FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283162970> ?p ?o ?g. }

• W4283162970 abstract "A growing body of work uses the paradigm of algorithmic fairness to frame the development of techniques to anticipate and proactively mitigate the introduction or exacerbation of health inequities that may follow from the use of model-guided decision-making. We evaluate the interplay between measures of model performance, fairness, and the expected utility of decision-making to offer practical recommendations for the operationalization of algorithmic fairness principles for the development and evaluation of predictive models in healthcare. We conduct an empirical case-study via development of models to estimate the ten-year risk of atherosclerotic cardiovascular disease to inform statin initiation in accordance with clinical practice guidelines. We demonstrate that approaches that incorporate fairness considerations into the model training objective typically do not improve model performance or confer greater net benefit for any of the studied patient populations compared to the use of standard learning paradigms followed by threshold selection concordant with patient preferences, evidence of intervention effectiveness, and model calibration. These results hold when the measured outcomes are not subject to differential measurement error across patient populations and threshold selection is unconstrained, regardless of whether differences in model performance metrics, such as in true and false positive error rates, are present. In closing, we argue for focusing model development efforts on developing calibrated models that predict outcomes well for all patient populations while emphasizing that such efforts are complementary to transparent reporting, participatory design, and reasoning about the impact of model-informed interventions in context." @default.
• W4283162970 created "2022-06-21" @default.
• W4283162970 creator A5034194687 @default.
• W4283162970 creator A5041175834 @default.
• W4283162970 creator A5048202246 @default.
• W4283162970 creator A5065839612 @default.
• W4283162970 creator A5069992937 @default.
• W4283162970 creator A5070470494 @default.
• W4283162970 date "2022-06-20" @default.
• W4283162970 modified "2023-10-06" @default.
• W4283162970 title "Net benefit, calibration, threshold selection, and training objectives for algorithmic fairness in healthcare" @default.
• W4283162970 cites W1484551447 @default.
• W4283162970 cites W1711352584 @default.
• W4283162970 cites W1761502526 @default.
• W4283162970 cites W1987318190 @default.
• W4283162970 cites W1996457987 @default.
• W4283162970 cites W2014164843 @default.
• W4283162970 cites W2015185375 @default.
• W4283162970 cites W2045030989 @default.
• W4283162970 cites W2082174016 @default.
• W4283162970 cites W2116666691 @default.
• W4283162970 cites W2121568629 @default.
• W4283162970 cites W2146719470 @default.
• W4283162970 cites W2160812379 @default.
• W4283162970 cites W2346445964 @default.
• W4283162970 cites W2460699727 @default.
• W4283162970 cites W2584805976 @default.
• W4283162970 cites W2604748569 @default.
• W4283162970 cites W2799695199 @default.
• W4283162970 cites W2805499342 @default.
• W4283162970 cites W2899921784 @default.
• W4283162970 cites W2900130109 @default.
• W4283162970 cites W2902054973 @default.
• W4283162970 cites W2954707123 @default.
• W4283162970 cites W2963189767 @default.
• W4283162970 cites W2981330642 @default.
• W4283162970 cites W2981991941 @default.
• W4283162970 cites W2996753114 @default.
• W4283162970 cites W2997398218 @default.
• W4283162970 cites W3005196550 @default.
• W4283162970 cites W3006057482 @default.
• W4283162970 cites W3023069697 @default.
• W4283162970 cites W3025479223 @default.
• W4283162970 cites W3040416015 @default.
• W4283162970 cites W3043023066 @default.
• W4283162970 cites W3100279624 @default.
• W4283162970 cites W3107969206 @default.
• W4283162970 cites W3110181119 @default.
• W4283162970 cites W3117058671 @default.
• W4283162970 cites W3125789530 @default.
• W4283162970 cites W3133874049 @default.
• W4283162970 cites W3172996796 @default.
• W4283162970 cites W3185350140 @default.
• W4283162970 cites W34678172 @default.
• W4283162970 cites W4221031345 @default.
• W4283162970 doi "https://doi.org/10.1145/3531146.3533166" @default.
• W4283162970 hasPublicationYear "2022" @default.
• W4283162970 type Work @default.
• W4283162970 citedByCount "6" @default.
• W4283162970 countsByYear W42831629702022 @default.
• W4283162970 countsByYear W42831629702023 @default.
• W4283162970 crossrefType "proceedings-article" @default.
• W4283162970 hasAuthorship W4283162970A5034194687 @default.
• W4283162970 hasAuthorship W4283162970A5041175834 @default.
• W4283162970 hasAuthorship W4283162970A5048202246 @default.
• W4283162970 hasAuthorship W4283162970A5065839612 @default.
• W4283162970 hasAuthorship W4283162970A5069992937 @default.
• W4283162970 hasAuthorship W4283162970A5070470494 @default.
• W4283162970 hasBestOaLocation W42831629702 @default.
• W4283162970 hasConcept C111472728 @default.
• W4283162970 hasConcept C112930515 @default.
• W4283162970 hasConcept C118552586 @default.
• W4283162970 hasConcept C119857082 @default.
• W4283162970 hasConcept C138885662 @default.
• W4283162970 hasConcept C151730666 @default.
• W4283162970 hasConcept C154945302 @default.
• W4283162970 hasConcept C160735492 @default.
• W4283162970 hasConcept C162324750 @default.
• W4283162970 hasConcept C27415008 @default.
• W4283162970 hasConcept C2776436953 @default.
• W4283162970 hasConcept C2779343474 @default.
• W4283162970 hasConcept C41008148 @default.
• W4283162970 hasConcept C50522688 @default.
• W4283162970 hasConcept C539667460 @default.
• W4283162970 hasConcept C71924100 @default.
• W4283162970 hasConcept C81917197 @default.
• W4283162970 hasConcept C86803240 @default.
• W4283162970 hasConcept C9354725 @default.
• W4283162970 hasConceptScore W4283162970C111472728 @default.
• W4283162970 hasConceptScore W4283162970C112930515 @default.
• W4283162970 hasConceptScore W4283162970C118552586 @default.
• W4283162970 hasConceptScore W4283162970C119857082 @default.
• W4283162970 hasConceptScore W4283162970C138885662 @default.
• W4283162970 hasConceptScore W4283162970C151730666 @default.
• W4283162970 hasConceptScore W4283162970C154945302 @default.
• W4283162970 hasConceptScore W4283162970C160735492 @default.
• W4283162970 hasConceptScore W4283162970C162324750 @default.
• W4283162970 hasConceptScore W4283162970C27415008 @default.
• W4283162970 hasConceptScore W4283162970C2776436953 @default.
• W4283162970 hasConceptScore W4283162970C2779343474 @default.

• next