FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387146075> ?p ?o ?g. }

• W4387146075 endingPage "106346" @default.
• W4387146075 startingPage "106334" @default.
• W4387146075 abstract "The prognosis of a patient’s re-admission and the forecast of future diagnoses is a critical task in the process of inferring clinical outcomes. The discharge summaries recorded in the Electronic Health Records (EHR) are stinking rich but they are also heterogeneous, sparse, noisy, and biased, and hinder the learning algorithms that aim to extract actionable insights from them. The existing approaches use the current admission’s International Classification of Diseases (ICD) codes as input but they do not fully describe the progression of the patient. Other systems apply the attention mechanisms directly to these notes without the guidance of a domain knowledge resulting in distorted predictions. In this work, we propose a hybrid LSTM-CNN self-guided attention model that aims to predict the ICD diagnosis that is likely to cause the next readmission within 90 days since the current discharge using the discharge narratives. Because the notes contain unnecessary tokens, the model leverages the recent advances in deep learning to predict the patient’s future diagnosis by reducing the number of tokens from the notes to be considered for prediction. We use a 1D CNN (Convolutional Neural Network) to capture all features from the note and concurrently an LSTM (Long Short-Term Memory) is used to extract the features of clinically meaningful Concept Unique Identifiers (CUI) that are fetched from the note itself to build a knowledge base. The textual knowledge base guides the learning module about which n-grams from the note to focus on for prediction. We consider 3 prediction scenarios; diagnosis category prediction, the probability of the occurrence of one of the top 20 disease conditions and ICD9 codes prediction. For the diagnosis category prediction, the model achieves a Macro-Average ROC of 0.82, an AUROC of 0.87 for most the Top 20 most appearing diseases prediction, and a Micro-RECALL of 0.84 for ICD9 codes prediction. The predictive accuracy of the model is assessed through the prediction of heart failure onset and for all these prediction scenarios the results show that the hybrid approach outperforms the existing baselines." @default.
• W4387146075 created "2023-09-29" @default.
• W4387146075 creator A5041291468 @default.
• W4387146075 creator A5065358792 @default.
• W4387146075 creator A5067151609 @default.
• W4387146075 creator A5080143856 @default.
• W4387146075 date "2023-01-01" @default.
• W4387146075 modified "2023-10-09" @default.
• W4387146075 title "HSGA: A Hybrid LSTM-CNN Self-Guided Attention to predict the future diagnosis from discharge narratives" @default.
• W4387146075 cites W1504291959 @default.
• W4387146075 cites W2139121045 @default.
• W4387146075 cites W2146089916 @default.
• W4387146075 cites W2487770199 @default.
• W4387146075 cites W2739996966 @default.
• W4387146075 cites W2761434131 @default.
• W4387146075 cites W2786554073 @default.
• W4387146075 cites W2789244308 @default.
• W4387146075 cites W2887377515 @default.
• W4387146075 cites W2896538705 @default.
• W4387146075 cites W2912907847 @default.
• W4387146075 cites W2914767245 @default.
• W4387146075 cites W2935277013 @default.
• W4387146075 cites W2937554593 @default.
• W4387146075 cites W2945248062 @default.
• W4387146075 cites W2949638244 @default.
• W4387146075 cites W2956721904 @default.
• W4387146075 cites W2963900105 @default.
• W4387146075 cites W2964067226 @default.
• W4387146075 cites W2964138017 @default.
• W4387146075 cites W2964142373 @default.
• W4387146075 cites W2964758338 @default.
• W4387146075 cites W2964883806 @default.
• W4387146075 cites W2964959375 @default.
• W4387146075 cites W2981330198 @default.
• W4387146075 cites W2990505288 @default.
• W4387146075 cites W2992883150 @default.
• W4387146075 cites W2995776595 @default.
• W4387146075 cites W3002510506 @default.
• W4387146075 cites W3004530661 @default.
• W4387146075 cites W3005836751 @default.
• W4387146075 cites W3098949126 @default.
• W4387146075 cites W3099136959 @default.
• W4387146075 cites W3104486441 @default.
• W4387146075 cites W3154562975 @default.
• W4387146075 cites W3198894034 @default.
• W4387146075 cites W3211021852 @default.
• W4387146075 cites W4210828371 @default.
• W4387146075 cites W4286565516 @default.
• W4387146075 cites W4311762778 @default.
• W4387146075 cites W4328103228 @default.
• W4387146075 doi "https://doi.org/10.1109/access.2023.3320179" @default.
• W4387146075 hasPublicationYear "2023" @default.
• W4387146075 type Work @default.
• W4387146075 citedByCount "0" @default.
• W4387146075 crossrefType "journal-article" @default.
• W4387146075 hasAuthorship W4387146075A5041291468 @default.
• W4387146075 hasAuthorship W4387146075A5065358792 @default.
• W4387146075 hasAuthorship W4387146075A5067151609 @default.
• W4387146075 hasAuthorship W4387146075A5080143856 @default.
• W4387146075 hasBestOaLocation W43871460751 @default.
• W4387146075 hasConcept C108583219 @default.
• W4387146075 hasConcept C111919701 @default.
• W4387146075 hasConcept C119857082 @default.
• W4387146075 hasConcept C120665830 @default.
• W4387146075 hasConcept C121332964 @default.
• W4387146075 hasConcept C138885662 @default.
• W4387146075 hasConcept C142724271 @default.
• W4387146075 hasConcept C147168706 @default.
• W4387146075 hasConcept C154504017 @default.
• W4387146075 hasConcept C154945302 @default.
• W4387146075 hasConcept C162324750 @default.
• W4387146075 hasConcept C187736073 @default.
• W4387146075 hasConcept C192209626 @default.
• W4387146075 hasConcept C199033989 @default.
• W4387146075 hasConcept C199360897 @default.
• W4387146075 hasConcept C204321447 @default.
• W4387146075 hasConcept C207685749 @default.
• W4387146075 hasConcept C2780451532 @default.
• W4387146075 hasConcept C41008148 @default.
• W4387146075 hasConcept C41895202 @default.
• W4387146075 hasConcept C4554734 @default.
• W4387146075 hasConcept C50644808 @default.
• W4387146075 hasConcept C534262118 @default.
• W4387146075 hasConcept C71924100 @default.
• W4387146075 hasConcept C81363708 @default.
• W4387146075 hasConcept C98045186 @default.
• W4387146075 hasConceptScore W4387146075C108583219 @default.
• W4387146075 hasConceptScore W4387146075C111919701 @default.
• W4387146075 hasConceptScore W4387146075C119857082 @default.
• W4387146075 hasConceptScore W4387146075C120665830 @default.
• W4387146075 hasConceptScore W4387146075C121332964 @default.
• W4387146075 hasConceptScore W4387146075C138885662 @default.
• W4387146075 hasConceptScore W4387146075C142724271 @default.
• W4387146075 hasConceptScore W4387146075C147168706 @default.
• W4387146075 hasConceptScore W4387146075C154504017 @default.
• W4387146075 hasConceptScore W4387146075C154945302 @default.
• W4387146075 hasConceptScore W4387146075C162324750 @default.
• W4387146075 hasConceptScore W4387146075C187736073 @default.

• next