Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042022206> ?p ?o ?g. }
- W3042022206 endingPage "258" @default.
- W3042022206 startingPage "249" @default.
- W3042022206 abstract "Healthcare providers are increasingly using machine learning to predict patient outcomes to make meaningful interventions. However, despite innovations in this area, deep learning models often struggle to match performance of shallow linear models in predicting these outcomes, making it difficult to leverage such techniques in practice. In this work, motivated by the task of clinical prediction from insurance claims, we present a new technique called reverse distillation which pretrains deep models by using high-performing linear models for initialization. We make use of the longitudinal structure of insurance claims datasets to develop Self Attention with Reverse Distillation, or SARD, an architecture that utilizes a combination of contextual embedding, temporal embedding and self-attention mechanisms and most critically is trained via reverse distillation. SARD outperforms state-of-the-art methods on multiple clinical prediction outcomes, with ablation studies revealing that reverse distillation is a primary driver of these improvements. Code is available at https://github.com/clinicalml/omop-learn." @default.
- W3042022206 created "2020-07-16" @default.
- W3042022206 creator A5013325970 @default.
- W3042022206 creator A5013431623 @default.
- W3042022206 creator A5014775997 @default.
- W3042022206 creator A5026061438 @default.
- W3042022206 creator A5030832120 @default.
- W3042022206 creator A5036303153 @default.
- W3042022206 date "2021-05-18" @default.
- W3042022206 modified "2023-09-28" @default.
- W3042022206 title "Deep Contextual Clinical Prediction with Reverse Distillation" @default.
- W3042022206 cites W1522301498 @default.
- W3042022206 cites W1821462560 @default.
- W3042022206 cites W1998616342 @default.
- W3042022206 cites W2098824882 @default.
- W3042022206 cites W2239135493 @default.
- W3042022206 cites W2328176404 @default.
- W3042022206 cites W2404901863 @default.
- W3042022206 cites W2481271618 @default.
- W3042022206 cites W2514071032 @default.
- W3042022206 cites W2557074642 @default.
- W3042022206 cites W2742491462 @default.
- W3042022206 cites W2753798143 @default.
- W3042022206 cites W2767395101 @default.
- W3042022206 cites W2804604520 @default.
- W3042022206 cites W2805497466 @default.
- W3042022206 cites W2901107321 @default.
- W3042022206 cites W2904803701 @default.
- W3042022206 cites W2914241418 @default.
- W3042022206 cites W2948184675 @default.
- W3042022206 cites W2963208729 @default.
- W3042022206 cites W2963271116 @default.
- W3042022206 cites W2963341956 @default.
- W3042022206 cites W2963403868 @default.
- W3042022206 cites W2964010366 @default.
- W3042022206 cites W2964098911 @default.
- W3042022206 cites W2964312993 @default.
- W3042022206 cites W2970971581 @default.
- W3042022206 cites W2985962305 @default.
- W3042022206 cites W2997653844 @default.
- W3042022206 cites W3000098859 @default.
- W3042022206 cites W3002709689 @default.
- W3042022206 cites W3017637887 @default.
- W3042022206 cites W3090841144 @default.
- W3042022206 cites W3098949126 @default.
- W3042022206 cites W3099136959 @default.
- W3042022206 cites W3101397981 @default.
- W3042022206 cites W3101973032 @default.
- W3042022206 cites W3102696737 @default.
- W3042022206 cites W3190561168 @default.
- W3042022206 cites W2402632249 @default.
- W3042022206 doi "https://doi.org/10.1609/aaai.v35i1.16099" @default.
- W3042022206 hasPublicationYear "2021" @default.
- W3042022206 type Work @default.
- W3042022206 sameAs 3042022206 @default.
- W3042022206 citedByCount "4" @default.
- W3042022206 countsByYear W30420222062022 @default.
- W3042022206 countsByYear W30420222062023 @default.
- W3042022206 crossrefType "journal-article" @default.
- W3042022206 hasAuthorship W3042022206A5013325970 @default.
- W3042022206 hasAuthorship W3042022206A5013431623 @default.
- W3042022206 hasAuthorship W3042022206A5014775997 @default.
- W3042022206 hasAuthorship W3042022206A5026061438 @default.
- W3042022206 hasAuthorship W3042022206A5030832120 @default.
- W3042022206 hasAuthorship W3042022206A5036303153 @default.
- W3042022206 hasBestOaLocation W30420222061 @default.
- W3042022206 hasConcept C108583219 @default.
- W3042022206 hasConcept C114466953 @default.
- W3042022206 hasConcept C119857082 @default.
- W3042022206 hasConcept C153083717 @default.
- W3042022206 hasConcept C154945302 @default.
- W3042022206 hasConcept C178790620 @default.
- W3042022206 hasConcept C185592680 @default.
- W3042022206 hasConcept C199360897 @default.
- W3042022206 hasConcept C204030448 @default.
- W3042022206 hasConcept C41008148 @default.
- W3042022206 hasConcept C41608201 @default.
- W3042022206 hasConceptScore W3042022206C108583219 @default.
- W3042022206 hasConceptScore W3042022206C114466953 @default.
- W3042022206 hasConceptScore W3042022206C119857082 @default.
- W3042022206 hasConceptScore W3042022206C153083717 @default.
- W3042022206 hasConceptScore W3042022206C154945302 @default.
- W3042022206 hasConceptScore W3042022206C178790620 @default.
- W3042022206 hasConceptScore W3042022206C185592680 @default.
- W3042022206 hasConceptScore W3042022206C199360897 @default.
- W3042022206 hasConceptScore W3042022206C204030448 @default.
- W3042022206 hasConceptScore W3042022206C41008148 @default.
- W3042022206 hasConceptScore W3042022206C41608201 @default.
- W3042022206 hasIssue "1" @default.
- W3042022206 hasLocation W30420222061 @default.
- W3042022206 hasLocation W30420222062 @default.
- W3042022206 hasOpenAccess W3042022206 @default.
- W3042022206 hasPrimaryLocation W30420222061 @default.
- W3042022206 hasRelatedWork W3014300295 @default.
- W3042022206 hasRelatedWork W3164822677 @default.
- W3042022206 hasRelatedWork W4223943233 @default.
- W3042022206 hasRelatedWork W4225161397 @default.
- W3042022206 hasRelatedWork W4250304930 @default.