2016
Building a Natural Language Processing Tool to Identify Patients With High Clinical Suspicion for Kawasaki Disease from Emergency Department Notes
Doan S, Maehara C, Chaparro J, Lu S, Liu R, Graham A, Berry E, Hsu C, Kanegaye J, Lloyd D, Ohno‐Machado L, Burns J, Tremoulet A, Group T. Building a Natural Language Processing Tool to Identify Patients With High Clinical Suspicion for Kawasaki Disease from Emergency Department Notes. Academic Emergency Medicine 2016, 23: 628-636. PMID: 26826020, PMCID: PMC5031359, DOI: 10.1111/acem.12925.Peer-Reviewed Original ResearchConceptsDiagnosis of KDKawasaki diseaseED notesHigh suspicionPediatric ED patientsSerious cardiac complicationsHigh clinical suspicionEmergency department patientsManual chart reviewCardiac complicationsChart reviewClinical suspicionFebrile illnessDepartment patientsED patientsElectronic health record systemsEmergency departmentClinical signsDiagnostic criteriaHealth record systemsPatientsClinical termsSuspicionDiagnosisRecord system
2000
Using electronic data to predict the probability of true bacteremia from positive blood cultures.
Wang S, Kuperman G, Ohno-Machado L, Onderdonk A, Sandige H, Bates D. Using electronic data to predict the probability of true bacteremia from positive blood cultures. AMIA Annual Symposium Proceedings 2000, 893-7. PMID: 11080013, PMCID: PMC2243892.Peer-Reviewed Original ResearchConceptsPositive blood culturesClinical prediction ruleBlood culturesTreatment decisionsTrue bacteremiaCulture resultsPositive blood culture resultsPrediction rulePaper chart reviewProbability of bacteremiaBlood culture resultsInfectious disease expertsAppropriate treatment decisionsLogistic regression modelsRevalidation studyChart reviewDisease expertsOne-year periodBacteremiaPhysiciansRegression modelsTrue positivesPatientsHospitalHousestaff