2024
HEART: Learning better representation of EHR data with a heterogeneous relation-aware transformer
Huang T, Rizvi S, Thakur R, Socrates V, Gupta M, van Dijk D, Taylor R, Ying R. HEART: Learning better representation of EHR data with a heterogeneous relation-aware transformer. Journal Of Biomedical Informatics 2024, 159: 104741. PMID: 39476994, DOI: 10.1016/j.jbi.2024.104741.Peer-Reviewed Original ResearchElectronic health recordsElectronic health record datasetDownstream tasksLanguage modelModeling electronic health recordsLearning better representationsPretrained language modelsEntity predictionRepresentation learningAnomaly detectionAttention weightsRelation embeddingsHealthcare applicationsEncoding schemeMed-BERTHigher-order representationsInput sequenceComputational costReadmission predictionPairwise relationshipsEHR dataElectronic health record dataSuperior performanceHeterogeneous contextsMedical entitiesNanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays
Roche S, Bayer Q, Carlson B, Ouligian W, Serhiayenka P, Stelzer J, Hong T. Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays. Nature Communications 2024, 15: 3527. PMID: 38664390, PMCID: PMC11045859, DOI: 10.1038/s41467-024-47704-8.Peer-Reviewed Original ResearchLarge Hadron ColliderAnomaly detectionExotic decaysExotic HiggsHiggs bosonPhysical processesHadron ColliderStandard modelHiggsTrigger systemDecision treeDeep decision treesReal-time applicationsLow latency valuesAnomaly detectorAutoencoder algorithmField Programmable Gate ArrayResource usageProgrammable gate arrayBosonsColliderCERNAutoencoderLargeResource constraintsSpeech motion anomaly detection via cross-modal translation of 4D motion fields from tagged MRI
Liu X, Xing F, Zhuo J, Stone M, Prince J, El Fakhri G, Woo J. Speech motion anomaly detection via cross-modal translation of 4D motion fields from tagged MRI. Proceedings Of SPIE--the International Society For Optical Engineering 2024, 12926: 129262w-129262w-5. PMID: 39238547, PMCID: PMC11377028, DOI: 10.1117/12.3006874.Peer-Reviewed Original ResearchCross-modal translationHealthy individualsTongue cancer patientsMotion fieldOut-of-distributionOne-class SVMPatient dataAnomaly detectionAnomaly detectorCancer patientsTagged MRISpeech-related disordersGeneralization capabilityReconstruction qualitySpeech qualityArticulatory-acoustic relationsPatientsSpeech waveformTraining setInnovative treatmentsMRITest setMotion patternsArticulatory featuresTraining translators
2021
Fixing Bias in Reconstruction-based Anomaly Detection with Lipschitz Discriminators
Tong A, Wolf G, Krishnaswamy S. Fixing Bias in Reconstruction-based Anomaly Detection with Lipschitz Discriminators. Journal Of Signal Processing Systems 2021, 94: 229-243. DOI: 10.1007/s11265-021-01715-6.Peer-Reviewed Original ResearchAnomaly detectionTraining dataReconstruction-based anomaly detectionAutoencoder reconstruction errorDeep learning methodsReconstruction-based methodsOriginal data spaceGraph dataLearning methodsData spaceUnseen anomaliesReconstruction errorImproved performanceIrregular graphsTraining setHealth recordsHealth record dataWasserstein distanceLow errorDiscriminatorImagesCIFAR10MNISTUndesirable resultsRecord data
2011
Anomaly and signature filtering improve classifier performance for detection of suspicious access to EHRs.
Kim J, Grillo J, Boxwala A, Jiang X, Mandelbaum R, Patel B, Mikels D, Vinterbo S, Ohno-Machado L. Anomaly and signature filtering improve classifier performance for detection of suspicious access to EHRs. AMIA Annual Symposium Proceedings 2011, 2011: 723-31. PMID: 22195129, PMCID: PMC3243249.Peer-Reviewed Original ResearchConceptsSuspicious accessAccess recordsRule-based techniquesMachine learning methodsConstruction of classifiersAnomaly detectionInformative instancesLearning methodsSymbolic clusteringClassifier performanceSignature detectionIndependent test setInappropriate accessTest setEHRFiltering methodIntegrated filtering strategyFiltering strategyClassifierFilteringNegative rateFalse negative rateAccessDetectionClustering
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply