2024
Use of electronic health records to characterize patients with uncontrolled hypertension in two large health system networks
Lu Y, Keeley E, Barrette E, Cooper-DeHoff R, Dhruva S, Gaffney J, Gamble G, Handke B, Huang C, Krumholz H, McDonough C, Schulz W, Shaw K, Smith M, Woodard J, Young P, Ervin K, Ross J. Use of electronic health records to characterize patients with uncontrolled hypertension in two large health system networks. BMC Cardiovascular Disorders 2024, 24: 497. PMID: 39289597, PMCID: PMC11409735, DOI: 10.1186/s12872-024-04161-x.Peer-Reviewed Original ResearchConceptsElectronic health recordsHealth recordsHealth systemUncontrolled hypertensionUse of electronic health recordsHypertension managementElectronic health record systemsOneFlorida Clinical Research ConsortiumElectronic health record dataYale New Haven Health SystemBP measurementsICD-10-CM codesHealth system networkPublic health priorityICD-10-CMIncidence rate of deathElevated BP measurementsElevated blood pressure measurementsHealthcare visitsAmbulatory careHealth priorityRetrospective cohort studyEHR dataOneFloridaBlood pressure measurementsBarriers to Optimal Clinician Guideline Adherence in Management of Markedly Elevated Blood Pressure
Lu Y, Arowojolu O, Qiu X, Liu Y, Curry L, Krumholz H. Barriers to Optimal Clinician Guideline Adherence in Management of Markedly Elevated Blood Pressure. JAMA Network Open 2024, 7: e2426135. PMID: 39106065, PMCID: PMC11304113, DOI: 10.1001/jamanetworkopen.2024.26135.Peer-Reviewed Original ResearchConceptsBarriers to guideline adherenceElectronic health recordsGuideline adherenceClinician adherenceEHR dataElevated blood pressureHypertension managementAnalysis of EHR dataYale New Haven Health SystemSevere hypertensionClinical practice guidelinesAdherence scenariosQualitative content analysisPublic health challengeThematic saturationHealth recordsHealth systemBlood pressureThematic analysisTargeted interventionsManagement of severe hypertensionQualitative studyHealth challengesPractice guidelinesPatient outcomesLearning implementation of a guideline based decision support system to improve hypertension treatment in primary care in China: pragmatic cluster randomised controlled trial
Song J, Wang X, Wang B, Ge Y, Bi L, Jing F, Jin H, Li T, Gu B, Wang L, Hao J, Zhao Y, Liu J, Zhang H, Li X, Li J, Ma W, Wang J, Normand S, Herrin J, Armitage J, Krumholz H, Zheng X. Learning implementation of a guideline based decision support system to improve hypertension treatment in primary care in China: pragmatic cluster randomised controlled trial. The BMJ 2024, 386: e079143. PMID: 39043397, PMCID: PMC11265211, DOI: 10.1136/bmj-2023-079143.Peer-Reviewed Original ResearchConceptsClinical decision support systemsPrimary care practicesElectronic health recordsIntervention groupSystolic blood pressurePrimary careCare practicesBlood pressure <Health recordsPragmatic cluster randomised controlled trialCluster randomised controlled trialImproving hypertension treatmentPrimary care settingBlood pressure control ratesBlood pressureProportion of visitsProportion of participantsRandomised controlled trialsSystolic blood pressure <Control groupInjurious fallsRelated visitsCare settingsDiastolic blood pressure <Follow-upStrokeClassifier: ischemic stroke etiology classification by ensemble consensus modeling using electronic health records
Lee H, Schwamm L, Sansing L, Kamel H, de Havenon A, Turner A, Sheth K, Krishnaswamy S, Brandt C, Zhao H, Krumholz H, Sharma R. StrokeClassifier: ischemic stroke etiology classification by ensemble consensus modeling using electronic health records. Npj Digital Medicine 2024, 7: 130. PMID: 38760474, PMCID: PMC11101464, DOI: 10.1038/s41746-024-01120-w.Peer-Reviewed Original ResearchElectronic health recordsWeighted F1MIMIC-IIIClinical decision support systemsMulti-class classificationNatural language processingMIMIC-III datasetHealth recordsMachine learning classifiersDecision support systemArtificial intelligence toolsVascular neurologistsLearning classifiersBinary classificationCross-validation accuracyLanguage processingMeta-modelIntelligence toolsStroke prevention effortsAcute ischemic strokeStroke etiologySupport systemStroke etiology classificationClassification toolClassifierThe PAX LC Trial: A Decentralized, Phase 2, Randomized, Double-blind Study of Nirmatrelvir/Ritonavir Compared with Placebo/Ritonavir for Long COVID
Krumholz H, Sawano M, Bhattacharjee B, Caraballo C, Khera R, Li S, Herrin J, Coppi A, Holub J, Henriquez Y, Johnson M, Goddard T, Rocco E, Hummel A, Al Mouslmani M, Putrino D, Carr K, Carvajal-Gonzalez S, Charnas L, De Jesus M, Ziegler F, Iwasaki A. The PAX LC Trial: A Decentralized, Phase 2, Randomized, Double-blind Study of Nirmatrelvir/Ritonavir Compared with Placebo/Ritonavir for Long COVID. The American Journal Of Medicine 2024 PMID: 38735354, DOI: 10.1016/j.amjmed.2024.04.030.Peer-Reviewed Original ResearchLC trialPROMIS-29Participants' homesTargeting viral persistencePlacebo-controlled trialDouble-blind studyElectronic health recordsCore Outcome MeasuresLong COVIDEQ-5D-5LRepeated measures analysisEvidence-based treatmentsPhase 2Double-blindParticipant-centred approachStudy drugPrimary endpointSecondary endpointsCommunity-dwellingHealth recordsHealthcare utilizationContiguous US statesViral persistencePatient groupDrug treatmentHypertension Trends and Disparities Over 12 Years in a Large Health System: Leveraging the Electronic Health Records
Brush J, Lu Y, Liu Y, Asher J, Li S, Sawano M, Young P, Schulz W, Anderson M, Burrows J, Krumholz H. Hypertension Trends and Disparities Over 12 Years in a Large Health System: Leveraging the Electronic Health Records. Journal Of The American Heart Association 2024, 13: e033253. PMID: 38686864, PMCID: PMC11179912, DOI: 10.1161/jaha.123.033253.Peer-Reviewed Original ResearchConceptsElectronic health recordsRegional health systemImprove hypertension careHealth systemHealth recordsHypertension careDiastolic blood pressureAge-adjusted prevalence ratesNon-Hispanic Black patientsPrevalence ratesLarger health systemCross-sectional analysisTransformation of medical dataLeveraging real-world dataHigh prevalence rateHypertension trendsHypertension prevalenceBlood pressureBlood pressure measurementsHypertension diagnosisPrimary outcomeNational trendsProportion of patientsAntihypertensive medicationsBlack patients
2023
Multinational patterns of second line antihyperglycaemic drug initiation across cardiovascular risk groups: federated pharmacoepidemiological evaluation in LEGEND-T2DM
Khera R, Dhingra L, Aminorroaya A, Li K, Zhou J, Arshad F, Blacketer C, Bowring M, Bu F, Cook M, Dorr D, Duarte-Salles T, DuVall S, Falconer T, French T, Hanchrow E, Horban S, Lau W, Li J, Liu Y, Lu Y, Man K, Matheny M, Mathioudakis N, McLemore M, Minty E, Morales D, Nagy P, Nishimura A, Ostropolets A, Pistillo A, Posada J, Pratt N, Reyes C, Ross J, Seager S, Shah N, Simon K, Wan E, Yang J, Yin C, You S, Schuemie M, Ryan P, Hripcsak G, Krumholz H, Suchard M. Multinational patterns of second line antihyperglycaemic drug initiation across cardiovascular risk groups: federated pharmacoepidemiological evaluation in LEGEND-T2DM. BMJ Medicine 2023, 2: e000651. PMID: 37829182, PMCID: PMC10565313, DOI: 10.1136/bmjmed-2023-000651.Peer-Reviewed Original ResearchType 2 diabetes mellitusSecond-line treatmentCardiovascular risk groupsDiabetes mellitusCardiovascular diseaseAntihyperglycaemic drugsLine treatmentRisk groupsObservational Health Data SciencesGlucagon-like peptide-1 receptor agonistsElectronic health recordsSodium-glucose cotransporter 2 inhibitorsCalendar year trendsPeptide-1 receptor agonistsUS databaseOutcomes of patientsCotransporter 2 inhibitorsAdministrative claims databaseSecond-line drugsHealth recordsSodium-glucose cotransporter-2 inhibitorsMedication useMetformin monotherapyGuideline recommendationsOutcome measuresFoundation models for generalist medical artificial intelligence
Moor M, Banerjee O, Abad Z, Krumholz H, Leskovec J, Topol E, Rajpurkar P. Foundation models for generalist medical artificial intelligence. Nature 2023, 616: 259-265. PMID: 37045921, DOI: 10.1038/s41586-023-05881-4.Peer-Reviewed Original ResearchConceptsMedical AILarge medical datasetsMedical artificial intelligenceArtificial intelligence modelsImage annotationMedical datasetsArtificial intelligenceElectronic health recordsAI devicesIntelligence modelsTraining datasetDiverse datasetsExpressive outputHealth recordsRapid developmentDatasetFree-text explanationsMedical modalitiesNew paradigmMedical textsAITechnical capabilitiesDiverse setNewfound capabilitiesCapabilityDeveloping 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 reportsAlgorithmDeveloping an Actionable Taxonomy of Persistent Hypertension Using Electronic Health Records
Lu Y, Du C, Khidir H, Caraballo C, Mahajan S, Spatz E, Curry L, Krumholz H. Developing an Actionable Taxonomy of Persistent Hypertension Using Electronic Health Records. Circulation Cardiovascular Quality And Outcomes 2023, 16: e009453. PMID: 36727515, DOI: 10.1161/circoutcomes.122.009453.Peer-Reviewed Original ResearchConceptsPersistent hypertensionElectronic health recordsBlood pressureHealth recordsPharmacologic agentsPrescribed treatmentYale New Haven Health SystemTreatment planAdditional pharmacologic agentsAntihypertensive treatment intensificationConsecutive outpatient visitsElevated blood pressurePersistence of hypertensionElectronic health record dataHealth record dataEligible patientsTreatment intensificationChart reviewHispanic patientsOutpatient visitsMean agePharmacological treatmentConventional content analysisHypertensionClinician notes
2022
Neural Natural Language Processing for unstructured data in electronic health records: A review
Li I, Pan J, Goldwasser J, Verma N, Wong W, Nuzumlalı M, Rosand B, Li Y, Zhang M, Chang D, Taylor R, Krumholz H, Radev D. Neural Natural Language Processing for unstructured data in electronic health records: A review. Computer Science Review 2022, 46: 100511. DOI: 10.1016/j.cosrev.2022.100511.Peer-Reviewed Original ResearchNatural language processingElectronic health recordsLanguage processingDeep learning approachHealth recordsRule-based systemNew neural networkVariety of tasksUnstructured dataUnstructured textKnowledge graphEHR applicationsDigital collectionsNeural networkNLP methodsLearning approachWord embeddingsSurvey paperSecondary useMedical dialogueHealthcare eventsTaskProcessingMultilingualityInterpretability
2021
Predictors of increased mortality in untreated moderate aortic stenosis
Gupta A, Liu T, Pounds C, Sharma R, Yong C, Krumholz H, Leon M. Predictors of increased mortality in untreated moderate aortic stenosis. European Heart Journal 2021, 42: ehab724.1573. DOI: 10.1093/eurheartj/ehab724.1573.Peer-Reviewed Original ResearchModerate aortic stenosisLong-term mortalityCoronary artery diseaseSeverity of ASAortic stenosisArtery diseaseAtrial fibrillationHeart failureUntreated severe aortic stenosisWorse long-term mortalityPoor long-term survivalSevere aortic stenosisAortic valve replacementHigh-risk featuresMild aortic stenosisPrognosis of patientsKaplan-Meier analysisLong-term survivalElectronic health recordsValve replacementAS severityMale sexRisk factorsSeverity groupsHigh riskTemporal relationship of computed and structured diagnoses in electronic health record data
Schulz WL, Young HP, Coppi A, Mortazavi BJ, Lin Z, Jean RA, Krumholz HM. Temporal relationship of computed and structured diagnoses in electronic health record data. BMC Medical Informatics And Decision Making 2021, 21: 61. PMID: 33596898, PMCID: PMC7890604, DOI: 10.1186/s12911-021-01416-x.Peer-Reviewed Original ResearchConceptsElectronic health recordsStructured diagnosisOutpatient blood pressureElectronic health record dataAcademic health systemLow-density lipoproteinHealth record dataBlood pressureStructured data elementsAdministrative claimsHypertensionClinical informationHyperlipidemiaClinical phenotypeEquivalent diagnosisVital signsHealth systemDiagnosisProblem listAdditional studiesHealth recordsRecord dataTimely accessEHR dataPatients
2020
Renin–angiotensin system blockers and susceptibility to COVID-19: an international, open science, cohort analysis
Morales DR, Conover MM, You SC, Pratt N, Kostka K, Duarte-Salles T, Fernández-Bertolín S, Aragón M, DuVall SL, Lynch K, Falconer T, van Bochove K, Sung C, Matheny ME, Lambert CG, Nyberg F, Alshammari TM, Williams AE, Park RW, Weaver J, Sena AG, Schuemie MJ, Rijnbeek PR, Williams RD, Lane JCE, Prats-Uribe A, Zhang L, Areia C, Krumholz HM, Prieto-Alhambra D, Ryan PB, Hripcsak G, Suchard MA. Renin–angiotensin system blockers and susceptibility to COVID-19: an international, open science, cohort analysis. The Lancet Digital Health 2020, 3: e98-e114. PMID: 33342753, PMCID: PMC7834915, DOI: 10.1016/s2589-7500(20)30289-2.Peer-Reviewed Original ResearchAngiotensin receptor blockersCalcium channel blockersAcute respiratory distress syndromeAcute kidney injuryHospital admissionRespiratory distress syndromeCOVID-19 diagnosisKidney injuryDistress syndromeDrug classesCohort analysisCOVID-19Renin-angiotensin system blockersThiazide-like diureticsBaseline patient characteristicsUse of ACEIsPost-authorisation studiesUK National InstituteRelative risk differenceNational InstituteCombination useMedical Research CouncilAustralian National HealthElectronic health recordsAntihypertensive usersPrinciples of Large-scale Evidence Generation and Evaluation across a Network of Databases (LEGEND)
Schuemie MJ, Ryan PB, Pratt N, Chen R, You SC, Krumholz HM, Madigan D, Hripcsak G, Suchard MA. Principles of Large-scale Evidence Generation and Evaluation across a Network of Databases (LEGEND). Journal Of The American Medical Informatics Association 2020, 27: 1331-1337. PMID: 32909033, PMCID: PMC7481029, DOI: 10.1093/jamia/ocaa103.Peer-Reviewed Original ResearchConceptsNetwork of databasesLarge-scale Evidence GenerationObservational Health Data SciencesObservational health care databasesHealth Data SciencesHealth care dataElectronic health recordsData sciencePublication biasPatient-level informationGeneric overviewHealth recordsMethods addressAforementioned concernsHealth care databasesAnalytic codeNetworkNew paradigmSuch dataHackingEvidence generationDissemination of evidenceHypertension treatmentResidual confoundingAdministrative claimsComparison of Cardiovascular and Safety Outcomes of Chlorthalidone vs Hydrochlorothiazide to Treat Hypertension
Hripcsak G, Suchard MA, Shea S, Chen R, You SC, Pratt N, Madigan D, Krumholz HM, Ryan PB, Schuemie MJ. Comparison of Cardiovascular and Safety Outcomes of Chlorthalidone vs Hydrochlorothiazide to Treat Hypertension. JAMA Internal Medicine 2020, 180: 542-551. PMID: 32065600, PMCID: PMC7042845, DOI: 10.1001/jamainternmed.2019.7454.Peer-Reviewed Original ResearchConceptsComposite outcome eventsHeart failureMyocardial infarctionOutcome eventsSafety outcomesComposite cardiovascular disease outcomeLarge-scale Evidence GenerationType 2 diabetes mellitusSignificant cardiovascular benefitsAcute renal failureAbnormal weight gainChronic kidney diseaseComposite cardiovascular outcomeFirst-line therapyAdministrative claims databaseComparative cohort studyCardiovascular disease outcomesSudden cardiac deathInpatient care episodesAcute myocardial infarctionPropensity score stratificationComparison of CardiovascularElectronic health recordsAntihypertensive monotherapyChlorthalidone useLeveraging the Electronic Health Records for Population Health: A Case Study of Patients With Markedly Elevated Blood Pressure
Lu Y, Huang C, Mahajan S, Schulz WL, Nasir K, Spatz ES, Krumholz HM. Leveraging the Electronic Health Records for Population Health: A Case Study of Patients With Markedly Elevated Blood Pressure. Journal Of The American Heart Association 2020, 9: e015033. PMID: 32200730, PMCID: PMC7428633, DOI: 10.1161/jaha.119.015033.Peer-Reviewed Original ResearchConceptsDiastolic blood pressureSystolic blood pressureElevated blood pressureBlood pressureElectronic health recordsPopulation health surveillanceHealth recordsYale New Haven Health SystemHealth surveillanceHealth systemPatterns of patientsLarge health systemUsual careOutpatient encountersControl ratePatientsCare patternsPopulation healthMonthsHgSurveillancePrevalenceRecordsVisitsCare
2018
The digital transformation of medicine can revitalize the patient-clinician relationship
Warraich HJ, Califf RM, Krumholz HM. The digital transformation of medicine can revitalize the patient-clinician relationship. Npj Digital Medicine 2018, 1: 49. PMID: 31304328, PMCID: PMC6550259, DOI: 10.1038/s41746-018-0060-2.Peer-Reviewed Original ResearchDigital transformationPatient-clinician relationshipData securityElectronic health recordsAnalytics technologiesSpeech recognitionComputer technologyInformation technologyMundane tasksHealth recordsHealthcare technologiesMajority of patientsDelivery of healthcareClinical care teamDigital phenotypingLives of patientsTechnologyPrior iterationsCare teamHealthcarePatientsNew analytic technologiesHealth professionalsMedical careCliniciansThe 21st Century Cures Act and electronic health records one year later: will patients see the benefits?
Lye CT, Forman HP, Daniel JG, Krumholz HM. The 21st Century Cures Act and electronic health records one year later: will patients see the benefits? Journal Of The American Medical Informatics Association 2018, 25: 1218-1220. PMID: 30184156, PMCID: PMC7646899, DOI: 10.1093/jamia/ocy065.Peer-Reviewed Original ResearchConceptsElectronic health recordsHealth recordsHealth information technologyInformation exchange networkHealth information exchangeData sharingHealth information exchange networkInformation technologyCentury Cures ActInformation exchangeInteroperabilityHealth dataCures ActImplementationAccessResearch initiativesRequirementsExchange networksSharingCertification requirementsNetworkTechnologyPotential benefitsRules
2017
Prediction of Adverse Events in Patients Undergoing Major Cardiovascular Procedures
Mortazavi B, Desai N, Zhang J, Coppi A, Warner F, Krumholz H, Negahban S. Prediction of Adverse Events in Patients Undergoing Major Cardiovascular Procedures. IEEE Journal Of Biomedical And Health Informatics 2017, 21: 1719-1729. PMID: 28287993, DOI: 10.1109/jbhi.2017.2675340.Peer-Reviewed Original ResearchConceptsMajor cardiovascular proceduresElectronic health recordsRespiratory failureAdverse eventsCardiovascular proceduresYale-New Haven HospitalPostoperative respiratory failurePatient cohortHospital costsPatient outcomesSpecific patientPatientsHealth recordsCohort-specific modelsCharacteristic curveInfectionFailureHospitalCohortClinicians