Improving Prehospital Stroke Diagnosis Using Natural Language Processing of Paramedic Reports.

Autor:	Mayampurath A; Department of Pediatrics (A.M.), University of Chicago, IL., Parnianpour Z; Department of Neurology (Z.P., S.J.M., J.L.H., S.P.), University of Chicago, IL., Richards CT; Department of Emergency Medicine, University of Cincinnati, OH (C.T.R.)., Meurer WJ; Department of Emergency Medicine, University of Michigan, Ann Arbor, IL (W.J.M.)., Lee J; Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL (J.L.)., Ankenman B; Department of Industrial Engineering and Management Studies, Northwestern University (B.A., O.P.)., Perry O; Department of Industrial Engineering and Management Studies, Northwestern University (B.A., O.P.)., Mendelson SJ; Department of Neurology (Z.P., S.J.M., J.L.H., S.P.), University of Chicago, IL., Holl JL; Department of Neurology (Z.P., S.J.M., J.L.H., S.P.), University of Chicago, IL., Prabhakaran S; Department of Neurology (Z.P., S.J.M., J.L.H., S.P.), University of Chicago, IL.
Jazyk:	angličtina
Zdroj:	Stroke [Stroke] 2021 Aug; Vol. 52 (8), pp. 2676-2679. Date of Electronic Publication: 2021 Jun 24.
DOI:	10.1161/STROKEAHA.120.033580
Abstrakt:	Background and Purpose: Accurate prehospital diagnosis of stroke by emergency medical services (EMS) can increase treatments rates, mitigate disability, and reduce stroke deaths. We aimed to develop a model that utilizes natural language processing of EMS reports and machine learning to improve prehospital stroke identification. Methods: We conducted a retrospective study of patients transported by the Chicago EMS to 17 regional primary and comprehensive stroke centers. Patients who were suspected of stroke by the EMS or had hospital-diagnosed stroke were included in our cohort. Text within EMS reports were converted to unigram features, which were given as input to a support-vector machine classifier that was trained on 70% of the cohort and tested on the remaining 30%. Outcomes included final diagnosis of stroke versus nonstroke, large vessel occlusion, severe stroke (National Institutes of Health Stroke Scale score >5), and comprehensive stroke center-eligible stroke (large vessel occlusion or hemorrhagic stroke). Results: Of 965 patients, 580 (60%) had confirmed acute stroke. In a test set of 289 patients, the text-based model predicted stroke nominally better than models based on the Cincinnati Prehospital Stroke Scale (c-statistic: 0.73 versus 0.67, P=0.165) and was superior to the 3-Item Stroke Scale (c-statistic: 0.73 versus 0.53, P<0.001) scores. Improvements in discrimination were also observed for the other outcomes. Conclusions: We derived a model that utilizes clinical text from paramedic reports to identify stroke. Our results require validation but have the potential of improving prehospital routing protocols.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu