Reproducibility in machine learning for health research: Still a ways to go.
Where this comes from
- Record sourced from PubMed, PMID 33762434.
- Also identified by DOI 10.1126/scitranslmed.abb1655 and PMC identifier 12862614.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
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.
Medical subject headings
- Machine Learning