2024
HEART: Learning better representation of EHR data with a heterogeneous relation-aware transformer
Huang T, Rizvi S, Thakur R, Socrates V, Gupta M, van Dijk D, Taylor R, Ying R. HEART: Learning better representation of EHR data with a heterogeneous relation-aware transformer. Journal Of Biomedical Informatics 2024, 104741. PMID: 39476994, DOI: 10.1016/j.jbi.2024.104741.Peer-Reviewed Original ResearchElectronic health recordsElectronic health record datasetDownstream tasksLanguage modelModeling electronic health recordsLearning better representationsPretrained language modelsEntity predictionRepresentation learningAnomaly detectionAttention weightsRelation embeddingsHealthcare applicationsEncoding schemeMed-BERTHigher-order representationsInput sequenceComputational costReadmission predictionPairwise relationshipsEHR dataElectronic health record dataSuperior performanceHeterogeneous contextsMedical entitiesAccelerated Chest Pain Treatment With Artificial Intelligence–Informed, Risk-Driven Triage
Hinson J, Taylor R, Venkatesh A, Steinhart B, Chmura C, Sangal R, Levin S. Accelerated Chest Pain Treatment With Artificial Intelligence–Informed, Risk-Driven Triage. JAMA Internal Medicine 2024, 184: 1125-1127. PMID: 39037785, PMCID: PMC11264065, DOI: 10.1001/jamainternmed.2024.3219.Peer-Reviewed Original ResearchBalancing act: the complex role of artificial intelligence in addressing burnout and healthcare workforce dynamics
Pavuluri S, Sangal R, Sather J, Taylor R. Balancing act: the complex role of artificial intelligence in addressing burnout and healthcare workforce dynamics. BMJ Health & Care Informatics Online 2024, 31: e101120. PMID: 39181545, PMCID: PMC11344516, DOI: 10.1136/bmjhci-2024-101120.Peer-Reviewed Original ResearchConceptsQuality of patient careSustainability of health systemsComplexity of medical informationArtificial intelligenceWorkforce attritionHealth systemClinical skillsPatient careSense of purposeHealthcare workersHealthcareMedical informationWorkforce dynamicsMedical practiceProfessional attributesDigital scribeData management systemCognitive burdenBurnoutAdvanced data management systemsAI technologyAI potentialAutomated billingSignificant riskCaregiversPatient-Representing Population's Perceptions of GPT-Generated Versus Standard Emergency Department Discharge Instructions: Randomized Blind Survey Assessment
Huang T, Safranek C, Socrates V, Chartash D, Wright D, Dilip M, Sangal R, Taylor R. Patient-Representing Population's Perceptions of GPT-Generated Versus Standard Emergency Department Discharge Instructions: Randomized Blind Survey Assessment. Journal Of Medical Internet Research 2024, 26: e60336. PMID: 39094112, PMCID: PMC11329854, DOI: 10.2196/60336.Peer-Reviewed Original ResearchRacial, Ethnic, and Age-Related Disparities in Sedation and Restraint Use for Older Adults in the Emergency Department
Jivalagian P, Gettel C, Smith C, Robinson L, Brinker M, Shah D, Kumar A, Faustino I, Nath B, Chang-Sing E, Taylor R, Kennedy M, Hwang U, Wong A. Racial, Ethnic, and Age-Related Disparities in Sedation and Restraint Use for Older Adults in the Emergency Department. American Journal Of Geriatric Psychiatry 2024 PMID: 39054237, DOI: 10.1016/j.jagp.2024.07.004.Peer-Reviewed Original ResearchPhysical restraint useRestraint useOlder adultsED visitsPhysical restraintEmergency departmentElectronic health record dataHealth record dataBlack non-HispanicPatient-level characteristicsAge-related disparitiesAssociated with increased useRegional hospital networkCross-sectional studyLogistic regression modelsChemical sedationRetrospective cross-sectional studyNon-Hispanic groupNon-HispanicAgitation managementHospital sitesHospital networkRecord dataWhite non-Hispanic groupPrimary outcomeComputationally derived transition points across phases of clinical care
Gilson A, Chartash D, Taylor R, Hart L. Computationally derived transition points across phases of clinical care. Npj Digital Medicine 2024, 7: 151. PMID: 38862589, PMCID: PMC11167560, DOI: 10.1038/s41746-024-01145-1.Peer-Reviewed Original ResearchSOFA score performs worse than age for predicting mortality in patients with COVID-19
Sherak R, Sajjadi H, Khimani N, Tolchin B, Jubanyik K, Taylor R, Schulz W, Mortazavi B, Haimovich A. SOFA score performs worse than age for predicting mortality in patients with COVID-19. PLOS ONE 2024, 19: e0301013. PMID: 38758942, PMCID: PMC11101117, DOI: 10.1371/journal.pone.0301013.Peer-Reviewed Original ResearchConceptsCrisis standards of careIn-hospital mortalityIntensive care unitAcademic health systemSequential Organ Failure Assessment scoreCohort of intensive care unitSequential Organ Failure AssessmentStandard of careLogistic regression modelsMortality predictionPredicting in-hospital mortalityHealth systemUnivariate logistic regression modelCrisis standardsDisease morbidityCOVID-19Geriatric End-of-Life Screening Tool Prediction of 6-Month Mortality in Older Patients
Haimovich A, Burke R, Nathanson L, Rubins D, Taylor R, Kross E, Ouchi K, Shapiro N, Schonberg M. Geriatric End-of-Life Screening Tool Prediction of 6-Month Mortality in Older Patients. JAMA Network Open 2024, 7: e2414213. PMID: 38819823, PMCID: PMC11143461, DOI: 10.1001/jamanetworkopen.2024.14213.Peer-Reviewed Original ResearchConceptsElectronic health recordsEmergency departmentObserved mortality rateED encountersEnd-of-Life Screening ToolOlder adultsEnd-of-life preferencesMortality riskIllness criteriaLife-limiting illnessOptimal screening criteriaDays of ED arrivalEHR-based algorithmTertiary care EDLow risk of mortalityHigher mortality riskMortality rateRisk of mortalityHealth recordsReceiver operating characteristic curveIllness diagnosisMain OutcomesED arrivalSerious illnessDemographic subgroupsImpact of the geriatric emergency medicine specialist intervention on final emergency department disposition
Cohen I, Sangal R, Taylor R, Crawford A, Lai J, Martin P, Palleschi S, Rothenberg C, Tomasino D, Hwang U. Impact of the geriatric emergency medicine specialist intervention on final emergency department disposition. Journal Of The American Geriatrics Society 2024, 72: 2017-2026. PMID: 38667266, DOI: 10.1111/jgs.18908.Peer-Reviewed Original ResearchED length of stayED lengthLength of stayObservation admissionsED dispositionInpatient admissionsEmergency departmentOdds of inpatient admissionRate of hospital admissionsAdvanced practice providersGeriatric ED patientsEmergency medicine specialistsTarget trial emulation frameworkHospital admission ratesOdds of dischargeRegional healthcare systemEmergency department dispositionIncreased odds of dischargeCare planningPractice providersED sitesED visitsOlder adultsSpecialist interventionAdmission ratesIdentifying signs and symptoms of urinary tract infection from emergency department clinical notes using large language models
Iscoe M, Socrates V, Gilson A, Chi L, Li H, Huang T, Kearns T, Perkins R, Khandjian L, Taylor R. Identifying signs and symptoms of urinary tract infection from emergency department clinical notes using large language models. Academic Emergency Medicine 2024, 31: 599-610. PMID: 38567658, DOI: 10.1111/acem.14883.Peer-Reviewed Original ResearchElectronic health recordsNatural language processingNatural language processing modelsEmergency departmentTransformer-based modelsClinical notesF1-measureClinical decision supportLanguage modelSpaCy modelsU.S. health systemElements of natural language processingPublic health surveillanceConvolutional neural network-based modelProcessing long documentsIdentification of symptomsHealth recordsHealth systemClinician notesNeural network-based modelMedical careHealth surveillanceSymptom identificationEntity recognitionNetwork-based modelAutomated HEART score determination via ChatGPT: Honing a framework for iterative prompt development
Safranek C, Huang T, Wright D, Wright C, Socrates V, Sangal R, Iscoe M, Chartash D, Taylor R. Automated HEART score determination via ChatGPT: Honing a framework for iterative prompt development. Journal Of The American College Of Emergency Physicians Open 2024, 5: e13133. PMID: 38481520, PMCID: PMC10936537, DOI: 10.1002/emp2.13133.Peer-Reviewed Original ResearchPrompt designsChest pain evaluationRule-based logicScore determinationLanguage modelPrivacy safeguardsPrompt improvementExtract insightsPain evaluationClinical notesRate of responseDiagnostic performancePhysician assessmentPrompt testingDetermination of heartChatGPTDesign frameworkNote analysisHeartSubscoresSimulated patientsClinical spaceIdentifying incarceration status in the electronic health record using large language models in emergency department settings
Huang T, Socrates V, Gilson A, Safranek C, Chi L, Wang E, Puglisi L, Brandt C, Taylor R, Wang K. Identifying incarceration status in the electronic health record using large language models in emergency department settings. Journal Of Clinical And Translational Science 2024, 8: e53. PMID: 38544748, PMCID: PMC10966832, DOI: 10.1017/cts.2024.496.Peer-Reviewed Original ResearchElectronic health recordsNatural language processingHealth recordsIncarceration statusSignificant social determinant of healthSocial determinants of healthClinic electronic health recordsEHR databasePopulation health initiativesDeterminants of healthMitigate health disparitiesRacial health inequitiesEmergency department settingICD-10 codesHealth inequalitiesNatural language processing modelsHealth disparitiesHealth initiativesDepartment settingEmergency departmentSystem interventionsICD-10Clinical notesStudy populationLanguage modelThe Scope of Multimorbidity in Family Medicine: Identifying Age Patterns Across the Lifespan
Chartash D, Gilson A, Taylor R, Hart L. The Scope of Multimorbidity in Family Medicine: Identifying Age Patterns Across the Lifespan. The Journal Of The American Board Of Family Medicine 2024, 37: 251-260. PMID: 38740476, DOI: 10.3122/jabfm.2023.230221r1.Peer-Reviewed Original ResearchConceptsRates of multimorbidityICD-10 diagnostic codesFamily medicine clinicPresence of multimorbidityHealth care systemCardiometabolic disordersMedical historyStudy periodMultimorbidity rateMultimorbidity indexGroup of diagnosesPatient transitionsFamily medicineGeriatric careRetrospective cohort studyCare systemMental healthMultimorbidityMedicine clinicDiagnostic codesPractical resourcesAlcohol use disorderCohort studyAged 0Age groupsCorrection: How Does ChatGPT Perform on the United States Medical Licensing Examination (USMLE)? The Implications of Large Language Models for Medical Education and Knowledge Assessment
Gilson A, Safranek C, Huang T, Socrates V, Chi L, Taylor R, Chartash D. Correction: How Does ChatGPT Perform on the United States Medical Licensing Examination (USMLE)? The Implications of Large Language Models for Medical Education and Knowledge Assessment. JMIR Medical Education 2024, 10: e57594. PMID: 38412478, PMCID: PMC10933712, DOI: 10.2196/57594.Peer-Reviewed Original ResearchFormative evaluation of an emergency department clinical decision support system for agitation symptoms: a study protocol
Wong A, Nath B, Shah D, Kumar A, Brinker M, Faustino I, Boyce M, Dziura J, Heckmann R, Yonkers K, Bernstein S, Adapa K, Taylor R, Ovchinnikova P, McCall T, Melnick E. Formative evaluation of an emergency department clinical decision support system for agitation symptoms: a study protocol. BMJ Open 2024, 14: e082834. PMID: 38373857, PMCID: PMC10882402, DOI: 10.1136/bmjopen-2023-082834.Peer-Reviewed Original ResearchConceptsComputerised clinical decision supportED treatRestraint useExperiences of restraint useMental health-related visitsEmergency departmentPrevent agitationSystems-related factorsImprove patient experienceClinical decision support systemsRegional health systemClinical decision supportDe-escalation techniquesRandomised controlled trialsFormative evaluationPeer-reviewed journalsBest-practice guidanceAt-risk populationsCDS toolsThematic saturationED cliniciansPatient experienceED sitesHealth systemED physicians
2023
Dementia risk analysis using temporal event modeling on a large real-world dataset
Taylor R, Gilson A, Chi L, Haimovich A, Crawford A, Brandt C, Magidson P, Lai J, Levin S, Mecca A, Hwang U. Dementia risk analysis using temporal event modeling on a large real-world dataset. Scientific Reports 2023, 13: 22618. PMID: 38114545, PMCID: PMC10730574, DOI: 10.1038/s41598-023-49330-8.Peer-Reviewed Original ResearchComplexity Measurement for Multitask Classification Problems in Machine Learning
Villuendas-Rey Y, Taylor R. Complexity Measurement for Multitask Classification Problems in Machine Learning. 2023, 00: 6-11. DOI: 10.1109/iscmi59957.2023.10458451.Peer-Reviewed Original ResearchClassification problemMachine learningHandling real-world scenariosReal-world scenariosRough set theoryComplexity measuresMachine learning methodsPublic datasetsGranular computingData quality measuresTarget labelsLearning methodsProblem spaceSet theoryMultitask problemsIncomplete datasetsProblem difficultyMachineQuality measuresDatasetPreliminary evaluationIntrinsic measureClassificationLearningMultitaskingAdoption of Emergency Department–Initiated Buprenorphine for Patients With Opioid Use Disorder
Gao E, Melnick E, Paek H, Nath B, Taylor R, Loza A. Adoption of Emergency Department–Initiated Buprenorphine for Patients With Opioid Use Disorder. JAMA Network Open 2023, 6: e2342786. PMID: 37948075, PMCID: PMC10638655, DOI: 10.1001/jamanetworkopen.2023.42786.Peer-Reviewed Original ResearchConceptsHealth care systemED initiationOpioid use disorderBuprenorphine initiationCare systemUse disordersEmergency Department-Initiated BuprenorphineSecondary analysisClinician's roleEmergency department initiationClinical decision support interventionClinical decision support toolProportional hazard modelingCare of patientsNetwork of cliniciansDecision support interventionsAdvanced practice practitionersDose-dependent mannerUnique cliniciansTime-dependent covariatesTrial interventionNonintervention groupED clustersMore effective interventionsNumber of exposuresComputational phenotypes for patients with opioid-related disorders presenting to the emergency department
Taylor R, Gilson A, Schulz W, Lopez K, Young P, Pandya S, Coppi A, Chartash D, Fiellin D, D’Onofrio G. Computational phenotypes for patients with opioid-related disorders presenting to the emergency department. PLOS ONE 2023, 18: e0291572. PMID: 37713393, PMCID: PMC10503758, DOI: 10.1371/journal.pone.0291572.Peer-Reviewed Original ResearchConceptsSubstance use disordersUse disordersED visitsPatient presentationCarlson comorbidity indexOpioid-related diagnosesOpioid-related disordersOne-year survivalRate of medicationOpioid use disorderElectronic health record dataPatient-oriented outcomesYears of ageHealth record dataChronic substance use disordersED returnComorbidity indexAcute overdoseMedical managementClinical entityRetrospective studyEmergency departmentChronic conditionsInclusion criteriaUnique cohortAuthors’ Reply to: Variability in Large Language Models’ Responses to Medical Licensing and Certification Examinations
Gilson A, Safranek C, Huang T, Socrates V, Chi L, Taylor R, Chartash D. Authors’ Reply to: Variability in Large Language Models’ Responses to Medical Licensing and Certification Examinations. JMIR Medical Education 2023, 9: e50336. PMID: 37440299, PMCID: PMC10375396, DOI: 10.2196/50336.Peer-Reviewed Original Research