Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211282104> ?p ?o ?g. }
- W3211282104 abstract "Abstract Machine learning and artificial intelligence have entered biomedical decision-making for diagnostics, prognostics, or therapy recommendations. However, these methods need to be interpreted with care because of the severe consequences for patients. In contrast to human decision-making, computational models typically make a decision also with low confidence. Machine learning with abstention better reflects human decision-making by introducing a reject option for samples with low confidence. The abstention intervals are typically symmetric intervals around the decision boundary. In the current study, we use asymmetric abstention intervals, which we demonstrate to be better suited for biomedical data that is typically highly imbalanced. We evaluate symmetric and asymmetric abstention on three real-world biomedical datasets and show that both approaches can significantly improve classification performance. However, asymmetric abstention rejects as many or fewer samples compared to symmetric abstention and thus, should be used in imbalanced data." @default.
- W3211282104 created "2021-11-08" @default.
- W3211282104 creator A5024834862 @default.
- W3211282104 creator A5060650201 @default.
- W3211282104 creator A5082777396 @default.
- W3211282104 date "2021-10-26" @default.
- W3211282104 modified "2023-10-03" @default.
- W3211282104 title "Machine learning with asymmetric abstention for biomedical decision-making" @default.
- W3211282104 cites W1505191356 @default.
- W3211282104 cites W1597716561 @default.
- W3211282104 cites W1969557815 @default.
- W3211282104 cites W1970488621 @default.
- W3211282104 cites W2009467617 @default.
- W3211282104 cites W2043919728 @default.
- W3211282104 cites W2064186732 @default.
- W3211282104 cites W2081337758 @default.
- W3211282104 cites W2104551758 @default.
- W3211282104 cites W2118377301 @default.
- W3211282104 cites W2126022166 @default.
- W3211282104 cites W2147947791 @default.
- W3211282104 cites W2402601207 @default.
- W3211282104 cites W2470965540 @default.
- W3211282104 cites W2550614318 @default.
- W3211282104 cites W2760946358 @default.
- W3211282104 cites W2798891231 @default.
- W3211282104 cites W2800714951 @default.
- W3211282104 cites W2805983151 @default.
- W3211282104 cites W2807833939 @default.
- W3211282104 cites W2902872384 @default.
- W3211282104 cites W2920054351 @default.
- W3211282104 cites W2949479579 @default.
- W3211282104 cites W2969756003 @default.
- W3211282104 cites W2999309192 @default.
- W3211282104 cites W3001821705 @default.
- W3211282104 cites W3037405958 @default.
- W3211282104 cites W3093152954 @default.
- W3211282104 cites W3143784018 @default.
- W3211282104 cites W3159075814 @default.
- W3211282104 cites W4256078332 @default.
- W3211282104 cites W4299689471 @default.
- W3211282104 doi "https://doi.org/10.1186/s12911-021-01655-y" @default.
- W3211282104 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8549182" @default.
- W3211282104 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34702225" @default.
- W3211282104 hasPublicationYear "2021" @default.
- W3211282104 type Work @default.
- W3211282104 sameAs 3211282104 @default.
- W3211282104 citedByCount "4" @default.
- W3211282104 countsByYear W32112821042022 @default.
- W3211282104 countsByYear W32112821042023 @default.
- W3211282104 crossrefType "journal-article" @default.
- W3211282104 hasAuthorship W3211282104A5024834862 @default.
- W3211282104 hasAuthorship W3211282104A5060650201 @default.
- W3211282104 hasAuthorship W3211282104A5082777396 @default.
- W3211282104 hasBestOaLocation W32112821041 @default.
- W3211282104 hasConcept C119857082 @default.
- W3211282104 hasConcept C124101348 @default.
- W3211282104 hasConcept C129364497 @default.
- W3211282104 hasConcept C145642194 @default.
- W3211282104 hasConcept C154945302 @default.
- W3211282104 hasConcept C160735492 @default.
- W3211282104 hasConcept C162324750 @default.
- W3211282104 hasConcept C2983241795 @default.
- W3211282104 hasConcept C41008148 @default.
- W3211282104 hasConcept C50522688 @default.
- W3211282104 hasConcept C545542383 @default.
- W3211282104 hasConcept C71924100 @default.
- W3211282104 hasConceptScore W3211282104C119857082 @default.
- W3211282104 hasConceptScore W3211282104C124101348 @default.
- W3211282104 hasConceptScore W3211282104C129364497 @default.
- W3211282104 hasConceptScore W3211282104C145642194 @default.
- W3211282104 hasConceptScore W3211282104C154945302 @default.
- W3211282104 hasConceptScore W3211282104C160735492 @default.
- W3211282104 hasConceptScore W3211282104C162324750 @default.
- W3211282104 hasConceptScore W3211282104C2983241795 @default.
- W3211282104 hasConceptScore W3211282104C41008148 @default.
- W3211282104 hasConceptScore W3211282104C50522688 @default.
- W3211282104 hasConceptScore W3211282104C545542383 @default.
- W3211282104 hasConceptScore W3211282104C71924100 @default.
- W3211282104 hasFunder F4320310905 @default.
- W3211282104 hasIssue "1" @default.
- W3211282104 hasLocation W32112821041 @default.
- W3211282104 hasLocation W32112821042 @default.
- W3211282104 hasLocation W32112821043 @default.
- W3211282104 hasLocation W32112821044 @default.
- W3211282104 hasLocation W32112821045 @default.
- W3211282104 hasOpenAccess W3211282104 @default.
- W3211282104 hasPrimaryLocation W32112821041 @default.
- W3211282104 hasRelatedWork W2961085424 @default.
- W3211282104 hasRelatedWork W3046775127 @default.
- W3211282104 hasRelatedWork W3170094116 @default.
- W3211282104 hasRelatedWork W4205958290 @default.
- W3211282104 hasRelatedWork W4285260836 @default.
- W3211282104 hasRelatedWork W4286629047 @default.
- W3211282104 hasRelatedWork W4306321456 @default.
- W3211282104 hasRelatedWork W4306674287 @default.
- W3211282104 hasRelatedWork W4386462264 @default.
- W3211282104 hasRelatedWork W4224009465 @default.
- W3211282104 hasVolume "21" @default.
- W3211282104 isParatext "false" @default.
- W3211282104 isRetracted "false" @default.