FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3105485205> ?p ?o ?g. }

• W3105485205 abstract "Abstract REM Behavior Disorder (RBD) is now recognized as the prodromal stage of α -synucleinopathies such as Parkinson’s disease (PD). In this paper, we describe deep learning models for diagnosis/prognosis derived from a few minutes of eyes-closed resting electroencephalography data (EEG) collected from idiopathic RBD patients (n=121) and healthy controls (HC, n=91). A few years after the EEG acquisition (4 ± 2 years), a subset of the RBD patients eventually developed either PD (n=14) or Dementia with Lewy bodies (DLB, n=13), while the rest remained idiopathic. We describe first a simple convolutional neural network (DCNN) with a five-layer architecture combining filtering and pooling, which we train using stacked multi-channel EEG spectrograms. We treat the data as in audio or image classification problems where deep networks have proven highly successful by exploiting compositional and translationally invariant features in the data. For comparison, we study an even simpler deep recurrent neural network using three stacked Long Short Term Memory network (LSTM) cells or gated-recurrent unit (GRU) cells—with very similar results. The performance of these networks typically reaches 80% (±1%) classification accuracy in the balanced HC vs. PD-outcome classification problem. In particular, using data from a single EEG channel we obtain an area under the curve (AUC) of 87% (±1%) while avoiding spectral feature selection. The trained classifier can also be used to generate synthetic spectrograms to study what spectrogram features are relevant for classification, pointing to the presence of theta band bursts and a decrease of power in the alpha band in future PD or DLB patients compared to HCs. We conclude that deep networks may provide a key tool for the analysis of EEG dynamics even from relatively small datasets and enable the delivery of new biomarkers." @default.
• W3105485205 created "2020-11-23" @default.
• W3105485205 creator A5008418589 @default.
• W3105485205 creator A5024802542 @default.
• W3105485205 creator A5044283961 @default.
• W3105485205 creator A5048003361 @default.
• W3105485205 creator A5063275477 @default.
• W3105485205 creator A5066414888 @default.
• W3105485205 creator A5081897983 @default.
• W3105485205 date "2018-01-17" @default.
• W3105485205 modified "2023-09-26" @default.
• W3105485205 title "Deep learning with EEG spectrograms in rapid eye movement behavior disorder" @default.
• W3105485205 cites W1661597557 @default.
• W3105485205 cites W1988949556 @default.
• W3105485205 cites W2023130608 @default.
• W3105485205 cites W2064432685 @default.
• W3105485205 cites W2064675550 @default.
• W3105485205 cites W2088633905 @default.
• W3105485205 cites W2119576606 @default.
• W3105485205 cites W2146288660 @default.
• W3105485205 cites W2157586156 @default.
• W3105485205 cites W2509382533 @default.
• W3105485205 cites W2741907166 @default.
• W3105485205 cites W2767433279 @default.
• W3105485205 cites W2768364432 @default.
• W3105485205 cites W2964065019 @default.
• W3105485205 cites W3102555501 @default.
• W3105485205 doi "https://doi.org/10.1101/240267" @default.
• W3105485205 hasPublicationYear "2018" @default.
• W3105485205 type Work @default.
• W3105485205 sameAs 3105485205 @default.
• W3105485205 citedByCount "9" @default.
• W3105485205 countsByYear W31054852052018 @default.
• W3105485205 countsByYear W31054852052019 @default.
• W3105485205 countsByYear W31054852052020 @default.
• W3105485205 countsByYear W31054852052021 @default.
• W3105485205 crossrefType "posted-content" @default.
• W3105485205 hasAuthorship W3105485205A5008418589 @default.
• W3105485205 hasAuthorship W3105485205A5024802542 @default.
• W3105485205 hasAuthorship W3105485205A5044283961 @default.
• W3105485205 hasAuthorship W3105485205A5048003361 @default.
• W3105485205 hasAuthorship W3105485205A5063275477 @default.
• W3105485205 hasAuthorship W3105485205A5066414888 @default.
• W3105485205 hasAuthorship W3105485205A5081897983 @default.
• W3105485205 hasBestOaLocation W31054852051 @default.
• W3105485205 hasConcept C108583219 @default.
• W3105485205 hasConcept C148483581 @default.
• W3105485205 hasConcept C153180895 @default.
• W3105485205 hasConcept C154945302 @default.
• W3105485205 hasConcept C15744967 @default.
• W3105485205 hasConcept C169760540 @default.
• W3105485205 hasConcept C28490314 @default.
• W3105485205 hasConcept C41008148 @default.
• W3105485205 hasConcept C45273575 @default.
• W3105485205 hasConcept C522805319 @default.
• W3105485205 hasConcept C81363708 @default.
• W3105485205 hasConcept C95623464 @default.
• W3105485205 hasConceptScore W3105485205C108583219 @default.
• W3105485205 hasConceptScore W3105485205C148483581 @default.
• W3105485205 hasConceptScore W3105485205C153180895 @default.
• W3105485205 hasConceptScore W3105485205C154945302 @default.
• W3105485205 hasConceptScore W3105485205C15744967 @default.
• W3105485205 hasConceptScore W3105485205C169760540 @default.
• W3105485205 hasConceptScore W3105485205C28490314 @default.
• W3105485205 hasConceptScore W3105485205C41008148 @default.
• W3105485205 hasConceptScore W3105485205C45273575 @default.
• W3105485205 hasConceptScore W3105485205C522805319 @default.
• W3105485205 hasConceptScore W3105485205C81363708 @default.
• W3105485205 hasConceptScore W3105485205C95623464 @default.
• W3105485205 hasLocation W31054852051 @default.
• W3105485205 hasLocation W31054852052 @default.
• W3105485205 hasOpenAccess W3105485205 @default.
• W3105485205 hasPrimaryLocation W31054852051 @default.
• W3105485205 hasRelatedWork W2731899572 @default.
• W3105485205 hasRelatedWork W2936488316 @default.
• W3105485205 hasRelatedWork W2999805992 @default.
• W3105485205 hasRelatedWork W3011074480 @default.
• W3105485205 hasRelatedWork W3116150086 @default.
• W3105485205 hasRelatedWork W3133861977 @default.
• W3105485205 hasRelatedWork W4200173597 @default.
• W3105485205 hasRelatedWork W4291897433 @default.
• W3105485205 hasRelatedWork W4312417841 @default.
• W3105485205 hasRelatedWork W4321369474 @default.
• W3105485205 isParatext "false" @default.
• W3105485205 isRetracted "false" @default.
• W3105485205 magId "3105485205" @default.
• W3105485205 workType "article" @default.