Featured Publications
Detecting model misconducts in decentralized healthcare federated learning
Kuo T, Pham A. Detecting model misconducts in decentralized healthcare federated learning. International Journal Of Medical Informatics 2021, 158: 104658. PMID: 34923447, PMCID: PMC10017272, DOI: 10.1016/j.ijmedinf.2021.104658.Peer-Reviewed Original ResearchFederated learningFederated machine learningDetection methodDetection frameworkLearning iterationsMalicious intentLearning methodsMachine learningArtificial intelligenceParameter tuningComputational costCross-institutional collaborationLearningLearning processIterationPerformance detectorsDetectionIncorrect modelFrameworkAlgorithmDatasetDetect misconductIntelligencePlagiarismMethod
2022
Quorum-based model learning on a blockchain hierarchical clinical research network using smart contracts
Kuo T, Pham A. Quorum-based model learning on a blockchain hierarchical clinical research network using smart contracts. International Journal Of Medical Informatics 2022, 169: 104924. PMID: 36402113, PMCID: PMC9984225, DOI: 10.1016/j.ijmedinf.2022.104924.Peer-Reviewed Original ResearchConceptsSmart contractsPrivacy-preserving modelHierarchical learning algorithmBlockchain smart contractsProtect patient privacyLearning algorithmsNetwork of networksConsensus protocolModeling processPatient privacyQuorum mechanismHierarchical networkAvailability issuesNetworkPrediction correctnessIterative phasesPrediction modelPrivacyImmutabilityCapabilityHealthcare institutionsAlgorithmDatasetIterationLearning continuityGeneralizable prediction of COVID-19 mortality on worldwide patient data
Edelson M, Kuo T. Generalizable prediction of COVID-19 mortality on worldwide patient data. JAMIA Open 2022, 5: ooac036. PMID: 35663116, PMCID: PMC9129227, DOI: 10.1093/jamiaopen/ooac036.Peer-Reviewed Original Research
2020
EXpectation Propagation LOgistic REgRession on permissioned blockCHAIN (ExplorerChain): decentralized online healthcare/genomics predictive model learning
Kuo T, Gabriel R, Cidambi K, Ohno-Machado L. EXpectation Propagation LOgistic REgRession on permissioned blockCHAIN (ExplorerChain): decentralized online healthcare/genomics predictive model learning. Journal Of The American Medical Informatics Association 2020, 27: 747-756. PMID: 32364235, PMCID: PMC7309256, DOI: 10.1093/jamia/ocaa023.Peer-Reviewed Original ResearchConceptsBlockchain technologyCentral serverServer-based methodBenefits of blockchainData protection policiesCentralized serverArtificial intelligenceModel learningDecentralized approachSmall datasetsBlockchainServerComputation strategySingle pointGeneralizable modelCost of efficiencyGenomic datasetsDatasetDistributed modelTechnologyGenomic dataMultiple institutionsDiscrimination powerIntelligencePotential advantages/disadvantages
2018
Identifying and characterizing highly similar notes in big clinical note datasets
Gabriel R, Kuo T, McAuley J, Hsu C. Identifying and characterizing highly similar notes in big clinical note datasets. Journal Of Biomedical Informatics 2018, 82: 63-69. PMID: 29679685, DOI: 10.1016/j.jbi.2018.04.009.Peer-Reviewed Original ResearchConceptsClinical note datasetsDe-duplication algorithmMIMIC-III datasetElectronic health recordsJaccard similarityDe-duplicationLocality sensitive hashingMIMIC-IIINear-duplicatesScalable algorithmMeasure similarityAccurate statistical modelsSources of duplicationClustering methodDatasetAlgorithmApproximation algorithmHealth recordsDisjoint setsInstitutional datasetComparison of notesPairs of notesHashPairwise comparisonsPairwise
2017
A Collaborative Filtering-Based Two Stage Model with Item Dependency for Course Recommendation
Lee E, Kuo T, Lin S. A Collaborative Filtering-Based Two Stage Model with Item Dependency for Course Recommendation. 2017, 496-503. DOI: 10.1109/dsaa.2017.18.Peer-Reviewed Original Research
2014
Minimizing Expected Loss for Risk-Avoiding Reinforcement Learning
Yeh J, Kuo T, Chen W, Lin S. Minimizing Expected Loss for Risk-Avoiding Reinforcement Learning. 2014, 11-17. DOI: 10.1109/dsaa.2014.7058045.Peer-Reviewed Original ResearchA Transfer-Learning Approach to Exploit Noisy Information for Classification and Its Application on Sentiment Detection
Lin W, Kuo T, Huang Y, Lu W, Lin S. A Transfer-Learning Approach to Exploit Noisy Information for Classification and Its Application on Sentiment Detection. Lecture Notes In Computer Science 2014, 8916: 262-273. DOI: 10.1007/978-3-319-13987-6_25.Peer-Reviewed Original Research
2013
Unsupervised link prediction using aggregative statistics on heterogeneous social networks
Kuo T, Yan R, Huang Y, Kung P, Lin S. Unsupervised link prediction using aggregative statistics on heterogeneous social networks. 2013, 775-783. DOI: 10.1145/2487575.2487614.Peer-Reviewed Original ResearchHeterogeneous social networksSocial networksUnsupervised link predictionFactor graph modelOnline social networksAggregate statisticsLabeled dataUnsupervised frameworkUnsupervised modelInference algorithmLink predictionOpinion holdersGraph modelNetworkDBLPNDCGPlurkPrediction scenariosScenariosPrivacyFoursquareUnsupervisedTwitterAlgorithmDataset
2012
Prediction-Based Outlier Detection with Explanations
Chen L, Kuo T, Lai W, De-Lin S, Tsai C. Prediction-Based Outlier Detection with Explanations. 2012, 44-49. DOI: 10.1109/grc.2012.6468672.Peer-Reviewed Original Research
2011
Learning-based concept-hierarchy refinement through exploiting topology, content and social information
Kuo T, Lin S. Learning-based concept-hierarchy refinement through exploiting topology, content and social information. Information Sciences 2011, 181: 2512-2528. DOI: 10.1016/j.ins.2011.02.006.Peer-Reviewed Original ResearchLearning-based approachConcept hierarchyNormalized Google DistanceWeb 2.0 eraSimilarity-based approachACM CCSTraining instancesGoogle DistanceSource codeRecommendation schemeLearning approachTarget conceptIndexing applicationsDatasetACMMetricsClassification schemeSchemeSocial informationHierarchyTopologyInternetInstancesNew termsConstruction criteria