人工智能在健康与医学中的应用
本文基于为期两年的每周追踪,讨论医学人工智能的关键进展。内容涵盖医学图像分析的前瞻性研究及研究与部署差距的缩小,并探讨非图像数据源、非常规问题构建和人机协作等新研究方向,同时审视从数据稀缺到种族偏见等技术伦理挑战。
要点
- 医学图像分析的前瞻性研究缩小了研究与部署之间的差距。
- 非图像数据源、非常规问题构建和人机协作是新颖医学人工智能研究的有前景途径。
- 数据稀缺和种族偏见等技术伦理挑战若得到解决,人工智能的潜力可能实现。
核心结论
- 随着数据稀缺到种族偏见等挑战得到解决,人工智能的潜力可能实现,使全球患者的医疗保健更准确、高效和可及。
研究设计与样本
- 基于为期两年的每周追踪工作,跟踪并分享医学人工智能的关键进展。
主要发现
- 医学图像分析的前瞻性研究缩小了研究与部署之间的差距。
- 非图像数据源、非常规问题构建和人机协作是有前景的新颖医学人工智能研究途径。
局限性
- 原文未报告局限性
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) is poised to broadly reshape medicine, potentially improving the experiences of both clinicians and patients. We discuss key findings from a 2-year weekly effort to track and share key developments in medical AI. We cover prospective studies and advances in medical image analysis, which have reduced the gap between research and deployment. We also address several promising avenues for novel medical AI research, including non-image data sources, unconventional problem formulations and human-AI collaboration. Finally, we consider serious technical and ethical challenges in issues spanning from data scarcity to racial bias. As these challenges are addressed, AI's potential may be realized, making healthcare more accurate, efficient and accessible for patients worldwide.
引用
- Rajpurkar P, Chen E, Banerjee O, et al. AI in health and medicine. Nat Med. 2022. PMID: 35058619. doi:10.1038/s41591-021-01614-0
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。