FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293565741> ?p ?o ?g. }

• W4293565741 endingPage "103167" @default.
• W4293565741 startingPage "103167" @default.
• W4293565741 abstract "Visual interpretation of electroencephalography (EEG) is time consuming, may lack objectivity, and is restricted to features detectable by a human. Computer-based approaches, especially deep learning, could potentially overcome these limitations. However, most deep learning studies focus on a specific question or a single pathology. Here we explore the potential of deep learning for EEG-based diagnostic and prognostic assessment of patients with acute consciousness impairment (ACI) of various etiologies. EEGs from 358 adults from a randomized controlled trial (CERTA, NCT03129438) were retrospectively analyzed. A convolutional neural network was used to predict the clinical outcome (based either on survival or on best cerebral performance category) and to determine the etiology (four diagnostic categories). The largest probability output served as marker for the confidence of the network in its prediction (certainty factor); we also systematically compared the predictions with raw EEG data, and used a visualization algorithm (Grad-CAM) to highlight discriminative patterns. When all patients were considered, the area under the receiver operating characteristic curve (AUC) was 0.721 for predicting survival and 0.703 for predicting the outcome based on best CPC; for patients with certainty factor ≥ 60 % the AUCs increased to 0.776 and 0.755 respectively; and for certainty factor ≥ 75 % to 0.852 and 0.879. The accuracy for predicting the etiology was 54.5 %; the accuracy increased to 67.7 %, 70.3 % and 84.1 % for patients with certainty factor of 50 %, 60 % and 75 % respectively. Visual analysis showed that the network learnt EEG patterns typically recognized by human experts, and suggested new criteria. This work demonstrates for the first time the potential of deep learning-based EEG analysis in critically ill patients with various etiologies of ACI. Certainty factor and post-hoc correlation of input data with prediction help to better characterize the method and pave the route for future implementations in clinical routine." @default.
• W4293565741 created "2022-08-30" @default.
• W4293565741 creator A5005212356 @default.
• W4293565741 creator A5034976793 @default.
• W4293565741 creator A5039476994 @default.
• W4293565741 creator A5040998367 @default.
• W4293565741 creator A5042974849 @default.
• W4293565741 creator A5045497387 @default.
• W4293565741 creator A5059323085 @default.
• W4293565741 date "2022-01-01" @default.
• W4293565741 modified "2023-10-14" @default.
• W4293565741 title "Diagnostic and prognostic EEG analysis of critically ill patients: A deep learning study" @default.
• W4293565741 cites W1845128836 @default.
• W4293565741 cites W1981592305 @default.
• W4293565741 cites W1982000043 @default.
• W4293565741 cites W1984207165 @default.
• W4293565741 cites W2027021543 @default.
• W4293565741 cites W2040316860 @default.
• W4293565741 cites W2150672723 @default.
• W4293565741 cites W2170276497 @default.
• W4293565741 cites W2278254262 @default.
• W4293565741 cites W2283300528 @default.
• W4293565741 cites W2308800763 @default.
• W4293565741 cites W2315878770 @default.
• W4293565741 cites W2337722030 @default.
• W4293565741 cites W2515884208 @default.
• W4293565741 cites W2561265802 @default.
• W4293565741 cites W2584232009 @default.
• W4293565741 cites W2607039194 @default.
• W4293565741 cites W2806537442 @default.
• W4293565741 cites W2806703420 @default.
• W4293565741 cites W2889402927 @default.
• W4293565741 cites W2900936992 @default.
• W4293565741 cites W2902907967 @default.
• W4293565741 cites W2915893085 @default.
• W4293565741 cites W2922066841 @default.
• W4293565741 cites W2948398841 @default.
• W4293565741 cites W2948560436 @default.
• W4293565741 cites W2963355311 @default.
• W4293565741 cites W2963915399 @default.
• W4293565741 cites W3006385477 @default.
• W4293565741 cites W3029979534 @default.
• W4293565741 cites W3045095715 @default.
• W4293565741 cites W3045676091 @default.
• W4293565741 cites W3046238651 @default.
• W4293565741 cites W3112089594 @default.
• W4293565741 cites W3124737603 @default.
• W4293565741 cites W3180136752 @default.
• W4293565741 cites W3183639040 @default.
• W4293565741 cites W3185122822 @default.
• W4293565741 cites W3195128660 @default.
• W4293565741 cites W3202099927 @default.
• W4293565741 cites W3203368638 @default.
• W4293565741 cites W3209901185 @default.
• W4293565741 cites W4254299754 @default.
• W4293565741 doi "https://doi.org/10.1016/j.nicl.2022.103167" @default.
• W4293565741 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36049354" @default.
• W4293565741 hasPublicationYear "2022" @default.
• W4293565741 type Work @default.
• W4293565741 citedByCount "1" @default.
• W4293565741 countsByYear W42935657412023 @default.
• W4293565741 crossrefType "journal-article" @default.
• W4293565741 hasAuthorship W4293565741A5005212356 @default.
• W4293565741 hasAuthorship W4293565741A5034976793 @default.
• W4293565741 hasAuthorship W4293565741A5039476994 @default.
• W4293565741 hasAuthorship W4293565741A5040998367 @default.
• W4293565741 hasAuthorship W4293565741A5042974849 @default.
• W4293565741 hasAuthorship W4293565741A5045497387 @default.
• W4293565741 hasAuthorship W4293565741A5059323085 @default.
• W4293565741 hasBestOaLocation W42935657411 @default.
• W4293565741 hasConcept C108583219 @default.
• W4293565741 hasConcept C118552586 @default.
• W4293565741 hasConcept C119857082 @default.
• W4293565741 hasConcept C137627325 @default.
• W4293565741 hasConcept C142724271 @default.
• W4293565741 hasConcept C154945302 @default.
• W4293565741 hasConcept C41008148 @default.
• W4293565741 hasConcept C522805319 @default.
• W4293565741 hasConcept C58471807 @default.
• W4293565741 hasConcept C71924100 @default.
• W4293565741 hasConcept C81363708 @default.
• W4293565741 hasConcept C97931131 @default.
• W4293565741 hasConceptScore W4293565741C108583219 @default.
• W4293565741 hasConceptScore W4293565741C118552586 @default.
• W4293565741 hasConceptScore W4293565741C119857082 @default.
• W4293565741 hasConceptScore W4293565741C137627325 @default.
• W4293565741 hasConceptScore W4293565741C142724271 @default.
• W4293565741 hasConceptScore W4293565741C154945302 @default.
• W4293565741 hasConceptScore W4293565741C41008148 @default.
• W4293565741 hasConceptScore W4293565741C522805319 @default.
• W4293565741 hasConceptScore W4293565741C58471807 @default.
• W4293565741 hasConceptScore W4293565741C71924100 @default.
• W4293565741 hasConceptScore W4293565741C81363708 @default.
• W4293565741 hasConceptScore W4293565741C97931131 @default.
• W4293565741 hasFunder F4320320924 @default.
• W4293565741 hasLocation W42935657411 @default.
• W4293565741 hasLocation W42935657412 @default.
• W4293565741 hasLocation W42935657413 @default.

• next