FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210291236> ?p ?o ?g. }

• W3210291236 abstract "Causal artificial intelligence aims at developing bias-robust models that can be used to intervene on, rather than just be predictive, of risks or outcomes. However, learning interventional models from observational data, including electronic health records (EHR), is challenging due to inherent bias, e.g., protopathic, confounding, collider. When estimating the effects of treatment interventions, classical approaches like propensity score matching are often used, but they pose limitations with large feature sets, nonlinear/nonparallel treatment group assignments, and collider bias. In this work, we used data from a large EHR consortium –OneFlorida– and evaluated causal statistical/machine learning methods for determining the effect of statin treatment on the risk of Alzheimer's disease, a debated clinical research question. We introduced a combination of directed acyclic graph (DAG) learning and comparison with expert's design, with calculation of the generalized adjustment criterion (GAC), to find an optimal set of covariates for estimation of treatment effects –ameliorating collider bias. The DAG/CAC approach was assessed together with traditional propensity score matching, inverse probability weighting, virtual-twin/counterfactual random forests, and deep counterfactual networks. We showed large heterogeneity in effect estimates upon different model configurations. Our results did not exclude a protective effect of statins, where the DAG/GAC point estimate aligned with the maximum credibility estimate, although the 95% credibility interval included a null effect, warranting further studies and replication." @default.
• W3210291236 created "2021-11-08" @default.
• W3210291236 creator A5021264901 @default.
• W3210291236 creator A5030387965 @default.
• W3210291236 creator A5030951014 @default.
• W3210291236 creator A5031161176 @default.
• W3210291236 creator A5032349293 @default.
• W3210291236 creator A5064885745 @default.
• W3210291236 creator A5071945053 @default.
• W3210291236 date "2021-05-14" @default.
• W3210291236 modified "2023-10-15" @default.
• W3210291236 title "Causal AI with Real World Data: Do Statins Protect from Alzheimer's Disease Onset?" @default.
• W3210291236 cites W1967862917 @default.
• W3210291236 cites W1986817546 @default.
• W3210291236 cites W2003336670 @default.
• W3210291236 cites W2024046085 @default.
• W3210291236 cites W2036193982 @default.
• W3210291236 cites W2064903582 @default.
• W3210291236 cites W2071068165 @default.
• W3210291236 cites W2075917870 @default.
• W3210291236 cites W2114063969 @default.
• W3210291236 cites W2120199131 @default.
• W3210291236 cites W2147048440 @default.
• W3210291236 cites W2165460624 @default.
• W3210291236 cites W2298338128 @default.
• W3210291236 cites W2484145743 @default.
• W3210291236 cites W2512043450 @default.
• W3210291236 cites W2560688864 @default.
• W3210291236 cites W2575790444 @default.
• W3210291236 cites W2582129089 @default.
• W3210291236 cites W2588146368 @default.
• W3210291236 cites W2794003552 @default.
• W3210291236 cites W2796659858 @default.
• W3210291236 cites W2808880546 @default.
• W3210291236 cites W2883560037 @default.
• W3210291236 cites W2896002881 @default.
• W3210291236 cites W2935712808 @default.
• W3210291236 cites W2948579453 @default.
• W3210291236 cites W2987196201 @default.
• W3210291236 cites W3041564249 @default.
• W3210291236 cites W3106503709 @default.
• W3210291236 doi "https://doi.org/10.1145/3472813.3473206" @default.
• W3210291236 hasPublicationYear "2021" @default.
• W3210291236 type Work @default.
• W3210291236 sameAs 3210291236 @default.
• W3210291236 citedByCount "0" @default.
• W3210291236 crossrefType "proceedings-article" @default.
• W3210291236 hasAuthorship W3210291236A5021264901 @default.
• W3210291236 hasAuthorship W3210291236A5030387965 @default.
• W3210291236 hasAuthorship W3210291236A5030951014 @default.
• W3210291236 hasAuthorship W3210291236A5031161176 @default.
• W3210291236 hasAuthorship W3210291236A5032349293 @default.
• W3210291236 hasAuthorship W3210291236A5064885745 @default.
• W3210291236 hasAuthorship W3210291236A5071945053 @default.
• W3210291236 hasConcept C107673813 @default.
• W3210291236 hasConcept C108650721 @default.
• W3210291236 hasConcept C11413529 @default.
• W3210291236 hasConcept C119043178 @default.
• W3210291236 hasConcept C119857082 @default.
• W3210291236 hasConcept C121332964 @default.
• W3210291236 hasConcept C126322002 @default.
• W3210291236 hasConcept C149782125 @default.
• W3210291236 hasConcept C152290109 @default.
• W3210291236 hasConcept C154945302 @default.
• W3210291236 hasConcept C15744967 @default.
• W3210291236 hasConcept C158600405 @default.
• W3210291236 hasConcept C17923572 @default.
• W3210291236 hasConcept C185544564 @default.
• W3210291236 hasConcept C23131810 @default.
• W3210291236 hasConcept C33923547 @default.
• W3210291236 hasConcept C35981017 @default.
• W3210291236 hasConcept C41008148 @default.
• W3210291236 hasConcept C57830394 @default.
• W3210291236 hasConcept C71924100 @default.
• W3210291236 hasConcept C74197172 @default.
• W3210291236 hasConcept C77805123 @default.
• W3210291236 hasConceptScore W3210291236C107673813 @default.
• W3210291236 hasConceptScore W3210291236C108650721 @default.
• W3210291236 hasConceptScore W3210291236C11413529 @default.
• W3210291236 hasConceptScore W3210291236C119043178 @default.
• W3210291236 hasConceptScore W3210291236C119857082 @default.
• W3210291236 hasConceptScore W3210291236C121332964 @default.
• W3210291236 hasConceptScore W3210291236C126322002 @default.
• W3210291236 hasConceptScore W3210291236C149782125 @default.
• W3210291236 hasConceptScore W3210291236C152290109 @default.
• W3210291236 hasConceptScore W3210291236C154945302 @default.
• W3210291236 hasConceptScore W3210291236C15744967 @default.
• W3210291236 hasConceptScore W3210291236C158600405 @default.
• W3210291236 hasConceptScore W3210291236C17923572 @default.
• W3210291236 hasConceptScore W3210291236C185544564 @default.
• W3210291236 hasConceptScore W3210291236C23131810 @default.
• W3210291236 hasConceptScore W3210291236C33923547 @default.
• W3210291236 hasConceptScore W3210291236C35981017 @default.
• W3210291236 hasConceptScore W3210291236C41008148 @default.
• W3210291236 hasConceptScore W3210291236C57830394 @default.
• W3210291236 hasConceptScore W3210291236C71924100 @default.
• W3210291236 hasConceptScore W3210291236C74197172 @default.
• W3210291236 hasConceptScore W3210291236C77805123 @default.
• W3210291236 hasFunder F4320332161 @default.
• W3210291236 hasLocation W32102912361 @default.

• next