FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294043977> ?p ?o ?g. }

• W4294043977 abstract "Abstract With the wider availability of healthcare data such as Electronic Health Records (EHR), more and more data-driven based approaches have been proposed to improve the quality of care delivery. Predictive modeling, which aims at building computational models for predicting clinical risk, is a popular research topic in healthcare analytics. However, concerns about privacy of healthcare data may hinder the development of effective predictive models that are generalizable because this often requires rich diverse data from multiple clinical institutions. Recently, federated learning (FL) has demonstrated promise in addressing this concern. However, data heterogeneity from different local participating sites may affect prediction performance. Exploring such heterogeneity of data sources would aid in building accurate risk prediction models in FL. Due to acute kidney injury (AKI) and sepsis’ high prevalence among patients admitted to intensive care units (ICU), the early prediction of these conditions based on AI is an important topic in critical care medicine. In this study, we take AKI and sepsis onset risk prediction in ICU as two examples to explore the impact of data heterogeneity in the FL framework for risk prediction using EHR data across multiple hospitals. In particular, we built predictive models based on local, pooled, and FL frameworks. The local framework only used data from each site itself. The pooled framework combined data from all sites. In the FL framework, each local site did not have access to other sites’ data. A model was trained locally and its parameters were shared to a central aggregator, which was used to update the federated model’s weights and then subsequently, shared with each site. We found models built within a FL framework outperformed local counterparts. Then, we analyzed variable importance discrepancies across sites and frameworks. Finally, we explored potential sources of the heterogeneity within the EHR data. The different distributions of demographic profiles, medication use, and site information contributed to data heterogeneity. Author Summary The availability of a large amount of healthcare data such as Electronic Health Records (EHR) and advances of artificial intelligence (AI) techniques provides opportunities to build predictive models for disease risk prediction. Due to the sensitive nature of healthcare data, it is challenging to collect the data together from different hospitals and train a unified model on the combined data. Recent federated learning (FL) demonstrates promise in addressing the fragmented healthcare data sources with privacy-preservation. However, data heterogeneity in the FL framework may influence prediction performance. Exploring the heterogeneity of data sources would contribute to building accurate disease risk prediction models in FL. In this study, we take acute kidney injury (AKI) and sepsis prediction in intensive care units (ICU) as two examples to explore the effects of data heterogeneity in the FL framework for disease risk prediction using EHR data across multiple hospital sites. In particular, multiple predictive models were built based on local, pooled, and FL frameworks. The local framework only used data from each site itself. The pooled framework combined data from all sites. In the FL framework, each local site did not have access to other sites’ data. We found models built within a FL framework outperformed local counterparts. Then, we analyzed variable importance discrepancies across sites and frameworks. Finally, we explored potential sources of the heterogeneity within EHR data. The different distributions of demographic profiles, medication use, site information such as the type of ICU at admission contributed to data heterogeneity." @default.
• W4294043977 created "2022-09-01" @default.
• W4294043977 creator A5040648859 @default.
• W4294043977 creator A5058023532 @default.
• W4294043977 creator A5065041207 @default.
• W4294043977 creator A5068424949 @default.
• W4294043977 creator A5075323750 @default.
• W4294043977 date "2022-09-01" @default.
• W4294043977 modified "2023-09-26" @default.
• W4294043977 title "Data Heterogeneity in Federated Learning with Electronic Health Records: Case Studies of Risk Prediction for Acute Kidney Injury and Sepsis Diseases in Critical Care" @default.
• W4294043977 cites W1996531679 @default.
• W4294043977 cites W2099287015 @default.
• W4294043977 cites W2162262523 @default.
• W4294043977 cites W2282181907 @default.
• W4294043977 cites W2755626276 @default.
• W4294043977 cites W3024264813 @default.
• W4294043977 cites W3098674050 @default.
• W4294043977 cites W3100779497 @default.
• W4294043977 cites W3103802018 @default.
• W4294043977 cites W3118996476 @default.
• W4294043977 cites W4225603140 @default.
• W4294043977 doi "https://doi.org/10.1101/2022.08.30.22279382" @default.
• W4294043977 hasPublicationYear "2022" @default.
• W4294043977 type Work @default.
• W4294043977 citedByCount "0" @default.
• W4294043977 crossrefType "posted-content" @default.
• W4294043977 hasAuthorship W4294043977A5040648859 @default.
• W4294043977 hasAuthorship W4294043977A5058023532 @default.
• W4294043977 hasAuthorship W4294043977A5065041207 @default.
• W4294043977 hasAuthorship W4294043977A5068424949 @default.
• W4294043977 hasAuthorship W4294043977A5075323750 @default.
• W4294043977 hasBestOaLocation W42940439771 @default.
• W4294043977 hasConcept C119857082 @default.
• W4294043977 hasConcept C124101348 @default.
• W4294043977 hasConcept C126322002 @default.
• W4294043977 hasConcept C160735492 @default.
• W4294043977 hasConcept C162324750 @default.
• W4294043977 hasConcept C177713679 @default.
• W4294043977 hasConcept C203014093 @default.
• W4294043977 hasConcept C2522767166 @default.
• W4294043977 hasConcept C2778384902 @default.
• W4294043977 hasConcept C2780472472 @default.
• W4294043977 hasConcept C2987404301 @default.
• W4294043977 hasConcept C3019952477 @default.
• W4294043977 hasConcept C3020144179 @default.
• W4294043977 hasConcept C41008148 @default.
• W4294043977 hasConcept C45804977 @default.
• W4294043977 hasConcept C50522688 @default.
• W4294043977 hasConcept C545542383 @default.
• W4294043977 hasConcept C71924100 @default.
• W4294043977 hasConcept C83209312 @default.
• W4294043977 hasConceptScore W4294043977C119857082 @default.
• W4294043977 hasConceptScore W4294043977C124101348 @default.
• W4294043977 hasConceptScore W4294043977C126322002 @default.
• W4294043977 hasConceptScore W4294043977C160735492 @default.
• W4294043977 hasConceptScore W4294043977C162324750 @default.
• W4294043977 hasConceptScore W4294043977C177713679 @default.
• W4294043977 hasConceptScore W4294043977C203014093 @default.
• W4294043977 hasConceptScore W4294043977C2522767166 @default.
• W4294043977 hasConceptScore W4294043977C2778384902 @default.
• W4294043977 hasConceptScore W4294043977C2780472472 @default.
• W4294043977 hasConceptScore W4294043977C2987404301 @default.
• W4294043977 hasConceptScore W4294043977C3019952477 @default.
• W4294043977 hasConceptScore W4294043977C3020144179 @default.
• W4294043977 hasConceptScore W4294043977C41008148 @default.
• W4294043977 hasConceptScore W4294043977C45804977 @default.
• W4294043977 hasConceptScore W4294043977C50522688 @default.
• W4294043977 hasConceptScore W4294043977C545542383 @default.
• W4294043977 hasConceptScore W4294043977C71924100 @default.
• W4294043977 hasConceptScore W4294043977C83209312 @default.
• W4294043977 hasLocation W42940439771 @default.
• W4294043977 hasOpenAccess W4294043977 @default.
• W4294043977 hasPrimaryLocation W42940439771 @default.
• W4294043977 hasRelatedWork W2080680021 @default.
• W4294043977 hasRelatedWork W2617679349 @default.
• W4294043977 hasRelatedWork W2910674778 @default.
• W4294043977 hasRelatedWork W2915160461 @default.
• W4294043977 hasRelatedWork W3025041032 @default.
• W4294043977 hasRelatedWork W3111277802 @default.
• W4294043977 hasRelatedWork W3127432093 @default.
• W4294043977 hasRelatedWork W4292230799 @default.
• W4294043977 hasRelatedWork W4294043977 @default.
• W4294043977 hasRelatedWork W4324311136 @default.
• W4294043977 isParatext "false" @default.
• W4294043977 isRetracted "false" @default.
• W4294043977 workType "article" @default.