| Literature DB >> 33762434 |
Matthew B A McDermott1, Shirly Wang2,3, Nikki Marinsek4, Rajesh Ranganath5, Luca Foschini4, Marzyeh Ghassemi2,6,7.
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.Mesh:
Year: 2021 PMID: 33762434 DOI: 10.1126/scitranslmed.abb1655
Source DB: PubMed Journal: Sci Transl Med ISSN: 1946-6234 Impact factor: 17.956