神经影像学数据分析中的可重复性和可复制性。
Reproducibility and replicability in neuroimaging data analysis.
机构信息
Department of CSEE, University of Maryland, Baltimore County, Baltimore, Maryland.
Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, Georgia, USA.
出版信息
Curr Opin Neurol. 2022 Aug 1;35(4):475-481. doi: 10.1097/WCO.0000000000001081.
PURPOSE OF REVIEW
Machine learning solutions are being increasingly used in the analysis of neuroimaging (NI) data, and as a result, there is an increase in the emphasis of the reproducibility and replicability of these data-driven solutions. Although this is a very positive trend, related terminology is often not properly defined, and more importantly, (computational) reproducibility that refers to obtaining consistent results using the same data and the same code is often disregarded.
RECENT FINDINGS
We review the findings of a recent paper on the topic along with other relevant literature, and present two examples that demonstrate the importance of accounting for reproducibility in widely used software for NI data.
SUMMARY
We note that reproducibility should be a first step in all NI data analyses including those focusing on replicability, and introduce available solutions for assessing reproducibility. We add the cautionary remark that when not taken into account, lack of reproducibility can significantly bias all subsequent analysis stages.
目的综述
机器学习解决方案越来越多地被应用于神经影像学（NI）数据的分析，因此，这些数据驱动解决方案的可重复性和可复制性受到了越来越多的重视。尽管这是一个非常积极的趋势，但相关术语通常没有得到正确定义，更重要的是，（计算）可重复性，即使用相同的数据和相同的代码获得一致的结果，往往被忽视。
最近的发现
我们回顾了一篇关于该主题的最新论文的发现以及其他相关文献，并提出了两个例子，说明了在广泛使用的 NI 数据软件中考虑可重复性的重要性。
总结
我们注意到，可重复性应该是包括关注可复制性的所有 NI 数据分析的第一步，并介绍了评估可重复性的可用解决方案。我们补充了一个警告，即如果不考虑可重复性，缺乏可重复性会严重影响所有后续的分析阶段。
Zotero 插件