人工智能算法在胸部X线检查中对服务不足患者群体的漏诊偏倚
研究分析三个大型胸部X线数据集及一个多源数据集,评估AI病理分类算法在女性、黑人、低社会经济地位等服务不足人群中的漏诊情况。结果显示,先进计算机视觉分类器一致且选择性地对服务不足人群漏诊,交叉弱势亚群(如西班牙裔女性患者)漏诊率更高,可能加剧现有医疗偏倚和不平等。
要点
- AI胸部X线分类器对服务不足人群一致且选择性地漏诊。
- 交叉弱势亚群(如西班牙裔女性患者)漏诊率更高。
- 此类偏倚可能加剧现有医疗偏倚并导致治疗可及性不平等。
核心结论
- 使用先进计算机视觉技术产生的分类器一致且选择性地对服务不足患者群体漏诊,交叉弱势亚群漏诊率更高。
研究设计与样本
- 分析三个大型胸部X线数据集及一个多源数据集,评估AI算法在胸部X线病理分类中的漏诊表现。
主要发现
- 分类器对服务不足患者群体一致且选择性地漏诊,交叉弱势亚群(如西班牙裔女性患者)漏诊率更高。
临床怎么用
- 作者指出,使用此类存在偏倚的AI系统进行医学影像疾病诊断,可能加剧现有医疗偏倚并导致治疗可及性不平等,引发临床使用的伦理担忧。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
Artificial intelligence (AI) systems have increasingly achieved expert-level performance in medical imaging applications. However, there is growing concern that such AI systems may reflect and amplify human bias, and reduce the quality of their performance in historically under-served populations such as female patients, Black patients, or patients of low socioeconomic status. Such biases are especially troubling in the context of underdiagnosis, whereby the AI algorithm would inaccurately label an individual with a disease as healthy, potentially delaying access to care. Here, we examine algorithmic underdiagnosis in chest X-ray pathology classification across three large chest X-ray datasets, as well as one multi-source dataset. We find that classifiers produced using state-of-the-art computer vision techniques consistently and selectively underdiagnosed under-served patient populations and that the underdiagnosis rate was higher for intersectional under-served subpopulations, for example, Hispanic female patients. Deployment of AI systems using medical imaging for disease diagnosis with such biases risks exacerbation of existing care biases and can potentially lead to unequal access to medical treatment, thereby raising ethical concerns for the use of these models in the clinic.
引用
- Seyyed-Kalantari L, Zhang H, McDermott MBA, et al. Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations. Nat Med. 2021. PMID: 34893776. doi:10.1038/s41591-021-01595-0
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。