Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119348539> ?p ?o ?g. }
- W3119348539 endingPage "44" @default.
- W3119348539 startingPage "38" @default.
- W3119348539 abstract "Traditional Machine Learning (ML) models have had limited success in predicting Coronoavirus-19 (COVID-19) outcomes using Electronic Health Record (EHR) data partially due to not effectively capturing the inter-connectivity patterns between various data modalities. In this work, we propose a novel framework that utilizes relational learning based on a heterogeneous graph model (HGM) for predicting mortality at different time windows in COVID-19 patients within the intensive care unit (ICU). We utilize the EHRs of one of the largest and most diverse patient populations across five hospitals in major health system in New York City. In our model, we use an LSTM for processing time varying patient data and apply our proposed relational learning strategy in the final output layer along with other static features. Here, we replace the traditional softmax layer with a Skip-Gram relational learning strategy to compare the similarity between a patient and outcome embedding representation. We demonstrate that the construction of a HGM can robustly learn the patterns classifying patient representations of outcomes through leveraging patterns within the embeddings of similar patients. Our experimental results show that our relational learning-based HGM model achieves higher area under the receiver operating characteristic curve (auROC) than both comparator models in all prediction time windows, with dramatic improvements to recall." @default.
- W3119348539 created "2021-01-18" @default.
- W3119348539 creator A5001694059 @default.
- W3119348539 creator A5013984574 @default.
- W3119348539 creator A5030539003 @default.
- W3119348539 creator A5032914921 @default.
- W3119348539 creator A5042331995 @default.
- W3119348539 creator A5047170063 @default.
- W3119348539 creator A5047405500 @default.
- W3119348539 creator A5076569669 @default.
- W3119348539 creator A5084566613 @default.
- W3119348539 date "2021-03-01" @default.
- W3119348539 modified "2023-10-14" @default.
- W3119348539 title "Relational Learning Improves Prediction of Mortality in COVID-19 in the Intensive Care Unit" @default.
- W3119348539 cites W2743104969 @default.
- W3119348539 cites W3008028633 @default.
- W3119348539 cites W3012813927 @default.
- W3119348539 cites W3025394897 @default.
- W3119348539 cites W3025948831 @default.
- W3119348539 cites W3037624367 @default.
- W3119348539 cites W3038003025 @default.
- W3119348539 cites W3075432525 @default.
- W3119348539 cites W3092436046 @default.
- W3119348539 cites W3095032158 @default.
- W3119348539 cites W3097187884 @default.
- W3119348539 cites W3108458441 @default.
- W3119348539 cites W3109916301 @default.
- W3119348539 doi "https://doi.org/10.1109/tbdata.2020.3048644" @default.
- W3119348539 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7990133" @default.
- W3119348539 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33768136" @default.
- W3119348539 hasPublicationYear "2021" @default.
- W3119348539 type Work @default.
- W3119348539 sameAs 3119348539 @default.
- W3119348539 citedByCount "10" @default.
- W3119348539 countsByYear W31193485392021 @default.
- W3119348539 countsByYear W31193485392022 @default.
- W3119348539 countsByYear W31193485392023 @default.
- W3119348539 crossrefType "journal-article" @default.
- W3119348539 hasAuthorship W3119348539A5001694059 @default.
- W3119348539 hasAuthorship W3119348539A5013984574 @default.
- W3119348539 hasAuthorship W3119348539A5030539003 @default.
- W3119348539 hasAuthorship W3119348539A5032914921 @default.
- W3119348539 hasAuthorship W3119348539A5042331995 @default.
- W3119348539 hasAuthorship W3119348539A5047170063 @default.
- W3119348539 hasAuthorship W3119348539A5047405500 @default.
- W3119348539 hasAuthorship W3119348539A5076569669 @default.
- W3119348539 hasAuthorship W3119348539A5084566613 @default.
- W3119348539 hasBestOaLocation W31193485391 @default.
- W3119348539 hasConcept C108583219 @default.
- W3119348539 hasConcept C119857082 @default.
- W3119348539 hasConcept C124101348 @default.
- W3119348539 hasConcept C126322002 @default.
- W3119348539 hasConcept C144024400 @default.
- W3119348539 hasConcept C148524875 @default.
- W3119348539 hasConcept C154945302 @default.
- W3119348539 hasConcept C188441871 @default.
- W3119348539 hasConcept C2776376669 @default.
- W3119348539 hasConcept C2779903281 @default.
- W3119348539 hasConcept C36289849 @default.
- W3119348539 hasConcept C41008148 @default.
- W3119348539 hasConcept C41608201 @default.
- W3119348539 hasConcept C5655090 @default.
- W3119348539 hasConcept C71924100 @default.
- W3119348539 hasConceptScore W3119348539C108583219 @default.
- W3119348539 hasConceptScore W3119348539C119857082 @default.
- W3119348539 hasConceptScore W3119348539C124101348 @default.
- W3119348539 hasConceptScore W3119348539C126322002 @default.
- W3119348539 hasConceptScore W3119348539C144024400 @default.
- W3119348539 hasConceptScore W3119348539C148524875 @default.
- W3119348539 hasConceptScore W3119348539C154945302 @default.
- W3119348539 hasConceptScore W3119348539C188441871 @default.
- W3119348539 hasConceptScore W3119348539C2776376669 @default.
- W3119348539 hasConceptScore W3119348539C2779903281 @default.
- W3119348539 hasConceptScore W3119348539C36289849 @default.
- W3119348539 hasConceptScore W3119348539C41008148 @default.
- W3119348539 hasConceptScore W3119348539C41608201 @default.
- W3119348539 hasConceptScore W3119348539C5655090 @default.
- W3119348539 hasConceptScore W3119348539C71924100 @default.
- W3119348539 hasFunder F4320332161 @default.
- W3119348539 hasFunder F4320337472 @default.
- W3119348539 hasIssue "1" @default.
- W3119348539 hasLocation W31193485391 @default.
- W3119348539 hasLocation W31193485392 @default.
- W3119348539 hasLocation W31193485393 @default.
- W3119348539 hasOpenAccess W3119348539 @default.
- W3119348539 hasPrimaryLocation W31193485391 @default.
- W3119348539 hasRelatedWork W3014300295 @default.
- W3119348539 hasRelatedWork W3164822677 @default.
- W3119348539 hasRelatedWork W4223943233 @default.
- W3119348539 hasRelatedWork W4225161397 @default.
- W3119348539 hasRelatedWork W4300427424 @default.
- W3119348539 hasRelatedWork W4312200629 @default.
- W3119348539 hasRelatedWork W4360585206 @default.
- W3119348539 hasRelatedWork W4364306694 @default.
- W3119348539 hasRelatedWork W4380075502 @default.
- W3119348539 hasRelatedWork W4380086463 @default.
- W3119348539 hasVolume "7" @default.
- W3119348539 isParatext "false" @default.