Weipeng Zhou
Postdoctoral Associate in Biomedical Informatics and Data ScienceAbout
Research
Publications
2024
The Automatic Context Measurement Tool (ACMT) to Compile Participant-Specific Built and Social Environment Measures for Health Research: Development and Usability Study
Zhou W, Youngbloom A, Ren X, Saelens B, Mooney S, Mooney S. The Automatic Context Measurement Tool (ACMT) to Compile Participant-Specific Built and Social Environment Measures for Health Research: Development and Usability Study. JMIR Formative Research 2024, 8: e56510. PMID: 39365663, PMCID: PMC11489801, DOI: 10.2196/56510.Peer-Reviewed Original ResearchConceptsUser dataUsability studySensitive dataDocker containersLocal computationSocial environment measuresOpen-sourceSystems expertiseWeb interfaceError correctionUser-friendlyUsersData sourcesEnvironment MeasureNew York CityChildren aged 5 to 9 yearsMeasurement toolsAged 5 to 9 yearsParticipant's addressYork CityHealth behaviorsPopulation healthCity HallNeighborhood measuresUsabilityGeneralizable clinical note section identification with large language models
Zhou W, Miller T. Generalizable clinical note section identification with large language models. JAMIA Open 2024, 7: ooae075. PMID: 39139700, PMCID: PMC11319784, DOI: 10.1093/jamiaopen/ooae075.Peer-Reviewed Original Research
2023
Identifying Rare Circumstances Preceding Female Firearm Suicides: Validating A Large Language Model Approach
Zhou W, Prater L, Goldstein E, Mooney S. Identifying Rare Circumstances Preceding Female Firearm Suicides: Validating A Large Language Model Approach. JMIR Mental Health 2023, 10: e49359. PMID: 37847549, PMCID: PMC10618876, DOI: 10.2196/49359.Peer-Reviewed Original ResearchNational Violent Death Reporting SystemFirearm suicidesViolent Death Reporting SystemFirearm suicide ratesDeath Reporting SystemFirearm suicide deathsMedical examinationFirearm suicide decedentsLaw enforcementViolent deathSuicide decedentsNarrative reportsSuicide ratesEnforcementSuicideSources of dataCircumstancesUnited StatesSuicide deathsCoronerReporting systemLawFirearmRare circumstancesReport dataImproving model transferability for clinical note section classification models using continued pretraining
Zhou W, Yetisgen M, Afshar M, Gao Y, Savova G, Miller T. Improving model transferability for clinical note section classification models using continued pretraining. Journal Of The American Medical Informatics Association 2023, 31: 89-97. PMID: 37725927, PMCID: PMC10746297, DOI: 10.1093/jamia/ocad190.Peer-Reviewed Original ResearchConceptsClinical note sectionsIn-domainClassification modelNatural language processing tasksNeural network-based methodTemporal information extractionLanguage processing tasksDrop of accuracyBERT-based modelsNetwork-based methodsInformation extractionCross-domainModel transferabilityF1 scoreProcessing tasksSocial determinantsBaseline modelPretrainingClassificationImprove model transferabilityNotes sectionModel performanceAccuracyImproved modelDatasetLeafAI: query generator for clinical cohort discovery rivaling a human programmer
Dobbins N, Han B, Zhou W, Lan K, Kim H, Harrington R, Uzuner Ö, Yetisgen M. LeafAI: query generator for clinical cohort discovery rivaling a human programmer. Journal Of The American Medical Informatics Association 2023, 30: 1954-1964. PMID: 37550244, PMCID: PMC10654856, DOI: 10.1093/jamia/ocad149.Peer-Reviewed Original ResearchConceptsUnified Medical Language SystemHuman programmersQuery creationDatabase programmersText processing problemsUnified Medical Language System conceptsState-of-the-artLogical reasoning capabilityKnowledge baseMedical Language SystemRule-based moduleHybrid deep learningQuery generationSchema elementsEntity recognitionReasoning capabilitiesQuery designDeep learningQueryCohort discoveryClinical trial eligibility criteriaLanguage systemConditional reasoningClinical trialsSequence-to-sequence transformationImproving the Transferability of Clinical Note Section Classification Models with BERT and Large Language Model Ensembles.
Zhou W, Dligach D, Afshar M, Gao Y, Miller T. Improving the Transferability of Clinical Note Section Classification Models with BERT and Large Language Model Ensembles. ACL Proceedings 2023, 2023: 125-130. PMID: 37786810, PMCID: PMC10544420.Peer-Reviewed Original ResearchCharacterizing Female Firearm Suicide Circumstances: A Natural Language Processing and Machine Learning Approach
Goldstein E, Mooney S, Takagi-Stewart J, Agnew B, Morgan E, Haviland M, Zhou W, Prater L. Characterizing Female Firearm Suicide Circumstances: A Natural Language Processing and Machine Learning Approach. American Journal Of Preventive Medicine 2023, 65: 278-285. PMID: 36931986, DOI: 10.1016/j.amepre.2023.01.030.Peer-Reviewed Original ResearchConceptsNational Violent Death Reporting SystemViolent Death Reporting SystemFirearm suicide ratesDeath Reporting SystemInterpersonal disputesCoroner/medical examinerIntimate partnersMale firearm suicide rateSuicide ratesFirearm suicidesSuicidal antecedentsNatural language processing pipelineReporting systemDisputesLanguage processing pipelinePositive predictive valueSuicideProcessing pipelineImmediate familyPredictive valueNatural language processingNationalSupport vector machineNarrative reportsMachine learning approachImproving the Transferability of Clinical Note Section Classification Models with BERT and Large Language Model Ensembles
Zhou W, Afshar M, Dligach D, Gao Y, Miller T. Improving the Transferability of Clinical Note Section Classification Models with BERT and Large Language Model Ensembles. 2023, 125-130. DOI: 10.18653/v1/2023.clinicalnlp-1.16.Peer-Reviewed Original Research
2021
Parameter Sensitivity Analysis for the Progressive Sampling-Based Bayesian Optimization Method for Automated Machine Learning Model Selection
Zhou W, Luo G. Parameter Sensitivity Analysis for the Progressive Sampling-Based Bayesian Optimization Method for Automated Machine Learning Model Selection. Lecture Notes In Computer Science 2021, 12633: 213-227. PMID: 33768220, PMCID: PMC7990322, DOI: 10.1007/978-3-030-71055-2_17.Peer-Reviewed Original ResearchMachine learning model selectionLearning model selectionSelection of machine learning algorithmsHyper-parameter valuesModel selectionMethod performanceReal-world problemsMachine learning algorithmsBayesian optimization methodLearning algorithmsMachine learningBayesian optimizationResource requirementsData setsDefault valuesOptimization methodMachineAutomated methodPerformanceAlgorithmParameter value changesLearningMethodSelectionOptimization