Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226182239> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4226182239 abstract "Abstract While there exist numerous methods to identify binary phenotypes (i.e. COPD) using electronic health record (EHR) data, few exist to ascertain the timings of phenotype events (i.e. COPD onset or exacerbations). Estimating event times could enable more powerful use of EHR data for longitudinal risk modeling, including survival analysis. Here we introduce Semi-supervised Adaptive Markov Gaussian Embedding Process (SAMGEP), a semi-supervised machine learning algorithm to estimate phenotype event times using EHR data with limited observed labels, which require resource-intensive chart review to obtain. SAMGEP models latent phenotype states as a binary Markov process, and it employs an adaptive weighting strategy to map timestamped EHR features to an embedding function that it models as a state-dependent Gaussian process. SAMGEP’s feature weighting achieves meaningful feature selection, and its predictions significantly improve AUCs and F1 scores over existing approaches in diverse simulations and real-world settings. It is particularly adept at predicting cumulative risk and event counting process functions, and is robust to diverse generative model parameters. Moreover, it achieves high accuracy with few (50-100) labels, efficiently leveraging unlabeled EHR data to maximize information gain from costly-to-obtain event time labels. SAMGEP can be used to estimate accurate phenotype state functions for risk modeling research." @default.
- W4226182239 created "2022-05-05" @default.
- W4226182239 creator A5008601756 @default.
- W4226182239 creator A5031794966 @default.
- W4226182239 creator A5034769265 @default.
- W4226182239 creator A5043900893 @default.
- W4226182239 creator A5052512997 @default.
- W4226182239 creator A5069572535 @default.
- W4226182239 date "2021-12-06" @default.
- W4226182239 modified "2023-10-16" @default.
- W4226182239 title "SAMGEP: A Novel Method for Prediction of Phenotype Event Times Using the Electronic Health Record" @default.
- W4226182239 doi "https://doi.org/10.21203/rs.3.rs-1119858/v1" @default.
- W4226182239 hasPublicationYear "2021" @default.
- W4226182239 type Work @default.
- W4226182239 citedByCount "0" @default.
- W4226182239 crossrefType "posted-content" @default.
- W4226182239 hasAuthorship W4226182239A5008601756 @default.
- W4226182239 hasAuthorship W4226182239A5031794966 @default.
- W4226182239 hasAuthorship W4226182239A5034769265 @default.
- W4226182239 hasAuthorship W4226182239A5043900893 @default.
- W4226182239 hasAuthorship W4226182239A5052512997 @default.
- W4226182239 hasAuthorship W4226182239A5069572535 @default.
- W4226182239 hasBestOaLocation W42261822391 @default.
- W4226182239 hasConcept C119857082 @default.
- W4226182239 hasConcept C121332964 @default.
- W4226182239 hasConcept C124101348 @default.
- W4226182239 hasConcept C126838900 @default.
- W4226182239 hasConcept C138885662 @default.
- W4226182239 hasConcept C154945302 @default.
- W4226182239 hasConcept C183115368 @default.
- W4226182239 hasConcept C2776401178 @default.
- W4226182239 hasConcept C2779662365 @default.
- W4226182239 hasConcept C41008148 @default.
- W4226182239 hasConcept C41608201 @default.
- W4226182239 hasConcept C41895202 @default.
- W4226182239 hasConcept C62520636 @default.
- W4226182239 hasConcept C71924100 @default.
- W4226182239 hasConceptScore W4226182239C119857082 @default.
- W4226182239 hasConceptScore W4226182239C121332964 @default.
- W4226182239 hasConceptScore W4226182239C124101348 @default.
- W4226182239 hasConceptScore W4226182239C126838900 @default.
- W4226182239 hasConceptScore W4226182239C138885662 @default.
- W4226182239 hasConceptScore W4226182239C154945302 @default.
- W4226182239 hasConceptScore W4226182239C183115368 @default.
- W4226182239 hasConceptScore W4226182239C2776401178 @default.
- W4226182239 hasConceptScore W4226182239C2779662365 @default.
- W4226182239 hasConceptScore W4226182239C41008148 @default.
- W4226182239 hasConceptScore W4226182239C41608201 @default.
- W4226182239 hasConceptScore W4226182239C41895202 @default.
- W4226182239 hasConceptScore W4226182239C62520636 @default.
- W4226182239 hasConceptScore W4226182239C71924100 @default.
- W4226182239 hasLocation W42261822391 @default.
- W4226182239 hasLocation W42261822392 @default.
- W4226182239 hasOpenAccess W4226182239 @default.
- W4226182239 hasPrimaryLocation W42261822391 @default.
- W4226182239 hasRelatedWork W1588204645 @default.
- W4226182239 hasRelatedWork W2132592511 @default.
- W4226182239 hasRelatedWork W2138705457 @default.
- W4226182239 hasRelatedWork W2283145973 @default.
- W4226182239 hasRelatedWork W2292751661 @default.
- W4226182239 hasRelatedWork W2351778949 @default.
- W4226182239 hasRelatedWork W2961085424 @default.
- W4226182239 hasRelatedWork W3162766389 @default.
- W4226182239 hasRelatedWork W4306674287 @default.
- W4226182239 hasRelatedWork W4224009465 @default.
- W4226182239 isParatext "false" @default.
- W4226182239 isRetracted "false" @default.
- W4226182239 workType "article" @default.