FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3118996476> ?p ?o ?g. }

• W3118996476 endingPage "e24207" @default.
• W3118996476 startingPage "e24207" @default.
• W3118996476 abstract "Background Machine learning models require large datasets that may be siloed across different health care institutions. Machine learning studies that focus on COVID-19 have been limited to single-hospital data, which limits model generalizability. Objective We aimed to use federated learning, a machine learning technique that avoids locally aggregating raw clinical data across multiple institutions, to predict mortality in hospitalized patients with COVID-19 within 7 days. Methods Patient data were collected from the electronic health records of 5 hospitals within the Mount Sinai Health System. Logistic regression with L1 regularization/least absolute shrinkage and selection operator (LASSO) and multilayer perceptron (MLP) models were trained by using local data at each site. We developed a pooled model with combined data from all 5 sites, and a federated model that only shared parameters with a central aggregator. Results The LASSOfederated model outperformed the LASSOlocal model at 3 hospitals, and the MLPfederated model performed better than the MLPlocal model at all 5 hospitals, as determined by the area under the receiver operating characteristic curve. The LASSOpooled model outperformed the LASSOfederated model at all hospitals, and the MLPfederated model outperformed the MLPpooled model at 2 hospitals. Conclusions The federated learning of COVID-19 electronic health record data shows promise in developing robust predictive models without compromising patient privacy." @default.
• W3118996476 created "2021-01-18" @default.
• W3118996476 creator A5001694059 @default.
• W3118996476 creator A5011314581 @default.
• W3118996476 creator A5016960786 @default.
• W3118996476 creator A5024226831 @default.
• W3118996476 creator A5025121313 @default.
• W3118996476 creator A5030539003 @default.
• W3118996476 creator A5032914921 @default.
• W3118996476 creator A5039899830 @default.
• W3118996476 creator A5042331995 @default.
• W3118996476 creator A5047405500 @default.
• W3118996476 creator A5053966533 @default.
• W3118996476 creator A5068151024 @default.
• W3118996476 creator A5071606253 @default.
• W3118996476 creator A5076569669 @default.
• W3118996476 creator A5083358059 @default.
• W3118996476 creator A5084566613 @default.
• W3118996476 creator A5084794615 @default.
• W3118996476 creator A5085531312 @default.
• W3118996476 creator A5085920644 @default.
• W3118996476 creator A5086529957 @default.
• W3118996476 creator A5087511277 @default.
• W3118996476 creator A5089434484 @default.
• W3118996476 creator A5091224898 @default.
• W3118996476 date "2021-01-27" @default.
• W3118996476 modified "2023-10-17" @default.
• W3118996476 title "Federated Learning of Electronic Health Records to Improve Mortality Prediction in Hospitalized Patients With COVID-19: Machine Learning Approach" @default.
• W3118996476 cites W2331331492 @default.
• W3118996476 cites W3004906315 @default.
• W3118996476 cites W3007940623 @default.
• W3118996476 cites W3008028633 @default.
• W3118996476 cites W3008443627 @default.
• W3118996476 cites W3010233963 @default.
• W3118996476 cites W3012454642 @default.
• W3118996476 cites W3021954309 @default.
• W3118996476 cites W3024264813 @default.
• W3118996476 cites W3025948831 @default.
• W3118996476 cites W3033315805 @default.
• W3118996476 cites W3037624367 @default.
• W3118996476 cites W3041275674 @default.
• W3118996476 cites W3044952634 @default.
• W3118996476 cites W3075432525 @default.
• W3118996476 doi "https://doi.org/10.2196/24207" @default.
• W3118996476 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7842859" @default.
• W3118996476 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33400679" @default.
• W3118996476 hasPublicationYear "2021" @default.
• W3118996476 type Work @default.
• W3118996476 sameAs 3118996476 @default.
• W3118996476 citedByCount "90" @default.
• W3118996476 countsByYear W31189964762020 @default.
• W3118996476 countsByYear W31189964762021 @default.
• W3118996476 countsByYear W31189964762022 @default.
• W3118996476 countsByYear W31189964762023 @default.
• W3118996476 crossrefType "journal-article" @default.
• W3118996476 hasAuthorship W3118996476A5001694059 @default.
• W3118996476 hasAuthorship W3118996476A5011314581 @default.
• W3118996476 hasAuthorship W3118996476A5016960786 @default.
• W3118996476 hasAuthorship W3118996476A5024226831 @default.
• W3118996476 hasAuthorship W3118996476A5025121313 @default.
• W3118996476 hasAuthorship W3118996476A5030539003 @default.
• W3118996476 hasAuthorship W3118996476A5032914921 @default.
• W3118996476 hasAuthorship W3118996476A5039899830 @default.
• W3118996476 hasAuthorship W3118996476A5042331995 @default.
• W3118996476 hasAuthorship W3118996476A5047405500 @default.
• W3118996476 hasAuthorship W3118996476A5053966533 @default.
• W3118996476 hasAuthorship W3118996476A5068151024 @default.
• W3118996476 hasAuthorship W3118996476A5071606253 @default.
• W3118996476 hasAuthorship W3118996476A5076569669 @default.
• W3118996476 hasAuthorship W3118996476A5083358059 @default.
• W3118996476 hasAuthorship W3118996476A5084566613 @default.
• W3118996476 hasAuthorship W3118996476A5084794615 @default.
• W3118996476 hasAuthorship W3118996476A5085531312 @default.
• W3118996476 hasAuthorship W3118996476A5085920644 @default.
• W3118996476 hasAuthorship W3118996476A5086529957 @default.
• W3118996476 hasAuthorship W3118996476A5087511277 @default.
• W3118996476 hasAuthorship W3118996476A5089434484 @default.
• W3118996476 hasAuthorship W3118996476A5091224898 @default.
• W3118996476 hasBestOaLocation W31189964761 @default.
• W3118996476 hasConcept C105795698 @default.
• W3118996476 hasConcept C119857082 @default.
• W3118996476 hasConcept C136764020 @default.
• W3118996476 hasConcept C151956035 @default.
• W3118996476 hasConcept C154945302 @default.
• W3118996476 hasConcept C160735492 @default.
• W3118996476 hasConcept C162324750 @default.
• W3118996476 hasConcept C179717631 @default.
• W3118996476 hasConcept C27158222 @default.
• W3118996476 hasConcept C3019952477 @default.
• W3118996476 hasConcept C3020144179 @default.
• W3118996476 hasConcept C33923547 @default.
• W3118996476 hasConcept C37616216 @default.
• W3118996476 hasConcept C41008148 @default.
• W3118996476 hasConcept C45804977 @default.
• W3118996476 hasConcept C50522688 @default.
• W3118996476 hasConcept C50644808 @default.
• W3118996476 hasConcept C71924100 @default.
• W3118996476 hasConceptScore W3118996476C105795698 @default.

• next