2023
AIONER: all-in-one scheme-based biomedical named entity recognition using deep learning
Luo L, Wei C, Lai P, Leaman R, Chen Q, Lu Z. AIONER: all-in-one scheme-based biomedical named entity recognition using deep learning. Bioinformatics 2023, 39: btad310. PMID: 37171899, PMCID: PMC10212279, DOI: 10.1093/bioinformatics/btad310.Peer-Reviewed Original ResearchConceptsDeep learningEntity recognitionTraining dataEntity typesLabeling training dataNatural language textText mining tasksSignificant domain expertiseMulti-task learningMining tasksInformation extractionBioNER taskDomain expertiseBiomedical entitiesIndependent tasksSource codeBenchmark tasksLanguage textBiomedical textArt approachesAccurate annotationExternal dataData scarcityTaskLearning
2022
Multi-task deep learning-based survival analysis on the prognosis of late AMD using the longitudinal data in AREDS.
Ghahramani G, Brendel M, Lin M, Chen Q, Keenan T, Chen K, Chew E, Lu Z, Peng Y, Wang F. Multi-task deep learning-based survival analysis on the prognosis of late AMD using the longitudinal data in AREDS. AMIA Annual Symposium Proceedings 2022, 2021: 506-515. PMID: 35308963.Peer-Reviewed Original ResearchMeSH KeywordsDeep LearningDisease ProgressionFundus OculiHumansMacular DegenerationPrognosisSurvival AnalysisConceptsAge-related macular degenerationImage featuresMulti-task learning frameworkConvolutional neural networkVision lossLate age-related macular degenerationEye Disease StudyLearning frameworkNeural networkFundus photographsPatient riskMacular degenerationStandard featuresSevere formComplex featuresSurvival analysisCurrent visitLongitudinal dataDisease StudyHistorical dataRapid paceFeaturesNetworkAREDSPatientsDetecting visually significant cataract using retinal photograph-based deep learning
Tham Y, Goh J, Anees A, Lei X, Rim T, Chee M, Wang Y, Jonas J, Thakur S, Teo Z, Cheung N, Hamzah H, Tan G, Husain R, Sabanayagam C, Wang J, Chen Q, Lu Z, Keenan T, Chew E, Tan A, Mitchell P, Goh R, Xu X, Liu Y, Wong T, Cheng C. Detecting visually significant cataract using retinal photograph-based deep learning. Nature Aging 2022, 2: 264-271. PMID: 37118370, PMCID: PMC10154193, DOI: 10.1038/s43587-022-00171-6.Peer-Reviewed Original ResearchDeepLensNet: Deep Learning Automated Diagnosis and Quantitative Classification of Cataract Type and Severity
Keenan T, Chen Q, Agrón E, Tham Y, Goh J, Lei X, Ng Y, Liu Y, Xu X, Cheng C, Bikbov M, Jonas J, Bhandari S, Broadhead G, Colyer M, Corsini J, Cousineau-Krieger C, Gensheimer W, Grasic D, Lamba T, Magone M, Maiberger M, Oshinsky A, Purt B, Shin S, Thavikulwat A, Lu Z, Chew E, Group A, Ajilore P, Akman A, Azar N, Azar W, Chan B, Cox V, Dave A, Dhanjal R, Donovan M, Farrell M, Finkel F, Goblirsch T, Ha W, Hill C, Kumar A, Kent K, Lee A, Patel P, Peprah D, Piliponis E, Selzer E, Swaby B, Tenney S, Zeleny A. DeepLensNet: Deep Learning Automated Diagnosis and Quantitative Classification of Cataract Type and Severity. Ophthalmology 2022, 129: 571-584. PMID: 34990643, PMCID: PMC9038670, DOI: 10.1016/j.ophtha.2021.12.017.Peer-Reviewed Original ResearchConceptsAge-related cataractSingapore Malay Eye StudyAnterior segment photographsCortical lens opacitiesPosterior subcapsular cataractCommon typeSlit-lamp photographsLeast common typeMedical studentsEye StudyNuclear sclerosisSubcapsular cataractLens opacitiesCataract typesRetroillumination photographsCataract assessmentOphthalmologistsCataract severityCataractExternal validationDiagnosisSeveritySclerosisStudy dataset
2021
Multimodal, multitask, multiattention (M3) deep learning detection of reticular pseudodrusen: Toward automated and accessible classification of age-related macular degeneration
Chen Q, Keenan T, Allot A, Peng Y, Agrón E, Domalpally A, Klaver C, Luttikhuizen D, Colyer M, Cukras C, Wiley H, Magone M, Cousineau-Krieger C, Wong W, Zhu Y, Chew E, Lu Z, Group F. Multimodal, multitask, multiattention (M3) deep learning detection of reticular pseudodrusen: Toward automated and accessible classification of age-related macular degeneration. Journal Of The American Medical Informatics Association 2021, 28: 1135-1148. PMID: 33792724, PMCID: PMC8200273, DOI: 10.1093/jamia/ocaa302.Peer-Reviewed Original ResearchConceptsColor fundus photographyAge-related macular degenerationFundus autofluorescenceReticular pseudodrusenMacular degenerationStandard color fundus photographyReceiver-operating characteristic curveAdvanced imaging modalitiesExternal validationRetinal specialistsAMD featuresFundus photographyGeographic atrophyPigmentary abnormalitiesAMD diagnosisImaging modalitiesCharacteristic curvePseudodrusenDegeneration
2020
Deep Learning Automated Detection of Reticular Pseudodrusen from Fundus Autofluorescence Images or Color Fundus Photographs in AREDS2
Keenan T, Chen Q, Peng Y, Domalpally A, Agrón E, Hwang C, Thavikulwat A, Lee D, Li D, Wong W, Lu Z, Chew E. Deep Learning Automated Detection of Reticular Pseudodrusen from Fundus Autofluorescence Images or Color Fundus Photographs in AREDS2. Ophthalmology 2020, 127: 1674-1687. PMID: 32447042, PMCID: PMC11079794, DOI: 10.1016/j.ophtha.2020.05.036.Peer-Reviewed Original ResearchDeep 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
ML-Net: multi-label classification of biomedical texts with deep neural networks
Du J, Chen Q, Peng Y, Xiang Y, Tao C, Lu Z. ML-Net: multi-label classification of biomedical texts with deep neural networks. Journal Of The American Medical Informatics Association 2019, 26: 1279-1285. PMID: 31233120, PMCID: PMC7647240, DOI: 10.1093/jamia/ocz085.Peer-Reviewed Original ResearchConceptsMulti-label classificationML-NetBiomedical textEnd deep learning frameworkMulti-label text classificationDeep learning frameworkDeep neural networksTraditional machineDocument contextFeature engineeringText classificationTextual documentsMachine learningNovel endLearning frameworkPrediction networkIndividual classifiersNeural networkHuman effortTarget documentsF-measureArt methodsPrediction mechanismContextual informationLabel countsA Deep Learning Approach for Automated Detection of Geographic Atrophy from Color Fundus Photographs
Keenan T, Dharssi S, Peng Y, Chen Q, Agrón E, Wong W, Lu Z, Chew E. A Deep Learning Approach for Automated Detection of Geographic Atrophy from Color Fundus Photographs. Ophthalmology 2019, 126: 1533-1540. PMID: 31358385, PMCID: PMC6810830, DOI: 10.1016/j.ophtha.2019.06.005.Peer-Reviewed Original Research
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