FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385478066> ?p ?o ?g. }

• W4385478066 abstract "Electronic health records (EHRs) have an inherently high degree of irregularity, including many missing values and varying time intervals, due to variations in patient conditions and treatment needs. This makes successful health risk prediction challenging. EHRs contain longitudinal patient data that records meaningful information associated with a chronological set of clinical observations for each patient. Existing methods focus on modeling variable correlations in patient data with deep neural networks to impute missing values and feed complete data matrices into machine learning models to perform downstream healthcare prediction tasks. However, not enough attention was given to the reliability of the imputed values by these methods. Further, it is likely that the pattern of missing data in EHR contains important information affecting relationships among variables, including time intervals. We propose a novel deep imputation-prediction network to simultaneously perform imputation and prediction tasks with EHR. Our method has the advantages of being able to: 1) learn from the longitudinal patient data in both forward and backward directions, 2) generate both the predicted and imputed values and enhance the reliability of imputed values, and 3) incorporate three common decay functions to capture the variation pattern of input variables in time and adaptively enhances the temporal representation of each pattern with adjustable weights. As well, our method is able to examine the association between input variables to identify critical indicative variables regardless of how long ago the associated event happened. Experimental results on MIMIC-III and eICU datasets demonstrate the effectiveness and superiority of our method for both imputation and prediction, as well as transparency and interpretability, compared to existing state-of-the-art methods." @default.
• W4385478066 created "2023-08-03" @default.
• W4385478066 creator A5000633755 @default.
• W4385478066 creator A5001608625 @default.
• W4385478066 creator A5067376850 @default.
• W4385478066 date "2023-06-18" @default.
• W4385478066 modified "2023-09-27" @default.
• W4385478066 title "Deep Imputation-Prediction Networks for Health Risk Prediction using Electronic Health Records" @default.
• W4385478066 cites W1977098485 @default.
• W4385478066 cites W2125291718 @default.
• W4385478066 cites W2157331557 @default.
• W4385478066 cites W2341109993 @default.
• W4385478066 cites W2396881363 @default.
• W4385478066 cites W2742491462 @default.
• W4385478066 cites W2771817472 @default.
• W4385478066 cites W2804604520 @default.
• W4385478066 cites W2809396336 @default.
• W4385478066 cites W2891400669 @default.
• W4385478066 cites W2943310667 @default.
• W4385478066 cites W2964010366 @default.
• W4385478066 cites W2964425131 @default.
• W4385478066 cites W2964959375 @default.
• W4385478066 cites W2997653844 @default.
• W4385478066 cites W3038139858 @default.
• W4385478066 cites W3080098168 @default.
• W4385478066 cites W3081822035 @default.
• W4385478066 cites W3094455654 @default.
• W4385478066 cites W3096831136 @default.
• W4385478066 cites W3101973032 @default.
• W4385478066 cites W3160263899 @default.
• W4385478066 cites W3174697924 @default.
• W4385478066 cites W3186462793 @default.
• W4385478066 cites W3192221070 @default.
• W4385478066 cites W4200310129 @default.
• W4385478066 cites W4207002853 @default.
• W4385478066 cites W4214660089 @default.
• W4385478066 cites W4229054007 @default.
• W4385478066 cites W4255632462 @default.
• W4385478066 doi "https://doi.org/10.1109/ijcnn54540.2023.10191793" @default.
• W4385478066 hasPublicationYear "2023" @default.
• W4385478066 type Work @default.
• W4385478066 citedByCount "0" @default.
• W4385478066 crossrefType "proceedings-article" @default.
• W4385478066 hasAuthorship W4385478066A5000633755 @default.
• W4385478066 hasAuthorship W4385478066A5001608625 @default.
• W4385478066 hasAuthorship W4385478066A5067376850 @default.
• W4385478066 hasConcept C119857082 @default.
• W4385478066 hasConcept C121332964 @default.
• W4385478066 hasConcept C124101348 @default.
• W4385478066 hasConcept C154945302 @default.
• W4385478066 hasConcept C160735492 @default.
• W4385478066 hasConcept C162324750 @default.
• W4385478066 hasConcept C163258240 @default.
• W4385478066 hasConcept C3019952477 @default.
• W4385478066 hasConcept C41008148 @default.
• W4385478066 hasConcept C43214815 @default.
• W4385478066 hasConcept C45804977 @default.
• W4385478066 hasConcept C50522688 @default.
• W4385478066 hasConcept C50644808 @default.
• W4385478066 hasConcept C58041806 @default.
• W4385478066 hasConcept C62520636 @default.
• W4385478066 hasConcept C9357733 @default.
• W4385478066 hasConceptScore W4385478066C119857082 @default.
• W4385478066 hasConceptScore W4385478066C121332964 @default.
• W4385478066 hasConceptScore W4385478066C124101348 @default.
• W4385478066 hasConceptScore W4385478066C154945302 @default.
• W4385478066 hasConceptScore W4385478066C160735492 @default.
• W4385478066 hasConceptScore W4385478066C162324750 @default.
• W4385478066 hasConceptScore W4385478066C163258240 @default.
• W4385478066 hasConceptScore W4385478066C3019952477 @default.
• W4385478066 hasConceptScore W4385478066C41008148 @default.
• W4385478066 hasConceptScore W4385478066C43214815 @default.
• W4385478066 hasConceptScore W4385478066C45804977 @default.
• W4385478066 hasConceptScore W4385478066C50522688 @default.
• W4385478066 hasConceptScore W4385478066C50644808 @default.
• W4385478066 hasConceptScore W4385478066C58041806 @default.
• W4385478066 hasConceptScore W4385478066C62520636 @default.
• W4385478066 hasConceptScore W4385478066C9357733 @default.
• W4385478066 hasLocation W43854780661 @default.
• W4385478066 hasOpenAccess W4385478066 @default.
• W4385478066 hasPrimaryLocation W43854780661 @default.
• W4385478066 hasRelatedWork W1973721774 @default.
• W4385478066 hasRelatedWork W2541565311 @default.
• W4385478066 hasRelatedWork W2751555317 @default.
• W4385478066 hasRelatedWork W2784019465 @default.
• W4385478066 hasRelatedWork W2900766238 @default.
• W4385478066 hasRelatedWork W2979641641 @default.
• W4385478066 hasRelatedWork W3049453136 @default.
• W4385478066 hasRelatedWork W4312712358 @default.
• W4385478066 hasRelatedWork W4385478066 @default.
• W4385478066 hasRelatedWork W569810835 @default.
• W4385478066 isParatext "false" @default.
• W4385478066 isRetracted "false" @default.
• W4385478066 workType "article" @default.