 @default.
- W3092788897 creator A5034846864 @default.
- W3092788897 creator A5035626083 @default.
- W3092788897 creator A5057770335 @default.
- W3092788897 creator A5070780364 @default.
- W3092788897 creator A5085397470 @default.
- W3092788897 date "2020-10-01" @default.
- W3092788897 modified "2023-10-17" @default.
- W3092788897 title "Development of a Portable Tool to Identify Patients With Atrial Fibrillation Using Clinical Notes From the Electronic Medical Record" @default.
- W3092788897 cites W1539721984 @default.
- W3092788897 cites W1759219020 @default.
- W3092788897 cites W2110777834 @default.
- W3092788897 cites W2137767404 @default.
- W3092788897 cites W2560688864 @default.
- W3092788897 cites W2770470819 @default.
- W3092788897 cites W2885638337 @default.
- W3092788897 cites W2886147870 @default.
- W3092788897 cites W2897815444 @default.
- W3092788897 cites W2922429916 @default.
- W3092788897 cites W3008553227 @default.
- W3092788897 doi "https://doi.org/10.1161/circoutcomes.120.006516" @default.
- W3092788897 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7646941" @default.
- W3092788897 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33079591" @default.
- W3092788897 hasPublicationYear "2020" @default.
- W3092788897 type Work @default.
- W3092788897 sameAs 3092788897 @default.
- W3092788897 citedByCount "1" @default.
- W3092788897 countsByYear W30927888972021 @default.
- W3092788897 crossrefType "journal-article" @default.
- W3092788897 hasAuthorship W3092788897A5000655566 @default.
- W3092788897 hasAuthorship W3092788897A5014706132 @default.
- W3092788897 hasAuthorship W3092788897A5016268965 @default.
- W3092788897 hasAuthorship W3092788897A5017418373 @default.
- W3092788897 hasAuthorship W3092788897A5017968102 @default.
- W3092788897 hasAuthorship W3092788897A5034846864 @default.
- W3092788897 hasAuthorship W3092788897A5035626083 @default.
- W3092788897 hasAuthorship W3092788897A5057770335 @default.
- W3092788897 hasAuthorship W3092788897A5070780364 @default.
- W3092788897 hasAuthorship W3092788897A5085397470 @default.
- W3092788897 hasBestOaLocation W30927888971 @default.
- W3092788897 hasConcept C119857082 @default.
- W3092788897 hasConcept C124101348 @default.
- W3092788897 hasConcept C126322002 @default.
- W3092788897 hasConcept C127413603 @default.
- W3092788897 hasConcept C138885662 @default.
- W3092788897 hasConcept C149782125 @default.
- W3092788897 hasConcept C151956035 @default.
- W3092788897 hasConcept C153180895 @default.
- W3092788897 hasConcept C154945302 @default.
- W3092788897 hasConcept C177264268 @default.
- W3092788897 hasConcept C199360897 @default.
- W3092788897 hasConcept C207609745 @default.
- W3092788897 hasConcept C21200559 @default.
- W3092788897 hasConcept C24326235 @default.
- W3092788897 hasConcept C2776401178 @default.
- W3092788897 hasConcept C2779161974 @default.
- W3092788897 hasConcept C33923547 @default.
- W3092788897 hasConcept C41008148 @default.
- W3092788897 hasConcept C41895202 @default.
- W3092788897 hasConcept C58471807 @default.
- W3092788897 hasConcept C58489278 @default.
- W3092788897 hasConcept C71924100 @default.
- W3092788897 hasConceptScore W3092788897C119857082 @default.
- W3092788897 hasConceptScore W3092788897C124101348 @default.
- W3092788897 hasConceptScore W3092788897C126322002 @default.
- W3092788897 hasConceptScore W3092788897C127413603 @default.
- W3092788897 hasConceptScore W3092788897C138885662 @default.
- W3092788897 hasConceptScore W3092788897C149782125 @default.
- W3092788897 hasConceptScore W3092788897C151956035 @default.
- W3092788897 hasConceptScore W3092788897C153180895 @default.
- W3092788897 hasConceptScore W3092788897C154945302 @default.
- W3092788897 hasConceptScore W3092788897C177264268 @default.
- W3092788897 hasConceptScore W3092788897C199360897 @default.
- W3092788897 hasConceptScore W3092788897C207609745 @default.
- W3092788897 hasConceptScore W3092788897C21200559 @default.
- W3092788897 hasConceptScore W3092788897C24326235 @default.
- W3092788897 hasConceptScore W3092788897C2776401178 @default.
- W3092788897 hasConceptScore W3092788897C2779161974 @default.
- W3092788897 hasConceptScore W3092788897C33923547 @default.
- W3092788897 hasConceptScore W3092788897C41008148 @default.
- W3092788897 hasConceptScore W3092788897C41895202 @default.
- W3092788897 hasConceptScore W3092788897C58471807 @default.
- W3092788897 hasConceptScore W3092788897C58489278 @default.
- W3092788897 hasConceptScore W3092788897C71924100 @default.
- W3092788897 hasLocation W30927888971 @default.
- W3092788897 hasLocation W30927888972 @default.
- W3092788897 hasLocation W30927888973 @default.
- W3092788897 hasOpenAccess W3092788897 @default.
- W3092788897 hasPrimaryLocation W30927888971 @default.
- W3092788897 hasRelatedWork W4260602 @default.
- W3092788897 hasRelatedWork W5628460 @default.
- W3092788897 hasRelatedWork W590744 @default.
- W3092788897 hasRelatedWork W6792268 @default.
- W3092788897 hasRelatedWork W7512250 @default.