FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3085682242> ?p ?o ?g. }

• W3085682242 abstract "Abstract Background We focus on the importance of interpreting the quality of the labeling used as the input of predictive models to understand the reliability of their output in support of human decision-making, especially in critical domains, such as medicine. Methods Accordingly, we propose a framework distinguishing the reference labeling (or Gold Standard) from the set of annotations from which it is usually derived (the Diamond Standard). We define a set of quality dimensions and related metrics: representativeness (are the available data representative of its reference population?); reliability (do the raters agree with each other in their ratings?); and accuracy (are the raters’ annotations a true representation?). The metrics for these dimensions are, respectively, the degree of correspondence , Ψ , the degree of weighted concordance ϱ , and the degree of fineness , Φ . We apply and evaluate these metrics in a diagnostic user study involving 13 radiologists. Results We evaluate Ψ against hypothesis-testing techniques, highlighting that our metrics can better evaluate distribution similarity in high-dimensional spaces. We discuss how Ψ could be used to assess the reliability of new predictions or for train-test selection. We report the value of ϱ for our case study and compare it with traditional reliability metrics, highlighting both their theoretical properties and the reasons that they differ. Then, we report the degree of fineness as an estimate of the accuracy of the collected annotations and discuss the relationship between this latter degree and the degree of weighted concordance , which we find to be moderately but significantly correlated. Finally, we discuss the implications of the proposed dimensions and metrics with respect to the context of Explainable Artificial Intelligence (XAI). Conclusion We propose different dimensions and related metrics to assess the quality of the datasets used to build predictive models and Medical Artificial Intelligence (MAI). We argue that the proposed metrics are feasible for application in real-world settings for the continuous development of trustable and interpretable MAI systems." @default.
• W3085682242 created "2020-09-21" @default.
• W3085682242 creator A5023849668 @default.
• W3085682242 creator A5045931370 @default.
• W3085682242 creator A5079824065 @default.
• W3085682242 date "2020-09-11" @default.
• W3085682242 modified "2023-10-09" @default.
• W3085682242 title "As if sand were stone. New concepts and metrics to probe the ground on which to build trustable AI" @default.
• W3085682242 cites W1600834507 @default.
• W3085682242 cites W160583832 @default.
• W3085682242 cites W1921594208 @default.
• W3085682242 cites W1972571116 @default.
• W3085682242 cites W1975971445 @default.
• W3085682242 cites W2003052370 @default.
• W3085682242 cites W2026653933 @default.
• W3085682242 cites W2061402733 @default.
• W3085682242 cites W2061504941 @default.
• W3085682242 cites W2106412328 @default.
• W3085682242 cites W2125865219 @default.
• W3085682242 cites W2132131059 @default.
• W3085682242 cites W2132138475 @default.
• W3085682242 cites W2132481658 @default.
• W3085682242 cites W2140080602 @default.
• W3085682242 cites W2146772657 @default.
• W3085682242 cites W2148215741 @default.
• W3085682242 cites W2153130422 @default.
• W3085682242 cites W2164777277 @default.
• W3085682242 cites W2165990543 @default.
• W3085682242 cites W2166944917 @default.
• W3085682242 cites W2293246850 @default.
• W3085682242 cites W2406470551 @default.
• W3085682242 cites W2800117778 @default.
• W3085682242 cites W2896215772 @default.
• W3085682242 cites W2902874468 @default.
• W3085682242 cites W2913345658 @default.
• W3085682242 cites W2921675416 @default.
• W3085682242 cites W2941140577 @default.
• W3085682242 cites W2993404698 @default.
• W3085682242 cites W3007464329 @default.
• W3085682242 cites W3011721937 @default.
• W3085682242 cites W3013578857 @default.
• W3085682242 cites W3013677525 @default.
• W3085682242 cites W3035203924 @default.
• W3085682242 cites W3192862352 @default.
• W3085682242 cites W383308755 @default.
• W3085682242 cites W4230388840 @default.
• W3085682242 cites W4238284510 @default.
• W3085682242 cites W4238893454 @default.
• W3085682242 cites W4252793191 @default.
• W3085682242 cites W4301347335 @default.
• W3085682242 doi "https://doi.org/10.1186/s12911-020-01224-9" @default.
• W3085682242 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7488864" @default.
• W3085682242 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32917183" @default.
• W3085682242 hasPublicationYear "2020" @default.
• W3085682242 type Work @default.
• W3085682242 sameAs 3085682242 @default.
• W3085682242 citedByCount "21" @default.
• W3085682242 countsByYear W30856822422020 @default.
• W3085682242 countsByYear W30856822422021 @default.
• W3085682242 countsByYear W30856822422022 @default.
• W3085682242 countsByYear W30856822422023 @default.
• W3085682242 crossrefType "journal-article" @default.
• W3085682242 hasAuthorship W3085682242A5023849668 @default.
• W3085682242 hasAuthorship W3085682242A5045931370 @default.
• W3085682242 hasAuthorship W3085682242A5079824065 @default.
• W3085682242 hasBestOaLocation W30856822421 @default.
• W3085682242 hasConcept C103278499 @default.
• W3085682242 hasConcept C105795698 @default.
• W3085682242 hasConcept C111472728 @default.
• W3085682242 hasConcept C115961682 @default.
• W3085682242 hasConcept C119857082 @default.
• W3085682242 hasConcept C121332964 @default.
• W3085682242 hasConcept C124101348 @default.
• W3085682242 hasConcept C126322002 @default.
• W3085682242 hasConcept C138885662 @default.
• W3085682242 hasConcept C144024400 @default.
• W3085682242 hasConcept C149923435 @default.
• W3085682242 hasConcept C154945302 @default.
• W3085682242 hasConcept C160798450 @default.
• W3085682242 hasConcept C163258240 @default.
• W3085682242 hasConcept C177264268 @default.
• W3085682242 hasConcept C17744445 @default.
• W3085682242 hasConcept C199360897 @default.
• W3085682242 hasConcept C199539241 @default.
• W3085682242 hasConcept C24890656 @default.
• W3085682242 hasConcept C2775997480 @default.
• W3085682242 hasConcept C2776359362 @default.
• W3085682242 hasConcept C2779530757 @default.
• W3085682242 hasConcept C2908647359 @default.
• W3085682242 hasConcept C33923547 @default.
• W3085682242 hasConcept C37381756 @default.
• W3085682242 hasConcept C41008148 @default.
• W3085682242 hasConcept C43214815 @default.
• W3085682242 hasConcept C62520636 @default.
• W3085682242 hasConcept C71924100 @default.
• W3085682242 hasConcept C94625758 @default.
• W3085682242 hasConceptScore W3085682242C103278499 @default.
• W3085682242 hasConceptScore W3085682242C105795698 @default.
• W3085682242 hasConceptScore W3085682242C111472728 @default.
• W3085682242 hasConceptScore W3085682242C115961682 @default.

• next