Addressing bias in big data and AI for health care: A call for open science.
Addressing bias in big data and AI for health care: A call for open science.
复制标题
DOI：
10.1016/j.patter.2021.100347
复制
发表时间：
2021-10-08
期刊：
影响因子：
--
通讯作者：
Tzovara A
中科院分区：
文献类型：
--
作者：
Norori N;Hu Q;Aellen FM;Faraci FD;Tzovara A
人工智能（AI）在辅助临床决策和彻底改变医疗保健领域方面具有惊人的潜力。人工智能在融入临床常规之前需要解决的一个主要挑战是算法偏差。大多数人工智能算法都需要大数据集来学习，但有几个人群在现有的生物医学数据集中长期缺席或被歪曲。如果训练数据错误地代表了群体变异性，人工智能就容易强化偏见，这可能导致致命的结果、误诊和缺乏泛化能力。在这里，我们描述了使人工智能算法更公平的挑战，并提出了使用开放科学领域的工具解决偏见的具体步骤。医学领域的偏见可以沿着沿着三个方向进行剖析：数据驱动、算法和人类。医疗保健AI算法的偏见可能会通过传播根深蒂固的社会偏见而产生灾难性的后果。这可能导致误诊某些患者群体，如性别和少数民族，这些患者群体在现有数据集中的代表性不足，进一步放大了不平等。开放科学实践可以帮助医疗保健领域的AI走向公平。其中包括（1）以参与者为中心的人工智能算法和参与式科学的开发;（2）负责任的数据共享和包容性数据标准，以支持互操作性;（3）代码共享，包括共享人工智能算法，可以合成代表性不足的数据，以解决偏见。未来的研究需要专注于制定医疗保健领域的人工智能标准，以实现透明度和数据共享，同时保护患者的隐私。人工智能（AI）在医疗保健革命方面具有惊人的潜力。一个主要的挑战是算法偏差。大多数人工智能算法都需要大数据集来学习，但现有数据集中没有或歪曲了几个人群。因此，人工智能很容易强化偏见，这可能导致致命的结果和误诊。在这里，我们描述了使人工智能算法更公平的挑战，并提出了使用开放科学工具解决偏见的具体步骤。
Artificial intelligence (AI) has an astonishing potential in assisting clinical decision making and revolutionizing the field of health care. A major open challenge that AI will need to address before its integration in the clinical routine is that of algorithmic bias. Most AI algorithms need big datasets to learn from, but several groups of the human population have a long history of being absent or misrepresented in existing biomedical datasets. If the training data is misrepresentative of the population variability, AI is prone to reinforcing bias, which can lead to fatal outcomes, misdiagnoses, and lack of generalization. Here, we describe the challenges in rendering AI algorithms fairer, and we propose concrete steps for addressing bias using tools from the field of open science. Bias in the medical field can be dissected along three directions: data-driven, algorithmic, and human. Bias in AI algorithms for health care can have catastrophic consequences by propagating deeply rooted societal biases. This can result in misdiagnosing certain patient groups, like gender and ethnic minorities, that have a history of being underrepresented in existing datasets, further amplifying inequalities. Open science practices can assist in moving toward fairness in AI for health care. These include (1) participant-centered development of AI algorithms and participatory science; (2) responsible data sharing and inclusive data standards to support interoperability; and (3) code sharing, including sharing of AI algorithms that can synthesize underrepresented data to address bias. Future research needs to focus on developing standards for AI in health care that enable transparency and data sharing, while at the same time preserving patients’ privacy. Artificial intelligence (AI) has an astonishing potential in revolutionizing health care. A major challenge is that of algorithmic bias. Most AI algorithms need big datasets to learn from, but several groups of the human population are absent or misrepresented in existing datasets. AI is thus prone to reinforcing bias, which can lead to fatal outcomes and misdiagnoses. Here, we describe challenges in rendering AI algorithms fairer, and we propose concrete steps for addressing bias using open science tools.
登录
查看更多内容
影响因子：
37.8
作者：
Churchwell, Keith;Elkind, Mitchell S. V.;Williams, Olajide
通讯作者：
Williams, Olajide
影响因子：
8.8
作者：
Bickler, PE;Feiner, JR;Severinghaus, JW
通讯作者：
Severinghaus, JW
影响因子：
1.9
作者：
Esnaola, Nestor F.;Ford, Marvella E.
通讯作者：
Ford, Marvella E.
影响因子：
0.5
作者：
Bolam, Michael R.;Corbett, Lauren E.;Ryszka, Deborah
通讯作者：
Ryszka, Deborah
影响因子：
5.4
作者：
Cornwall, A;Jewkes, R
通讯作者：
Jewkes, R