FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2810401299> ?p ?o ?g. }

• W2810401299 endingPage "S10" @default.
• W2810401299 startingPage "S10" @default.
• W2810401299 abstract "The emergence of precision medicine and the movement of large volumes of medical records to an electronic format provides opportunities to make risk prediction and intervention selection more precise but introduces methodologic challenges to traditional modelling approaches. Bayesian networks (BNs) are graphical probabilistic models increasingly being applied and are well suited to handling the unique challenges of the precision medicine era. Approach: We introduce BNs, key theoretical concepts around graphical probabilistic models and our review of the literature on the applications of such models to real-world problems for medical interventions, specifically causal reasoning under uncertainty for decision models and risk prediction. We present five examples where BNs represent a different approach to risk prediction from commonly used generalized linear regression models. BNs are graphical representations of a joint probability distribution made up of nodes and edges representing random variables and the influences between them. BNs are computationally efficient because of the explicit representation of independencies between nodes, which can result in a large reduction of connectivity in a graph. Reasoning from effect to cause is a special capability of BNs that enables individual-level ‘what if’ analyses to identify hidden sources of value. Risk prediction modelling with BNs has several advantages over commonly used regression-based approaches that address routine challenges in risk prediction: 1) they generate network structures such that can be visualized and disseminated; 2) they can perform what-if scenario analysis and individual level risk prediction, and 3) they can be transformed into decision models straightforwardly growing only linearly with the decision problem. The coming era of precision medicine will require novel approaches to risk prediction and decision analysis while maintaining a high degree of flexibility to accommodate developments in knowledge, new interventions and database complexity. BN approaches facilitate this and should be explored further." @default.
• W2810401299 created "2018-07-10" @default.
• W2810401299 creator A5019379095 @default.
• W2810401299 creator A5031562242 @default.
• W2810401299 creator A5049181806 @default.
• W2810401299 date "2018-05-01" @default.
• W2810401299 modified "2023-09-27" @default.
• W2810401299 title "Graphical Probabilistic Models for Risk Prediction and Decision Making Using Real-World Data: A Developing Tool for the Era of Precision Medicine" @default.
• W2810401299 doi "https://doi.org/10.1016/j.jval.2018.04.048" @default.
• W2810401299 hasPublicationYear "2018" @default.
• W2810401299 type Work @default.
• W2810401299 sameAs 2810401299 @default.
• W2810401299 citedByCount "0" @default.
• W2810401299 crossrefType "journal-article" @default.
• W2810401299 hasAuthorship W2810401299A5019379095 @default.
• W2810401299 hasAuthorship W2810401299A5031562242 @default.
• W2810401299 hasAuthorship W2810401299A5049181806 @default.
• W2810401299 hasBestOaLocation W28104012991 @default.
• W2810401299 hasConcept C119857082 @default.
• W2810401299 hasConcept C124101348 @default.
• W2810401299 hasConcept C132525143 @default.
• W2810401299 hasConcept C154945302 @default.
• W2810401299 hasConcept C155846161 @default.
• W2810401299 hasConcept C17744445 @default.
• W2810401299 hasConcept C199539241 @default.
• W2810401299 hasConcept C2776359362 @default.
• W2810401299 hasConcept C33724603 @default.
• W2810401299 hasConcept C41008148 @default.
• W2810401299 hasConcept C49937458 @default.
• W2810401299 hasConcept C80444323 @default.
• W2810401299 hasConcept C94625758 @default.
• W2810401299 hasConceptScore W2810401299C119857082 @default.
• W2810401299 hasConceptScore W2810401299C124101348 @default.
• W2810401299 hasConceptScore W2810401299C132525143 @default.
• W2810401299 hasConceptScore W2810401299C154945302 @default.
• W2810401299 hasConceptScore W2810401299C155846161 @default.
• W2810401299 hasConceptScore W2810401299C17744445 @default.
• W2810401299 hasConceptScore W2810401299C199539241 @default.
• W2810401299 hasConceptScore W2810401299C2776359362 @default.
• W2810401299 hasConceptScore W2810401299C33724603 @default.
• W2810401299 hasConceptScore W2810401299C41008148 @default.
• W2810401299 hasConceptScore W2810401299C49937458 @default.
• W2810401299 hasConceptScore W2810401299C80444323 @default.
• W2810401299 hasConceptScore W2810401299C94625758 @default.
• W2810401299 hasLocation W28104012991 @default.
• W2810401299 hasOpenAccess W2810401299 @default.
• W2810401299 hasPrimaryLocation W28104012991 @default.
• W2810401299 hasRelatedWork W1571764942 @default.
• W2810401299 hasRelatedWork W2043642599 @default.
• W2810401299 hasRelatedWork W2128214664 @default.
• W2810401299 hasRelatedWork W2158940596 @default.
• W2810401299 hasRelatedWork W2189510368 @default.
• W2810401299 hasRelatedWork W2210219486 @default.
• W2810401299 hasRelatedWork W2511279186 @default.
• W2810401299 hasRelatedWork W2561451072 @default.
• W2810401299 hasRelatedWork W2963058055 @default.
• W2810401299 hasRelatedWork W3125134981 @default.
• W2810401299 hasVolume "21" @default.
• W2810401299 isParatext "false" @default.
• W2810401299 isRetracted "false" @default.
• W2810401299 magId "2810401299" @default.
• W2810401299 workType "article" @default.