2024
Identifying EEG Biomarkers of Depression with Novel Explainable Deep Learning Architectures
Ellis C, Sancho M, Miller R, Calhoun V. Identifying EEG Biomarkers of Depression with Novel Explainable Deep Learning Architectures. Communications In Computer And Information Science 2024, 2156: 102-124. DOI: 10.1007/978-3-031-63803-9_6.Peer-Reviewed Original ResearchDeep learning modelsExplainability methodsExplainability analysisConvolutional neural network architectureLearning modelsRaw electroencephalogramNeural network architectureDeep learning architectureMajor depressive disorderLearning architectureNetwork architectureDeep learningModel architectureMultichannel electroencephalogramTraining approachArchitectureBiomarkers of depressionFrequency bandElectroencephalogramResearch contextDepressive disorderElectroencephalogram biomarkerAccuracyRight hemisphereExplainability
2023
Improving Explainability for Single-Channel EEG Deep Learning Classifiers via Interpretable Filters and Activation Analysis*
Ellis C, Miller R, Calhoun V. Improving Explainability for Single-Channel EEG Deep Learning Classifiers via Interpretable Filters and Activation Analysis*. 2023, 00: 2474-2481. DOI: 10.1109/bibm58861.2023.10385647.Peer-Reviewed Original ResearchDeep learning methodsLearning methodsContext of automated sleep stage classificationDeep learning classifierSleep stage classificationAutomated feature extractionMachine learning methodsImprove explainabilityLearned featuresFeature extractionExplainability methodsAwake samplesLearning classifiersRaw electroencephalographyIncrease model performanceLayer filtersExplainabilityModeling activitiesModel performanceFilterStage classificationClassifierFiltering activityElectroencephalographyFrequency filteringAn Explainable and Robust Deep Learning Approach for Automated Electroencephalography-Based Schizophrenia Diagnosis
Sattiraju A, Ellis C, Miller R, Calhoun V. An Explainable and Robust Deep Learning Approach for Automated Electroencephalography-Based Schizophrenia Diagnosis. 2023, 00: 255-259. DOI: 10.1109/bibe60311.2023.00048.Peer-Reviewed Original ResearchConvolutional neural networkRobust deep learning approachBaseline convolutional neural networkChannel lossDeep learning methodsDeep learning modelsDeep learning approachDecision support roleExplainability approachesClassifier performanceRobust modelNeural networkExplainable modelsLearning methodsLearning approachLearning modelsAutomated diagnosisImplementation environmentEEG dataDiagnosis of SZExplainabilityRaw EEGTest dataRobustnessBiomarkers of SZNovel Approach Explains Spatio-Spectral Interactions In Raw Electroencephalogram Deep Learning Classifiers
Ellis C, Sattiraju A, Miller R, Calhoun V. Novel Approach Explains Spatio-Spectral Interactions In Raw Electroencephalogram Deep Learning Classifiers. 2023, 00: 1-5. DOI: 10.1109/icasspw59220.2023.10193605.Peer-Reviewed Original ResearchNovel methods for elucidating modality importance in multimodal electrophysiology classifiers
Ellis C, Sendi M, Zhang R, Carbajal D, Wang M, Miller R, Calhoun V. Novel methods for elucidating modality importance in multimodal electrophysiology classifiers. Frontiers In Neuroinformatics 2023, 17: 1123376. PMID: 37006636, PMCID: PMC10050434, DOI: 10.3389/fninf.2023.1123376.Peer-Reviewed Original ResearchExplainability approachesExplainability methodsAutomated sleep stage classificationRaw time series dataConvolutional neural networkDeep learning classifierSleep stage classificationNovel methodMultimodal classificationLearning classifiersNeural networkClassifierLocal explanationsGlobal explanationsExplainabilitySubject-level differencesTime series dataAdvancement of personalized medicineGlobal methodClinical classifierClassificationClinical variablesElectrophysiological studiesStage classificationElectrophysiological classification