Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386783764> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4386783764 endingPage "102659" @default.
- W4386783764 startingPage "102659" @default.
- W4386783764 abstract "Deep Learning (DL) models have received increasing attention in the clinical setting, particularly in intensive care units (ICU). In this context, the interpretability of the outcomes estimated by the DL models is an essential step towards increasing adoption of DL models in clinical practice. To address this challenge, we propose an ante-hoc, interpretable neural network model. Our proposed model, named double self-attention architecture (DSA), uses two attention-based mechanisms, including self-attention and effective attention. It can capture the importance of input variables in general, as well as changes in importance along the time dimension for the outcome of interest. We evaluated our model using two real-world clinical datasets covering 22840 patients in predicting onset of delirium 12 h and 48 h in advance. Additionally, we compare the descriptive performance of our model with three post-hoc interpretable algorithms as well as with the opinion of clinicians based on the published literature and clinical experience. We find that our model covers the majority of the top-10 variables ranked by the other three post-hoc interpretable algorithms as well as the clinical opinion, with the advantage of taking into account both, the dependencies among variables as well as dependencies between varying time-steps. Finally, our results show that our model can improve descriptive performance without sacrificing predictive performance." @default.
- W4386783764 created "2023-09-16" @default.
- W4386783764 creator A5001834655 @default.
- W4386783764 creator A5031401755 @default.
- W4386783764 creator A5059313480 @default.
- W4386783764 creator A5084559937 @default.
- W4386783764 date "2023-10-01" @default.
- W4386783764 modified "2023-10-07" @default.
- W4386783764 title "An interpretable deep learning model for time-series electronic health records: Case study of delirium prediction in critical care" @default.
- W4386783764 cites W2073231946 @default.
- W4386783764 cites W2079735306 @default.
- W4386783764 cites W2124135067 @default.
- W4386783764 cites W2143617649 @default.
- W4386783764 cites W2165155752 @default.
- W4386783764 cites W2396881363 @default.
- W4386783764 cites W2625625371 @default.
- W4386783764 cites W2884365846 @default.
- W4386783764 cites W2888487581 @default.
- W4386783764 cites W2891400669 @default.
- W4386783764 cites W2913977338 @default.
- W4386783764 cites W2966351171 @default.
- W4386783764 cites W2994898777 @default.
- W4386783764 cites W2996603502 @default.
- W4386783764 cites W3123085258 @default.
- W4386783764 cites W4281749155 @default.
- W4386783764 doi "https://doi.org/10.1016/j.artmed.2023.102659" @default.
- W4386783764 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37783541" @default.
- W4386783764 hasPublicationYear "2023" @default.
- W4386783764 type Work @default.
- W4386783764 citedByCount "0" @default.
- W4386783764 crossrefType "journal-article" @default.
- W4386783764 hasAuthorship W4386783764A5001834655 @default.
- W4386783764 hasAuthorship W4386783764A5031401755 @default.
- W4386783764 hasAuthorship W4386783764A5059313480 @default.
- W4386783764 hasAuthorship W4386783764A5084559937 @default.
- W4386783764 hasBestOaLocation W43867837641 @default.
- W4386783764 hasConcept C108583219 @default.
- W4386783764 hasConcept C119857082 @default.
- W4386783764 hasConcept C124101348 @default.
- W4386783764 hasConcept C151730666 @default.
- W4386783764 hasConcept C154945302 @default.
- W4386783764 hasConcept C177713679 @default.
- W4386783764 hasConcept C2779343474 @default.
- W4386783764 hasConcept C2779753318 @default.
- W4386783764 hasConcept C2781067378 @default.
- W4386783764 hasConcept C41008148 @default.
- W4386783764 hasConcept C71924100 @default.
- W4386783764 hasConcept C86803240 @default.
- W4386783764 hasConceptScore W4386783764C108583219 @default.
- W4386783764 hasConceptScore W4386783764C119857082 @default.
- W4386783764 hasConceptScore W4386783764C124101348 @default.
- W4386783764 hasConceptScore W4386783764C151730666 @default.
- W4386783764 hasConceptScore W4386783764C154945302 @default.
- W4386783764 hasConceptScore W4386783764C177713679 @default.
- W4386783764 hasConceptScore W4386783764C2779343474 @default.
- W4386783764 hasConceptScore W4386783764C2779753318 @default.
- W4386783764 hasConceptScore W4386783764C2781067378 @default.
- W4386783764 hasConceptScore W4386783764C41008148 @default.
- W4386783764 hasConceptScore W4386783764C71924100 @default.
- W4386783764 hasConceptScore W4386783764C86803240 @default.
- W4386783764 hasLocation W43867837641 @default.
- W4386783764 hasLocation W43867837642 @default.
- W4386783764 hasOpenAccess W4386783764 @default.
- W4386783764 hasPrimaryLocation W43867837641 @default.
- W4386783764 hasRelatedWork W1986582023 @default.
- W4386783764 hasRelatedWork W2806259446 @default.
- W4386783764 hasRelatedWork W2883749686 @default.
- W4386783764 hasRelatedWork W2905433371 @default.
- W4386783764 hasRelatedWork W4310278675 @default.
- W4386783764 hasRelatedWork W4311431240 @default.
- W4386783764 hasRelatedWork W4315864862 @default.
- W4386783764 hasRelatedWork W4361193272 @default.
- W4386783764 hasRelatedWork W4380075502 @default.
- W4386783764 hasRelatedWork W2963326959 @default.
- W4386783764 hasVolume "144" @default.
- W4386783764 isParatext "false" @default.
- W4386783764 isRetracted "false" @default.
- W4386783764 workType "article" @default.