Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136644799> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3136644799 abstract "Introduction: Early identification of stroke by emergency medical services (EMS) providers in the prehospital setting is associated with increased treatment rates, improved functional outcomes, and reduced mortality. We hypothesize that a predictive model utilizing machine learning and natural language processing (NLP) techniques can be developed to analyze EMS run reports to identify stroke patients accurately. Methods: We analyzed EMS data from the Chicago Fire Department matched with inpatient data on confirmed and suspected strokes from 17 Chicago hospitals in the Get With The Guidelines-Stroke (GWTG-Stroke) registry from 11/28/2018 to 5/31/2019. Using features derived from paramedic notes, we developed a support vector machine classifier to predict the following categories: any stroke, AIS-LVO, severe stroke (NIHSS>5), and CSC-eligible stroke (AIS-LVO or ICH/SAH). Individuals were randomly assigned into model derivation (70%) and validation cohorts (30%). C-statistics were used to evaluate discrimination of the classifier for stroke categories. Results: A total of 965 patients were included for analysis. In a validation cohort of 289 patients, the text-based model predicted stroke better than models trained using the Cincinnati Prehospital Stroke Scale (CPSS, c-statistic: 0.73 vs. 0.67, P=0.165) and the 3-Item Stroke Scale (3I-SS, c-statistic: 0.73 vs. 0.53, P <0.001) scores. The text-based model also demonstrated improved performance over the CPSS and 3I-SS models in discriminating patients with other stroke categories (Table 1). Conclusion: We derived a predictive model using clinical text from paramedic reports that has superior performance to existing prehospital clinical screening tools to identify stroke in the prehospital setting. Future studies can evaluate the implementation of an NLP-based decision tool to assist in prehospital stroke evaluation and destination decision-making." @default.
- W3136644799 created "2021-03-29" @default.
- W3136644799 creator A5011989564 @default.
- W3136644799 creator A5022565043 @default.
- W3136644799 creator A5036463370 @default.
- W3136644799 creator A5047743484 @default.
- W3136644799 creator A5052800525 @default.
- W3136644799 creator A5058647871 @default.
- W3136644799 creator A5063187509 @default.
- W3136644799 creator A5069187445 @default.
- W3136644799 creator A5069853831 @default.
- W3136644799 creator A5089229495 @default.
- W3136644799 date "2021-03-01" @default.
- W3136644799 modified "2023-09-23" @default.
- W3136644799 title "Abstract P225: Improving Prehospital Stroke Identification Using Natural Language Processing of Paramedic Reports" @default.
- W3136644799 doi "https://doi.org/10.1161/str.52.suppl_1.p225" @default.
- W3136644799 hasPublicationYear "2021" @default.
- W3136644799 type Work @default.
- W3136644799 sameAs 3136644799 @default.
- W3136644799 citedByCount "0" @default.
- W3136644799 crossrefType "journal-article" @default.
- W3136644799 hasAuthorship W3136644799A5011989564 @default.
- W3136644799 hasAuthorship W3136644799A5022565043 @default.
- W3136644799 hasAuthorship W3136644799A5036463370 @default.
- W3136644799 hasAuthorship W3136644799A5047743484 @default.
- W3136644799 hasAuthorship W3136644799A5052800525 @default.
- W3136644799 hasAuthorship W3136644799A5058647871 @default.
- W3136644799 hasAuthorship W3136644799A5063187509 @default.
- W3136644799 hasAuthorship W3136644799A5069187445 @default.
- W3136644799 hasAuthorship W3136644799A5069853831 @default.
- W3136644799 hasAuthorship W3136644799A5089229495 @default.
- W3136644799 hasConcept C105795698 @default.
- W3136644799 hasConcept C118552586 @default.
- W3136644799 hasConcept C126322002 @default.
- W3136644799 hasConcept C127413603 @default.
- W3136644799 hasConcept C194828623 @default.
- W3136644799 hasConcept C2780645631 @default.
- W3136644799 hasConcept C2780724011 @default.
- W3136644799 hasConcept C3020166492 @default.
- W3136644799 hasConcept C33923547 @default.
- W3136644799 hasConcept C545288138 @default.
- W3136644799 hasConcept C545542383 @default.
- W3136644799 hasConcept C71924100 @default.
- W3136644799 hasConcept C72563966 @default.
- W3136644799 hasConcept C78519656 @default.
- W3136644799 hasConcept C89128539 @default.
- W3136644799 hasConceptScore W3136644799C105795698 @default.
- W3136644799 hasConceptScore W3136644799C118552586 @default.
- W3136644799 hasConceptScore W3136644799C126322002 @default.
- W3136644799 hasConceptScore W3136644799C127413603 @default.
- W3136644799 hasConceptScore W3136644799C194828623 @default.
- W3136644799 hasConceptScore W3136644799C2780645631 @default.
- W3136644799 hasConceptScore W3136644799C2780724011 @default.
- W3136644799 hasConceptScore W3136644799C3020166492 @default.
- W3136644799 hasConceptScore W3136644799C33923547 @default.
- W3136644799 hasConceptScore W3136644799C545288138 @default.
- W3136644799 hasConceptScore W3136644799C545542383 @default.
- W3136644799 hasConceptScore W3136644799C71924100 @default.
- W3136644799 hasConceptScore W3136644799C72563966 @default.
- W3136644799 hasConceptScore W3136644799C78519656 @default.
- W3136644799 hasConceptScore W3136644799C89128539 @default.
- W3136644799 hasIssue "Suppl_1" @default.
- W3136644799 hasLocation W31366447991 @default.
- W3136644799 hasOpenAccess W3136644799 @default.
- W3136644799 hasPrimaryLocation W31366447991 @default.
- W3136644799 hasRelatedWork W1817558971 @default.
- W3136644799 hasRelatedWork W1970658819 @default.
- W3136644799 hasRelatedWork W2188477849 @default.
- W3136644799 hasRelatedWork W2336612561 @default.
- W3136644799 hasRelatedWork W2402962025 @default.
- W3136644799 hasRelatedWork W2612218989 @default.
- W3136644799 hasRelatedWork W3017570460 @default.
- W3136644799 hasRelatedWork W3122377352 @default.
- W3136644799 hasRelatedWork W4210343577 @default.
- W3136644799 hasRelatedWork W4210375789 @default.
- W3136644799 hasVolume "52" @default.
- W3136644799 isParatext "false" @default.
- W3136644799 isRetracted "false" @default.
- W3136644799 magId "3136644799" @default.
- W3136644799 workType "article" @default.