导致放射学偏见的"捷径" 人工智能:原因,评估和缓解
Imon Banerjee1, Kamanasish Bhattacharjee2, John L Burns3
1Department of Radiology, Mayo Clinic, Scottsdale, Arizona; School of Computing and Augmented Intelligence, Arizona State University, Tempe, Arizona.
Journal of the American College of Radiology : JACR
|July 28, 2023
概括
医学中的人工智能 (AI) 模型可能会因为"捷径学习"而失败,使用无关的图像特征并导致对某些患者群体的偏见. 解决这种偏见对于公平的AI部署至关重要.
科学领域:
- 医学成像人工智能 医学成像人工智能
- 算法公平性 算法公平性
- 医疗保健技术 技术 医疗保健 技术
背景情况:
- 人工智能模型在医学成像方面取得了专业的表现,但在现实世界中表现出失败.
- 人工智能模型中的偏见导致各种患者子组的不同结果,限制了临床效用.
- 人工智能模型可以利用虚假的相关性 (捷径学习) 而不是真正的病理学来进行预测.
研究的目的:
- 审查人工智能的偏见类型,从人工智能开发管道的捷径学习到人工智能开发管道.
- 总结医学AI中偏见评估和缓解的工具包.
- 讨论当前的偏见缓解技术和需要多样化的研究团队.
主要方法:
- 对人工智能偏见文献的审查,专注于医学成像中的快捷方式学习.
- 将偏差分类为数据,建模和推理偏差.
- 现有的偏见评估和缓解工具包和技术的摘要.
主要成果:
- 人工智能模型通过检测受保护的属性 (年龄,性别,种族) 来表现出偏见,并且在服务不足的子组中表现更差.
- 使用非病理特征的捷径学习是人工智能偏差的一个关键机制.
- 偏差可以发生在数据,建模和推断阶段;现有的缓解工具需要医学AI评估.
结论:
- 了解和减轻来自捷径学习的偏见对于医疗保健中的公平人工智能至关重要.
- 预处理,计算和后处理方法可以解决AI偏差.
- 未来的努力需要多元化的团队来解决整个AI管道,并遵守不断变化的法律标准.
相关概念视频
01:29Bias in Epidemiological Studies
356
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:
356
01:29Issues And Trends In Healthcare Delivery System
5.7K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
5.7K
01:22Bias
4.3K
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...
4.3K
01:08The Availability Heuristic
6.0K
A heuristic is a general problem-solving framework (Tversky & Kahneman, 1974). You can think of these as mental shortcuts that are used to solve problems. Different types of heuristics are used in different types of situations, and the impulse to use a heuristic occurs when one of five conditions is met (Pratkanis, 1989):
6.0K