2021
Benchmarking Effectiveness and Efficiency of Deep Learning Models for Semantic Textual Similarity in the Clinical Domain: Validation Study
Chen Q, Rankine A, Peng Y, Aghaarabi E, Lu Z. Benchmarking Effectiveness and Efficiency of Deep Learning Models for Semantic Textual Similarity in the Clinical Domain: Validation Study. JMIR Medical Informatics 2021, 9: e27386. PMID: 34967748, PMCID: PMC8759018, DOI: 10.2196/27386.Peer-Reviewed Original ResearchSemantic textual similarityConvolutional neural networkDeep learning modelsReal-time applicationsDL modelsSentence pairsNeural networkTextual similarityBERT modelNational Natural Language Processing Clinical ChallengesLearning modelNatural language processingAverage Pearson correlationData setsDifferent similarity levelsInference timeGeneralization capabilityManual annotationLanguage processingPearson correlationEnsemble modelWord orderTime efficiencyNegation termsTraining set
2020
Deep learning with sentence embeddings pre-trained on biomedical corpora improves the performance of finding similar sentences in electronic medical records
Chen Q, Du J, Kim S, Wilbur W, Lu Z. Deep learning with sentence embeddings pre-trained on biomedical corpora improves the performance of finding similar sentences in electronic medical records. BMC Medical Informatics And Decision Making 2020, 20: 73. PMID: 32349758, PMCID: PMC7191680, DOI: 10.1186/s12911-020-1044-0.Peer-Reviewed Original ResearchConceptsEnd deep learning modelEncoder networkDeep learning modelsSentence embeddingsBiomedical corporaLearning modelRandom forestTraditional machineText mining applicationsDeep learning approachSimilar sentencesMachine learning modelsHigh performanceMining applicationsRelated datasetsClinical notesLearning approachSentence semanticsPubMed abstractsChallenge taskEnsembled modelBest submissionSentence pairsNetworkTest setBioConceptVec: Creating and evaluating literature-based biomedical concept embeddings on a large scale
Chen Q, Lee K, Yan S, Kim S, Wei C, Lu Z. BioConceptVec: Creating and evaluating literature-based biomedical concept embeddings on a large scale. PLOS Computational Biology 2020, 16: e1007617. PMID: 32324731, PMCID: PMC7237030, DOI: 10.1371/journal.pcbi.1007617.Peer-Reviewed Original ResearchConceptsConcept embeddingsNER toolsLearning modelBiomedical text mining applicationsAdvanced deep learning modelsDifferent machine learning modelsEvaluation resultsText mining applicationsDeep learning modelsSemantics of conceptsMachine learning modelsLiterature-based discoveryConcept recognitionDifferent machineProtein-protein interaction predictionPubMed abstractsRecognition toolsMassive numberVector representationBiomedical conceptsLarge marginExtrinsic evaluationBiomedical literatureIntrinsic evaluationSemantic relatedness
2019
A multi-task deep learning model for the classification of Age-related Macular Degeneration.
Chen Q, Peng Y, Keenan T, Dharssi S, Agro N E, Wong W, Chew E, Lu Z. A multi-task deep learning model for the classification of Age-related Macular Degeneration. AMIA Joint Summits On Translational Science Proceedings 2019, 2019: 505-514. PMID: 31259005, PMCID: PMC6568069.Peer-Reviewed Original ResearchDeep learning modelsLearning modelMulti-task deep learning modelNovel deep learning modelMulti-task learning techniquesColor fundus imagesImage datasetsLearning techniquesAutomated classificationManual classificationArt modelsManual gradingFundus imagesGrading processClassificationImagesAge-related macular degenerationCurrent stateEye Disease Study GroupAMD severity scaleOverfittingDatasetMacular degenerationModelAccuracy
2018
DeepSeeNet: A Deep Learning Model for Automated Classification of Patient-based Age-related Macular Degeneration Severity from Color Fundus Photographs
Peng Y, Dharssi S, Chen Q, Keenan T, Agrón E, Wong W, Chew E, Lu Z. DeepSeeNet: A Deep Learning Model for Automated Classification of Patient-based Age-related Macular Degeneration Severity from Color Fundus Photographs. Ophthalmology 2018, 126: 565-575. PMID: 30471319, PMCID: PMC6435402, DOI: 10.1016/j.ophtha.2018.11.015.Peer-Reviewed Original ResearchMeSH KeywordsAgedAged, 80 and overArea Under CurveDeep LearningDiagnosis, Computer-AssistedDiagnostic Techniques, OphthalmologicalDisease ProgressionFemaleGeographic AtrophyHumansMaleMiddle AgedModels, TheoreticalPhotographyProspective StudiesReproducibility of ResultsRetinal DrusenRisk FactorsSensitivity and SpecificitySeverity of Illness IndexConceptsLate age-related macular degenerationAge-related macular degenerationColor fundus photographsSeverity ScaleRetinal specialistsSeverity scoreDeep learning modelsLarge drusenFundus photographsPigmentary abnormalitiesAge-related macular degeneration (AMD) severityPatient-based scoring systemsAMD risk factorsRisk of progressionLearning modelEye Disease StudyDeep learning systemGold-standard labelsRisk factorsMacular degenerationIndividual patientsGrading processPatient-based classificationPatientsScoring system