Reproducibility in machine learning for health research: Still a ways to go

Science Translational Medicine
17 March 2021 Vol 13, Issue 585
https://stm.sciencemag.org/

 

Perspective
Reproducibility in machine learning for health research: Still a ways to go
By Matthew B. A. McDermott, Shirly Wang, Nikki Marinsek, Rajesh Ranganath, Luca Foschini, Marzyeh Ghassemi
Science Translational Medicine24 Mar 2021 Restricted Access
Abstract
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.