MOABB: Trustworthy algorithm benchmarking for BCIs
This addresses reproducibility and benchmarking issues for researchers and developers in the brain-computer interface (BCI) field, though it is incremental as it builds on existing tools like MNE and scikit-learn.
The authors tackled the problems of small sample sizes and lack of reproducibility in BCI algorithm development by creating MOABB, an open-source software suite that streamlines data preprocessing and provides a consistent interface for machine learning methods. Their analysis of state-of-the-art decoding algorithms across 12 datasets with over 250 subjects showed that identical pipelines yield very different results across datasets, and many previously validated methods fail when applied broadly.
BCI algorithm development has long been hampered by two major issues: small sample sets and a lack of reproducibility. We offer a solution to both of these problems via a software suite that streamlines both the issues of finding and preprocessing data in a reliable manner, as well as that of using a consistent interface for machine learning methods. By building on recent advances in software for signal analysis implemented in the MNE toolkit, and the unified framework for machine learning offered by the scikit-learn project, we offer a system that can improve BCI algorithm development. This system is fully open-source under the BSD licence and available at https://github.com/NeuroTechX/moabb. To validate our efforts, we analyze a set of state-of-the-art decoding algorithms across 12 open access datasets, with over 250 subjects. Our analysis confirms that different datasets can result in very different results for identical processing pipelines, highlighting the need for trustworthy algorithm benchmarking in the field of BCIs, and further that many previously validated methods do not hold up when applied across different datasets, which has wide-reaching implications for practical BCIs.