2024
Automated Identification of Heart Failure With Reduced Ejection Fraction Using Deep Learning-Based Natural Language Processing
Nargesi A, Adejumo P, Dhingra L, Rosand B, Hengartner A, Coppi A, Benigeri S, Sen S, Ahmad T, Nadkarni G, Lin Z, Ahmad F, Krumholz H, Khera R. Automated Identification of Heart Failure With Reduced Ejection Fraction Using Deep Learning-Based Natural Language Processing. JACC Heart Failure 2024 PMID: 39453355, DOI: 10.1016/j.jchf.2024.08.012.Peer-Reviewed Original ResearchReduced ejection fractionEjection fractionHeart failureLeft ventricular ejection fractionVentricular ejection fractionYale-New Haven HospitalIdentification of patientsCommunity hospitalIdentification of heart failureLanguage modelNorthwestern MedicineMeasure care qualityQuality of careNew Haven HospitalDeep learning-based natural language processingHFrEFGuideline-directed careDeep learning language modelsMIMIC-IIIDetect HFrEFNatural language processingReclassification improvementHospital dischargePatientsCare quality
2023
Developing Validated Tools to Identify Pulmonary Embolism in Electronic Databases: Rationale and Design of the PE-EHR+ Study
Bikdeli B, Lo Y, Khairani C, Bejjani A, Jimenez D, Barco S, Mahajan S, Caraballo C, Secemsky E, Klok F, Hunsaker A, Aghayev A, Muriel A, Wang Y, Hussain M, Appah-Sampong A, Lu Y, Lin Z, Aneja S, Khera R, Goldhaber S, Zhou L, Monreal M, Krumholz H, Piazza G. Developing Validated Tools to Identify Pulmonary Embolism in Electronic Databases: Rationale and Design of the PE-EHR+ Study. Thrombosis And Haemostasis 2023, 123: 649-662. PMID: 36809777, PMCID: PMC11200175, DOI: 10.1055/a-2039-3222.Peer-Reviewed Original ResearchConceptsElectronic health recordsNLP algorithmNatural language processing toolsLanguage processing toolsPrincipal discharge diagnosisICD-10 codesDischarge diagnosisNLP toolsChart reviewHealth systemProcessing toolsYale New Haven Health SystemPatient identificationElectronic databasesHealth recordsData validationHigh-risk PEPulmonary Embolism ResearchSecondary discharge diagnosisIdentification of patientsManual chart reviewNegative predictive valueCodeRadiology reportsAlgorithm
2018
Enhancing the prediction of acute kidney injury risk after percutaneous coronary intervention using machine learning techniques: A retrospective cohort study
Huang C, Murugiah K, Mahajan S, Li SX, Dhruva SS, Haimovich JS, Wang Y, Schulz WL, Testani JM, Wilson FP, Mena CI, Masoudi FA, Rumsfeld JS, Spertus JA, Mortazavi BJ, Krumholz HM. Enhancing the prediction of acute kidney injury risk after percutaneous coronary intervention using machine learning techniques: A retrospective cohort study. PLOS Medicine 2018, 15: e1002703. PMID: 30481186, PMCID: PMC6258473, DOI: 10.1371/journal.pmed.1002703.Peer-Reviewed Original ResearchMeSH KeywordsAcute Kidney InjuryAgedClinical Decision-MakingData MiningDecision Support TechniquesFemaleHumansMachine LearningMaleMiddle AgedPercutaneous Coronary InterventionProtective FactorsRegistriesReproducibility of ResultsRetrospective StudiesRisk AssessmentRisk FactorsTime FactorsTreatment OutcomeConceptsPercutaneous coronary interventionNational Cardiovascular Data RegistryRisk prediction modelAKI eventsAKI riskCoronary interventionAKI modelMean ageCardiology-National Cardiovascular Data RegistryAcute kidney injury riskAKI risk predictionRetrospective cohort studyIdentification of patientsCandidate variablesAvailable candidate variablesCohort studyPCI proceduresPoint of careBrier scoreAmerican CollegeData registryPatientsCalibration slopeInjury riskSame cohort