Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
Department of Computer Science, University of Toronto, Toronto, ON M5T 3A1, Canada.
Sci Transl Med. 2021 Mar 24;13(586). doi: 10.1126/scitranslmed.abb1655.
Machine learning for health must be reproducible to ensure reliable clinical use. We evaluated 511 scientific papers across several machine learning subfields and found that machine learning for health compared poorly to other areas regarding reproducibility metrics, such as dataset and code accessibility. We propose recommendations to address this problem.
机器学习在医疗领域的应用必须是可重复的，以确保其在临床应用中的可靠性。我们评估了机器学习的 511 篇科学论文，发现与其他领域相比，机器学习在医疗领域的可重复性指标（如数据集和代码的可访问性）方面表现较差。我们提出了一些建议来解决这个问题。
