评估和改进用于COVID-19严重程度分类的算法公平性,使用基于可解释的人工智能的偏差缓解
Shayan Nejadshamsi1,2,3, Charlene H Chu4,5, Katherine S McGilton4,5
1Mila-Quebec AI Institute, Montreal, QC H2S 3H1, Canada.
JAMIA open
|January 12, 2026
概括
这项研究开发了一种可解释的AI (XAI) 方法,以减少COVID-19严重性预测模型中的性别偏见. XAI方法提高了公平性,但没有显著影响模型的准确性,确保老年人获得公平的医疗保健.
科学领域:
- 医疗信息学 医疗信息学
- 医疗保健中的人工智能
- 健康 公平 卫生 公平
背景情况:
- 机器学习 (ML) 模型越来越多地用于预测COVID-19的严重程度,这对于临床决策和资源分配至关重要.
- 确保ML预测的公平性至关重要,以防止医疗保健差距,特别是关于基于性别的偏见.
- 现有的公平干预措施往往会降低模型的准确性,限制临床适用性.
研究的目的:
- 在基于ML的COVID-19严重程度分类模型中评估公平性.
- 提出并评估基于可解释AI (XAI) 的策略,以缓解与性别相关的偏见.
- 在临床决策支持系统中实现预测准确性和公平性之间的平衡.
主要方法:
- 使用北克生物库数据开发了一个XGBoost多类分类模型.
- 使用子集精度平价差异 (SAPD) 和标签明智的机会平等差异 (LEOD) 指标评估公平性.
- 实施并比较了四种偏差缓解策略,包括使用SHAPley添加式扩展 (SHAP) 的基于XAI的方法.
主要成果:
- 基线模型实现了90.68%的准确性,但显示了10.11%的基组准确性性别差异差异.
- 与其他策略相比,基于XAI的方法显示了性能和公平性之间的优越权衡.
- 识别和整合性敏感特征相互作用到模型再培训使用SHAP值.
结论:
- 基于XAI的偏见缓解有效地减少了COVID-19严重程度预测中的基于性别的差异.
- 与传统的公平干预相比,这种方法最大限度地减少了准确性损失.
- 为开发公平,准确的临床决策支持系统提供框架,为老年人提供公平的护理.
相关概念视频
Classification of Illness
8.5K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
8.5K
Bias
7.2K
Bias refers to any tendency that prevents a question from being considered unprejudiced. In research, bias occurs when one outcome or answer is selected or encouraged over others in sampling or testing. Bias can occur during any research phase, including study design, data collection, analysis, and publication.
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
7.2K
Strategies for Assessing and Addressing Confounding
349
Confounding is a critical issue in epidemiological studies, often leading to misleading conclusions about associations between exposures and outcomes. It occurs when the relationship between the exposure and the outcome is mixed with the effects of other factors that influence the outcome. Given that, addressing confounding is of high importance for drawing accurate inferences in research.
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
349
Bias in Epidemiological Studies
1.3K
Biases can arise at various stages of research, from study design and data collection to analysis and interpretation. Recognizing and addressing these biases is essential to ensure the validity and reliability of epidemiological findings.Broadly speaking, biases in epidemiology fall into three main categories: selection bias, information bias, and confounding. A more detailed description of possible biases is:
1.3K

