Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200205921> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4200205921 abstract "Background . In critical care, intensivists are required to continuously monitor high-dimensional vital signs and lab measurements to detect and diagnose acute patient conditions, which has always been a challenging task. Recently, deep learning models such as recurrent neural networks (RNNs) have demonstrated their strong potential on predicting such events. However, in real deployment, the patient data are continuously coming and there is no effective adaptation mechanism for RNN to incorporate those new data and become more accurate. Methods . In this study, we propose a novel self-correcting mechanism for RNN to fill in this gap. Our mechanism feeds prediction errors from the predictions of previous timestamps into the prediction of the current timestamp, so that the model can “learn” from previous predictions. We also proposed a regularization method that takes into account not only the model’s prediction errors on the labels but also its estimation errors on the input data. Results . We compared the performance of our proposed method with the conventional deep learning models on two real-world clinical datasets for the task of acute kidney injury (AKI) prediction and demonstrated that the proposed model achieved an area under ROC curve at 0.893 on the MIMIC-III dataset and 0.871 on the Philips eICU dataset. Conclusions . The proposed self-correcting RNNs demonstrated effectiveness in AKI prediction and have the potential to be applied to clinical applications." @default.
- W4200205921 created "2021-12-31" @default.
- W4200205921 creator A5001852186 @default.
- W4200205921 creator A5022222926 @default.
- W4200205921 creator A5038294037 @default.
- W4200205921 creator A5054008198 @default.
- W4200205921 creator A5057558023 @default.
- W4200205921 creator A5075323750 @default.
- W4200205921 date "2021-01-01" @default.
- W4200205921 modified "2023-10-16" @default.
- W4200205921 title "Self-Correcting Recurrent Neural Network for Acute Kidney Injury Prediction in Critical Care" @default.
- W4200205921 cites W1971206893 @default.
- W4200205921 cites W2022511345 @default.
- W4200205921 cites W2064675550 @default.
- W4200205921 cites W2105119992 @default.
- W4200205921 cites W2131419242 @default.
- W4200205921 cites W2139937737 @default.
- W4200205921 cites W2141413316 @default.
- W4200205921 cites W2157331557 @default.
- W4200205921 cites W2255847468 @default.
- W4200205921 cites W2396881363 @default.
- W4200205921 cites W2594913668 @default.
- W4200205921 cites W2610332124 @default.
- W4200205921 cites W2781246281 @default.
- W4200205921 cites W2807771243 @default.
- W4200205921 cites W2889224519 @default.
- W4200205921 cites W2963020213 @default.
- W4200205921 doi "https://doi.org/10.34133/2021/9808426" @default.
- W4200205921 hasPublicationYear "2021" @default.
- W4200205921 type Work @default.
- W4200205921 citedByCount "2" @default.
- W4200205921 countsByYear W42002059212022 @default.
- W4200205921 crossrefType "journal-article" @default.
- W4200205921 hasAuthorship W4200205921A5001852186 @default.
- W4200205921 hasAuthorship W4200205921A5022222926 @default.
- W4200205921 hasAuthorship W4200205921A5038294037 @default.
- W4200205921 hasAuthorship W4200205921A5054008198 @default.
- W4200205921 hasAuthorship W4200205921A5057558023 @default.
- W4200205921 hasAuthorship W4200205921A5075323750 @default.
- W4200205921 hasBestOaLocation W42002059211 @default.
- W4200205921 hasConcept C105339364 @default.
- W4200205921 hasConcept C108583219 @default.
- W4200205921 hasConcept C111919701 @default.
- W4200205921 hasConcept C113954288 @default.
- W4200205921 hasConcept C119857082 @default.
- W4200205921 hasConcept C124101348 @default.
- W4200205921 hasConcept C126322002 @default.
- W4200205921 hasConcept C147168706 @default.
- W4200205921 hasConcept C154945302 @default.
- W4200205921 hasConcept C162324750 @default.
- W4200205921 hasConcept C187736073 @default.
- W4200205921 hasConcept C2776135515 @default.
- W4200205921 hasConcept C2780451532 @default.
- W4200205921 hasConcept C2780472472 @default.
- W4200205921 hasConcept C41008148 @default.
- W4200205921 hasConcept C50644808 @default.
- W4200205921 hasConcept C5465570 @default.
- W4200205921 hasConcept C71924100 @default.
- W4200205921 hasConcept C79403827 @default.
- W4200205921 hasConceptScore W4200205921C105339364 @default.
- W4200205921 hasConceptScore W4200205921C108583219 @default.
- W4200205921 hasConceptScore W4200205921C111919701 @default.
- W4200205921 hasConceptScore W4200205921C113954288 @default.
- W4200205921 hasConceptScore W4200205921C119857082 @default.
- W4200205921 hasConceptScore W4200205921C124101348 @default.
- W4200205921 hasConceptScore W4200205921C126322002 @default.
- W4200205921 hasConceptScore W4200205921C147168706 @default.
- W4200205921 hasConceptScore W4200205921C154945302 @default.
- W4200205921 hasConceptScore W4200205921C162324750 @default.
- W4200205921 hasConceptScore W4200205921C187736073 @default.
- W4200205921 hasConceptScore W4200205921C2776135515 @default.
- W4200205921 hasConceptScore W4200205921C2780451532 @default.
- W4200205921 hasConceptScore W4200205921C2780472472 @default.
- W4200205921 hasConceptScore W4200205921C41008148 @default.
- W4200205921 hasConceptScore W4200205921C50644808 @default.
- W4200205921 hasConceptScore W4200205921C5465570 @default.
- W4200205921 hasConceptScore W4200205921C71924100 @default.
- W4200205921 hasConceptScore W4200205921C79403827 @default.
- W4200205921 hasFunder F4320320698 @default.
- W4200205921 hasLocation W42002059211 @default.
- W4200205921 hasLocation W42002059212 @default.
- W4200205921 hasOpenAccess W4200205921 @default.
- W4200205921 hasPrimaryLocation W42002059211 @default.
- W4200205921 hasRelatedWork W2793022090 @default.
- W4200205921 hasRelatedWork W2919358988 @default.
- W4200205921 hasRelatedWork W3099765033 @default.
- W4200205921 hasRelatedWork W3184291683 @default.
- W4200205921 hasRelatedWork W3192794374 @default.
- W4200205921 hasRelatedWork W4200205921 @default.
- W4200205921 hasRelatedWork W4281386417 @default.
- W4200205921 hasRelatedWork W4298168912 @default.
- W4200205921 hasRelatedWork W4312200629 @default.
- W4200205921 hasRelatedWork W4317242789 @default.
- W4200205921 hasVolume "2021" @default.
- W4200205921 isParatext "false" @default.
- W4200205921 isRetracted "false" @default.
- W4200205921 workType "article" @default.