2018
DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network
Katzman JL, Shaham U, Cloninger A, Bates J, Jiang T, Kluger Y. DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network. BMC Medical Research Methodology 2018, 18: 24. PMID: 29482517, PMCID: PMC5828433, DOI: 10.1186/s12874-018-0482-1.Peer-Reviewed Original ResearchConceptsDeep neural networksPersonalized treatment recommendationsTreatment recommendationsNeural networkTreatment optionsPatient covariatesRecommender systemsSurvival methodsCox proportional hazards modelDifferent treatment optionsProportional hazards modelSurvival modelsExtensive feature engineeringIndividual treatment recommendationsPrior medical knowledgeSet of patientsLinear Cox proportional hazards modelsPatient characteristicsClinical studiesPatient featuresSurvival timeFeature engineeringHazards modelArt survival modelsTreatment effectiveness
2017
Removal of batch effects using distribution-matching residual networks
Shaham U, Stanton KP, Zhao J, Li H, Raddassi K, Montgomery R, Kluger Y. Removal of batch effects using distribution-matching residual networks. Bioinformatics 2017, 33: 2539-2546. PMID: 28419223, PMCID: PMC5870543, DOI: 10.1093/bioinformatics/btx196.Peer-Reviewed Original ResearchConceptsMeasurement errorNovel deep learning approachRandom measurement errorMultivariate distributionsResidual neural networkDeep learning approachNovel biological technologiesMaximum mean discrepancyPhysical phenomenaResidual networkNeural networkLearning approachSystematic componentSupplementary dataSystematic errorsMean discrepancyScRNA-seq datasetsBatch effectsErrorNetworkStatistical analysis