Reproducibility in machine learning for health research: Still a ways to go
Published in
Science Translational Medicine(2021)External Links:
TL
TL;DR
This work 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.
Abstract
Machine learning applied to health falls short on several reproducibility metrics compared to other machine learning subfields. 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.