Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320560900> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4320560900 abstract "Auditing machine learning-based (ML) healthcare tools for bias is critical to preventing patient harm, especially in communities that disproportionately face health inequities. General frameworks are becoming increasingly available to measure ML fairness gaps between groups. However, ML for health (ML4H) auditing principles call for a contextual, patient-centered approach to model assessment. Therefore, ML auditing tools must be (1) better aligned with ML4H auditing principles and (2) able to illuminate and characterize communities vulnerable to the most harm. To address this gap, we propose supplementing ML4H auditing frameworks with SLOGAN (patient Severity-based LOcal Group biAs detectioN), an automatic tool for capturing local biases in a clinical prediction task. SLOGAN adapts an existing tool, LOGAN (LOcal Group biAs detectioN), by contextualizing group bias detection in patient illness severity and past medical history. We investigate and compare SLOGAN's bias detection capabilities to LOGAN and other clustering techniques across patient subgroups in the MIMIC-III dataset. On average, SLOGAN identifies larger fairness disparities in over 75% of patient groups than LOGAN while maintaining clustering quality. Furthermore, in a diabetes case study, health disparity literature corroborates the characterizations of the most biased clusters identified by SLOGAN. Our results contribute to the broader discussion of how machine learning biases may perpetuate existing healthcare disparities." @default.
- W4320560900 created "2023-02-15" @default.
- W4320560900 creator A5064234845 @default.
- W4320560900 creator A5066282713 @default.
- W4320560900 creator A5078132977 @default.
- W4320560900 creator A5087096372 @default.
- W4320560900 creator A5090145147 @default.
- W4320560900 date "2022-11-16" @default.
- W4320560900 modified "2023-09-28" @default.
- W4320560900 title "Auditing Algorithmic Fairness in Machine Learning for Health with Severity-Based LOGAN" @default.
- W4320560900 doi "https://doi.org/10.48550/arxiv.2211.08742" @default.
- W4320560900 hasPublicationYear "2022" @default.
- W4320560900 type Work @default.
- W4320560900 citedByCount "0" @default.
- W4320560900 crossrefType "posted-content" @default.
- W4320560900 hasAuthorship W4320560900A5064234845 @default.
- W4320560900 hasAuthorship W4320560900A5066282713 @default.
- W4320560900 hasAuthorship W4320560900A5078132977 @default.
- W4320560900 hasAuthorship W4320560900A5087096372 @default.
- W4320560900 hasAuthorship W4320560900A5090145147 @default.
- W4320560900 hasBestOaLocation W43205609001 @default.
- W4320560900 hasConcept C111472728 @default.
- W4320560900 hasConcept C119857082 @default.
- W4320560900 hasConcept C121955636 @default.
- W4320560900 hasConcept C138885662 @default.
- W4320560900 hasConcept C144133560 @default.
- W4320560900 hasConcept C154945302 @default.
- W4320560900 hasConcept C15744967 @default.
- W4320560900 hasConcept C160735492 @default.
- W4320560900 hasConcept C17744445 @default.
- W4320560900 hasConcept C199521495 @default.
- W4320560900 hasConcept C199539241 @default.
- W4320560900 hasConcept C2777363581 @default.
- W4320560900 hasConcept C2779530757 @default.
- W4320560900 hasConcept C2780619561 @default.
- W4320560900 hasConcept C41008148 @default.
- W4320560900 hasConcept C71924100 @default.
- W4320560900 hasConcept C73555534 @default.
- W4320560900 hasConcept C77805123 @default.
- W4320560900 hasConcept C94625758 @default.
- W4320560900 hasConceptScore W4320560900C111472728 @default.
- W4320560900 hasConceptScore W4320560900C119857082 @default.
- W4320560900 hasConceptScore W4320560900C121955636 @default.
- W4320560900 hasConceptScore W4320560900C138885662 @default.
- W4320560900 hasConceptScore W4320560900C144133560 @default.
- W4320560900 hasConceptScore W4320560900C154945302 @default.
- W4320560900 hasConceptScore W4320560900C15744967 @default.
- W4320560900 hasConceptScore W4320560900C160735492 @default.
- W4320560900 hasConceptScore W4320560900C17744445 @default.
- W4320560900 hasConceptScore W4320560900C199521495 @default.
- W4320560900 hasConceptScore W4320560900C199539241 @default.
- W4320560900 hasConceptScore W4320560900C2777363581 @default.
- W4320560900 hasConceptScore W4320560900C2779530757 @default.
- W4320560900 hasConceptScore W4320560900C2780619561 @default.
- W4320560900 hasConceptScore W4320560900C41008148 @default.
- W4320560900 hasConceptScore W4320560900C71924100 @default.
- W4320560900 hasConceptScore W4320560900C73555534 @default.
- W4320560900 hasConceptScore W4320560900C77805123 @default.
- W4320560900 hasConceptScore W4320560900C94625758 @default.
- W4320560900 hasLocation W43205609001 @default.
- W4320560900 hasOpenAccess W4320560900 @default.
- W4320560900 hasPrimaryLocation W43205609001 @default.
- W4320560900 hasRelatedWork W1999627569 @default.
- W4320560900 hasRelatedWork W2748952813 @default.
- W4320560900 hasRelatedWork W2899084033 @default.
- W4320560900 hasRelatedWork W2961085424 @default.
- W4320560900 hasRelatedWork W3046775127 @default.
- W4320560900 hasRelatedWork W4286629047 @default.
- W4320560900 hasRelatedWork W4306321456 @default.
- W4320560900 hasRelatedWork W4306674287 @default.
- W4320560900 hasRelatedWork W763609066 @default.
- W4320560900 hasRelatedWork W4224009465 @default.
- W4320560900 isParatext "false" @default.
- W4320560900 isRetracted "false" @default.
- W4320560900 workType "article" @default.