FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298087144> ?p ?o ?g. }

• W4298087144 endingPage "949" @default.
• W4298087144 startingPage "949" @default.
• W4298087144 abstract "To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA).Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions.Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of pre-PTA shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram.Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance." @default.
• W4298087144 created "2022-10-01" @default.
• W4298087144 creator A5000608206 @default.
• W4298087144 creator A5000628512 @default.
• W4298087144 creator A5007766813 @default.
• W4298087144 creator A5032354311 @default.
• W4298087144 creator A5039487186 @default.
• W4298087144 creator A5048298191 @default.
• W4298087144 creator A5056172990 @default.
• W4298087144 creator A5056229401 @default.
• W4298087144 creator A5061220504 @default.
• W4298087144 creator A5063572107 @default.
• W4298087144 creator A5073965191 @default.
• W4298087144 creator A5089175956 @default.
• W4298087144 date "2022-01-01" @default.
• W4298087144 modified "2023-10-18" @default.
• W4298087144 title "Feasibility of Deep Learning-Based Analysis of Auscultation for Screening Significant Stenosis of Native Arteriovenous Fistula for Hemodialysis Requiring Angioplasty" @default.
• W4298087144 cites W1983193952 @default.
• W4298087144 cites W1992935770 @default.
• W4298087144 cites W2007729853 @default.
• W4298087144 cites W2030714555 @default.
• W4298087144 cites W2038570295 @default.
• W4298087144 cites W2095899212 @default.
• W4298087144 cites W2109819743 @default.
• W4298087144 cites W2115389700 @default.
• W4298087144 cites W2123073293 @default.
• W4298087144 cites W2148143831 @default.
• W4298087144 cites W2233636230 @default.
• W4298087144 cites W2792351646 @default.
• W4298087144 cites W2795164129 @default.
• W4298087144 cites W2801920224 @default.
• W4298087144 cites W3012497879 @default.
• W4298087144 cites W3027928993 @default.
• W4298087144 cites W3032019894 @default.
• W4298087144 cites W3036482809 @default.
• W4298087144 cites W3136868560 @default.
• W4298087144 doi "https://doi.org/10.3348/kjr.2022.0364" @default.
• W4298087144 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36174999" @default.
• W4298087144 hasPublicationYear "2022" @default.
• W4298087144 type Work @default.
• W4298087144 citedByCount "1" @default.
• W4298087144 countsByYear W42980871442022 @default.
• W4298087144 crossrefType "journal-article" @default.
• W4298087144 hasAuthorship W4298087144A5000608206 @default.
• W4298087144 hasAuthorship W4298087144A5000628512 @default.
• W4298087144 hasAuthorship W4298087144A5007766813 @default.
• W4298087144 hasAuthorship W4298087144A5032354311 @default.
• W4298087144 hasAuthorship W4298087144A5039487186 @default.
• W4298087144 hasAuthorship W4298087144A5048298191 @default.
• W4298087144 hasAuthorship W4298087144A5056172990 @default.
• W4298087144 hasAuthorship W4298087144A5056229401 @default.
• W4298087144 hasAuthorship W4298087144A5061220504 @default.
• W4298087144 hasAuthorship W4298087144A5063572107 @default.
• W4298087144 hasAuthorship W4298087144A5073965191 @default.
• W4298087144 hasAuthorship W4298087144A5089175956 @default.
• W4298087144 hasBestOaLocation W42980871442 @default.
• W4298087144 hasConcept C126322002 @default.
• W4298087144 hasConcept C126838900 @default.
• W4298087144 hasConcept C164705383 @default.
• W4298087144 hasConcept C2777706214 @default.
• W4298087144 hasConcept C2778063415 @default.
• W4298087144 hasConcept C2778286760 @default.
• W4298087144 hasConcept C2779055095 @default.
• W4298087144 hasConcept C2779063477 @default.
• W4298087144 hasConcept C2780007028 @default.
• W4298087144 hasConcept C2780643987 @default.
• W4298087144 hasConcept C28490314 @default.
• W4298087144 hasConcept C41008148 @default.
• W4298087144 hasConcept C45273575 @default.
• W4298087144 hasConcept C58471807 @default.
• W4298087144 hasConcept C71924100 @default.
• W4298087144 hasConceptScore W4298087144C126322002 @default.
• W4298087144 hasConceptScore W4298087144C126838900 @default.
• W4298087144 hasConceptScore W4298087144C164705383 @default.
• W4298087144 hasConceptScore W4298087144C2777706214 @default.
• W4298087144 hasConceptScore W4298087144C2778063415 @default.
• W4298087144 hasConceptScore W4298087144C2778286760 @default.
• W4298087144 hasConceptScore W4298087144C2779055095 @default.
• W4298087144 hasConceptScore W4298087144C2779063477 @default.
• W4298087144 hasConceptScore W4298087144C2780007028 @default.
• W4298087144 hasConceptScore W4298087144C2780643987 @default.
• W4298087144 hasConceptScore W4298087144C28490314 @default.
• W4298087144 hasConceptScore W4298087144C41008148 @default.
• W4298087144 hasConceptScore W4298087144C45273575 @default.
• W4298087144 hasConceptScore W4298087144C58471807 @default.
• W4298087144 hasConceptScore W4298087144C71924100 @default.
• W4298087144 hasIssue "10" @default.
• W4298087144 hasLocation W42980871441 @default.
• W4298087144 hasLocation W42980871442 @default.
• W4298087144 hasLocation W42980871443 @default.
• W4298087144 hasLocation W42980871444 @default.
• W4298087144 hasOpenAccess W4298087144 @default.
• W4298087144 hasPrimaryLocation W42980871441 @default.
• W4298087144 hasRelatedWork W144939884 @default.
• W4298087144 hasRelatedWork W1972438460 @default.
• W4298087144 hasRelatedWork W2002288156 @default.
• W4298087144 hasRelatedWork W2010652546 @default.
• W4298087144 hasRelatedWork W2024262772 @default.

• next