2025
Identifying Deprescribing Opportunities With Large Language Models in Older Adults: Retrospective Cohort Study
Socrates V, Wright D, Huang T, Fereydooni S, Dien C, Chi L, Albano J, Patterson B, Kanaparthy N, Wright C, Loza A, Chartash D, Iscoe M, Taylor R. Identifying Deprescribing Opportunities With Large Language Models in Older Adults: Retrospective Cohort Study. JMIR Aging 2025, 8: e69504. PMID: 40215480, PMCID: PMC12032504, DOI: 10.2196/69504.Peer-Reviewed Original ResearchAutomated computation of the HEART score with the GPT-4 large language model
Wright D, Socrates V, Huang T, Safranek C, Sangal R, Dilip M, Boivin Z, Srica N, Wright C, Feher A, Miller E, Chartash D, Taylor R. Automated computation of the HEART score with the GPT-4 large language model. The American Journal Of Emergency Medicine 2025, 93: 120-125. PMID: 40184662, PMCID: PMC12202168, DOI: 10.1016/j.ajem.2025.03.065.Peer-Reviewed Original ResearchConceptsClinical decision supportHEART scoreChest pain observation unitAverage heart scoreCohen's weighted kappaDecision supportNurse practitionersPhysician assistantsRetrospective cohort studyRoutine careCases of disagreementProspective InvestigationAPP scoresCohort studySafety interventionsPhysician judgmentObservation unitAdverse cardiac eventsInstitutional registryScoresPhysiciansInterventionParticipantsNo significant differenceAppsUsing natural language processing to identify emergency department patients with incidental lung nodules requiring follow‐up
Moore C, Socrates V, Hesami M, Denkewicz R, Cavallo J, Venkatesh A, Taylor R. Using natural language processing to identify emergency department patients with incidental lung nodules requiring follow‐up. Academic Emergency Medicine 2025, 32: 274-283. PMID: 39821298, DOI: 10.1111/acem.15080.Peer-Reviewed Original ResearchNatural language processingIncidental lung nodulesFollow-upChest CTsCT reportsF1 scoreLung nodulesEmergency departmentLanguage processingFollow-up of incidental findingsIncidental findingNatural language processing developersAbsence of malignancyMetrics of precisionNatural language processing pipelineNatural language processing metricsChest CT reportsRecommended follow-upEmergency department patientsFollow-up rateLanguage modelLung cancerReduce errorsMalignancyDepartment patientsCharacterizing Emergency Department Care for Patients With Histories of Incarceration
Huang T, Socrates V, Ovchinnikova P, Faustino I, Kumar A, Safranek C, Chi L, Wang E, Puglisi L, Wong A, Wang K, Taylor R. Characterizing Emergency Department Care for Patients With Histories of Incarceration. Journal Of The American College Of Emergency Physicians Open 2025, 6: 100022. PMID: 40012663, PMCID: PMC11852703, DOI: 10.1016/j.acepjo.2024.100022.Peer-Reviewed Original ResearchCare processesHistory of incarcerationRestraint useEmergency departmentHealth care team membersMeasuring care processesCompare socio-demographic characteristicsCare team membersHealth care disparitiesEmergency department careHealth care systemSocio-demographic characteristicsUnique patient encountersMultivariate logistic regressionCare disparitiesHealth behaviorsED settingCare systemPatient encountersSubstance use historyMedical adviceLogistic regressionDemographic characteristicsTeam membersCare
2024
Leveraging artificial intelligence to reduce diagnostic errors in emergency medicine: Challenges, opportunities, and future directions
Taylor R, Sangal R, Smith M, Haimovich A, Rodman A, Iscoe M, Pavuluri S, Rose C, Janke A, Wright D, Socrates V, Declan A. Leveraging artificial intelligence to reduce diagnostic errors in emergency medicine: Challenges, opportunities, and future directions. Academic Emergency Medicine 2024, 32: 327-339. PMID: 39676165, PMCID: PMC11921089, DOI: 10.1111/acem.15066.Peer-Reviewed Original ResearchClinical decision supportEmergency departmentArtificial intelligencePatient safetyDiagnostic errorsImplementing AIImprove patient safetyClinical decision support systemsEnhance patient outcomesReducing diagnostic errorsLeverage artificial intelligenceEmergency medicineHealth careTargeted educationReduce cognitive loadQuality improvementEmergency cliniciansData retrievalReal-time insightsDecision supportPatient outcomesCognitive overloadInformation-gathering processPatient detailsCliniciansHEART: 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, 159: 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 entitiesPatient-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 ResearchIdentifying 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 modelCorrection: 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 ResearchYale at “Discharge Me!”: Evaluating Constrained Generation of Discharge Summaries with Unstructured and Structured Information
Socrates V, Huang T, Ai X, Fereydooni S, Chen Q, Taylor R, Chartash D. Yale at “Discharge Me!”: Evaluating Constrained Generation of Discharge Summaries with Unstructured and Structured Information. 2024, 724-730. DOI: 10.18653/v1/2024.bionlp-1.64.Peer-Reviewed Original Research
2023
How Does ChatGPT Perform on the United States Medical Licensing Examination? 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. How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Models for Medical Education and Knowledge Assessment. JMIR Medical Education 2023, 9: e45312. PMID: 36753318, PMCID: PMC9947764, DOI: 10.2196/45312.Peer-Reviewed Original Research
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply