监测重症监护患者死亡率模型的公平性，发现不同人群表现差异。

Monitoring fairness in machine learning models that predict patient mortality in the ICU

• 通过分组分析种族、性别和诊断对模型预测的影响
• 揭示临床记录偏差导致模型在部分群体中表现更差
• 适合关注医疗AI公平性的研究人员与临床开发者

本文提出一种针对重症监护室（ICU）患者死亡率预测模型的公平性监控方法。研究考察了不同种族、性别及疾病诊断患者群体中模型的表现差异。结果表明，临床测量记录中的文档偏差会影响模型公平性，使某些群体的预测准确率显著下降。该分析揭示了传统准确率指标无法反映的深层问题，为医疗人工智能的公平性评估提供了更细致的视角。

原文摘要 · Abstract (English)

This work proposes a fairness monitoring approach for machine learning models that predict patient mortality in the ICU. We investigate how well models perform for patient groups with different race, sex and medical diagnoses. We investigate Documentation bias in clinical measurement, showing how fairness analysis provides a more detailed and insightful comparison of model performance than traditional accuracy metrics alone.

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。