PerspectiveBIOMEDICAL POLICY

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

See allHide authors and affiliations

Science Translational Medicine  24 Mar 2021:
Vol. 13, Issue 586, eabb1655
DOI: 10.1126/scitranslmed.abb1655

You are currently viewing the abstract.

View Full Text

Log in to view the full text

Log in through your institution

Log in through your institution

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.

View Full Text

Stay Connected to Science Translational Medicine