English(EN) When Annotation Patterns Are Learned: Skin-Tone Dependence in Dermatology Concepts

皮肤病学AI模型对深色皮肤色调存在偏见

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

一项发表在arXiv上的新研究强调了皮肤病学概念数据集中存在的显著的肤色偏见，特别是广泛使用的SkinCon数据集。研究发现，与浅色皮肤相比，在深色皮肤上，作为皮肤炎症关键指标的红斑的注释频率较低，比值比为0.17。相反，色素沉着和色素减退在深色皮肤上的注释频率更高。这种依赖于肤调的注释模式会被概念瓶颈模型学习到，可能导致模型同意遗漏而非纠正的诊断错误。研究表明，在依赖使用这些数据集训练的AI模型进行临床解释之前，必须对概念注释进行亚组偏见审计。 AI

影响强调了在AI训练数据中进行偏见审计的至关重要性，以确保在不同人群中的公平表现。

排序理由发表在arXiv上的研究论文，详细介绍了皮肤病学数据集中的偏见。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 发表在arXiv上的研究论文，详细介绍了皮肤病学数据集中的偏见。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Y. Li, M. Bigliardi-Qi, S. Bedros, P. Bigliardi, N. Papanikolopoulos · 2026-10-23 04:00

When Annotation Patterns Are Learned: Skin-Tone Dependence in Dermatology Concepts

arXiv:2610.30901v1 Announce Type: new Abstract: Concept bottleneck models (CBMs) let clinicians inspect and correct skin disease diagnoses through clinical concepts, but only if the concept annotations are reliable. We therefore audit the reliability of SkinCon, a widely used der…

本文如何被排名

报道来源 [1]

When Annotation Patterns Are Learned: Skin-Tone Dependence in Dermatology Concepts

相关实体

相关话题