评估18个脑瘤分割模型在648名患者中的公平性，发现患者特征比模型架构更能影响性能。
Fairboard: a quantitative framework for equity assessment of healthcare models
- 从多维角度量化医疗模型在不同患者群体中的表现差异
- 临床因素如分子诊断和肿瘤分级对分割精度预测力更强
- 开源工具Fairboard助力非技术团队监测模型公平性
尽管已有超过1000个经FDA批准的AI医疗设备，但正式的公平性评估仍极为罕见。本文评估了18个开源脑瘤分割模型在两个独立数据集共648名胶质瘤患者中的公平性（总计11,664次模型推断），覆盖单变量、贝叶斯多变量、空间和表征维度。结果发现，患者身份解释的性能方差大于模型选择，临床因素（包括分子诊断、肿瘤分级和切除程度）对分割准确性的预测力强于模型架构。基于体素的空间元分析揭示了神经解剖定位的偏见，这些偏见具有区域特异性但跨模型具有一致性。在高维病变掩码与临床人口学特征的潜在空间中，模型性能显著聚类，表明患者特征空间存在算法脆弱轴线。尽管较新模型更趋公平，但均未提供形式化公平保障。最后，我们发布了Fairboard，一个开源、无需代码的仪表板，降低医疗影像中公平性监控的技术门槛。
原文摘要 · Abstract (English)
Despite there now being more than 1,000 FDA-authorised AI medical devices, formal equity assessments -- whether model performance is uniform across patient subgroups -- are rare. Here, we evaluate the equity of 18 open-source brain tumour segmentation models across 648 glioma patients from two independent datasets (n = 11,664 model inferences) along distinct univariate, Bayesian multivariate, spatial, and representational dimensions. We find that patient identity consistently explains more performance variance than model choice, with clinical factors, including molecular diagnosis, tumour grade, and extent of resection, predicting segmentation accuracy more strongly than model architecture. A voxel-wise spatial meta-analysis identifies neuroanatomically localised biases that are compartment-specific yet often consistent across models. Within a high-dimensional latent space of lesion masks and clinic-demographic features, model performance clusters significantly, indicating that the patient feature space contains axes of algorithmic vulnerability. Although newer models tend toward greater equity, none provide a formal fairness guarantee. Lastly, we release Fairboard, an open-source, no-code dashboard that lowers barriers to equitable model monitoring in medical imaging.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。