Matches in SemOpenAlex for { <https://semopenalex.org/work/W3118545158> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3118545158 endingPage "102006" @default.
- W3118545158 startingPage "102006" @default.
- W3118545158 abstract "High-resolution manometry (HRM) is the primary method for diagnosing esophageal motility disorders and its interpretation and classification are based on variables (features) from data of each swallow. Modeling and learning the semantics directly from raw swallow data could not only help automate the feature extraction, but also alleviate the bias from pre-defined features. With more than 32-thousand raw swallow data, a generative model using the approach of variational auto-encoder (VAE) was developed, which, to our knowledge, is the first deep-learning-based unsupervised model on raw esophageal manometry data. The VAE model was reformulated to include different types of loss motivated by domain knowledge and tuned with different hyper-parameters. Training of the VAE model was found sensitive on the learning rate and hence the evidence lower bound objective (ELBO) was further scaled by the data dimension. Case studies showed that the dimensionality of latent space have a big impact on the learned semantics. In particular, cases with 4-dimensional latent variables were found to encode various physiologically meaningful contraction patterns, including strength, propagation pattern as well as sphincter relaxation. Cases with so-called hybrid L2 loss seemed to better capture the coherence of contraction/relaxation transition. Discriminating capability was further evaluated using simple linear discriminative analysis (LDA) on predicting swallow type and swallow pressurization, which yields clustering patterns consistent with clinical impression. The current work on modeling and understanding swallow-level data will guide the development of study-level models for automatic diagnosis as the next stage." @default.
- W3118545158 created "2021-01-18" @default.
- W3118545158 creator A5014075719 @default.
- W3118545158 creator A5032081824 @default.
- W3118545158 creator A5066504153 @default.
- W3118545158 creator A5073783476 @default.
- W3118545158 creator A5077603745 @default.
- W3118545158 creator A5084810789 @default.
- W3118545158 creator A5085920650 @default.
- W3118545158 date "2021-02-01" @default.
- W3118545158 modified "2023-10-01" @default.
- W3118545158 title "A deep-learning-based unsupervised model on esophageal manometry using variational autoencoder" @default.
- W3118545158 cites W1579736884 @default.
- W3118545158 cites W2023804350 @default.
- W3118545158 cites W2030733796 @default.
- W3118545158 cites W2150516656 @default.
- W3118545158 cites W2255060555 @default.
- W3118545158 cites W2343858548 @default.
- W3118545158 cites W2465102378 @default.
- W3118545158 cites W2530734946 @default.
- W3118545158 cites W2610332124 @default.
- W3118545158 cites W2761173650 @default.
- W3118545158 cites W2783554090 @default.
- W3118545158 cites W2797155551 @default.
- W3118545158 cites W2800764028 @default.
- W3118545158 cites W2803760365 @default.
- W3118545158 cites W2807593075 @default.
- W3118545158 cites W2895890926 @default.
- W3118545158 cites W2905189062 @default.
- W3118545158 cites W2964032056 @default.
- W3118545158 cites W2978294504 @default.
- W3118545158 doi "https://doi.org/10.1016/j.artmed.2020.102006" @default.
- W3118545158 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7901248" @default.
- W3118545158 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33581826" @default.
- W3118545158 hasPublicationYear "2021" @default.
- W3118545158 type Work @default.
- W3118545158 sameAs 3118545158 @default.
- W3118545158 citedByCount "17" @default.
- W3118545158 countsByYear W31185451582021 @default.
- W3118545158 countsByYear W31185451582022 @default.
- W3118545158 countsByYear W31185451582023 @default.
- W3118545158 crossrefType "journal-article" @default.
- W3118545158 hasAuthorship W3118545158A5014075719 @default.
- W3118545158 hasAuthorship W3118545158A5032081824 @default.
- W3118545158 hasAuthorship W3118545158A5066504153 @default.
- W3118545158 hasAuthorship W3118545158A5073783476 @default.
- W3118545158 hasAuthorship W3118545158A5077603745 @default.
- W3118545158 hasAuthorship W3118545158A5084810789 @default.
- W3118545158 hasAuthorship W3118545158A5085920650 @default.
- W3118545158 hasBestOaLocation W31185451582 @default.
- W3118545158 hasConcept C101738243 @default.
- W3118545158 hasConcept C108583219 @default.
- W3118545158 hasConcept C119857082 @default.
- W3118545158 hasConcept C153180895 @default.
- W3118545158 hasConcept C154945302 @default.
- W3118545158 hasConcept C41008148 @default.
- W3118545158 hasConcept C52622490 @default.
- W3118545158 hasConcept C59404180 @default.
- W3118545158 hasConcept C70518039 @default.
- W3118545158 hasConcept C8038995 @default.
- W3118545158 hasConcept C97931131 @default.
- W3118545158 hasConceptScore W3118545158C101738243 @default.
- W3118545158 hasConceptScore W3118545158C108583219 @default.
- W3118545158 hasConceptScore W3118545158C119857082 @default.
- W3118545158 hasConceptScore W3118545158C153180895 @default.
- W3118545158 hasConceptScore W3118545158C154945302 @default.
- W3118545158 hasConceptScore W3118545158C41008148 @default.
- W3118545158 hasConceptScore W3118545158C52622490 @default.
- W3118545158 hasConceptScore W3118545158C59404180 @default.
- W3118545158 hasConceptScore W3118545158C70518039 @default.
- W3118545158 hasConceptScore W3118545158C8038995 @default.
- W3118545158 hasConceptScore W3118545158C97931131 @default.
- W3118545158 hasFunder F4320332161 @default.
- W3118545158 hasLocation W31185451581 @default.
- W3118545158 hasLocation W31185451582 @default.
- W3118545158 hasLocation W31185451583 @default.
- W3118545158 hasOpenAccess W3118545158 @default.
- W3118545158 hasPrimaryLocation W31185451581 @default.
- W3118545158 hasRelatedWork W2285052147 @default.
- W3118545158 hasRelatedWork W2292254049 @default.
- W3118545158 hasRelatedWork W2592385986 @default.
- W3118545158 hasRelatedWork W2772780115 @default.
- W3118545158 hasRelatedWork W2998168123 @default.
- W3118545158 hasRelatedWork W3200601913 @default.
- W3118545158 hasRelatedWork W4287995534 @default.
- W3118545158 hasRelatedWork W4301878994 @default.
- W3118545158 hasRelatedWork W4307326401 @default.
- W3118545158 hasRelatedWork W4313145684 @default.
- W3118545158 hasVolume "112" @default.
- W3118545158 isParatext "false" @default.
- W3118545158 isRetracted "false" @default.
- W3118545158 magId "3118545158" @default.
- W3118545158 workType "article" @default.