Reproducibility in Machine Learning and Healthcare Paper Annotation Datasets

Matthew B. A. McDermott, Wang, Marinsek, Ranganath, Foschini, GhassemiZenodo 2021 · DOI · OpenAlex

Abstract

Paper Annotations for an extended version of https://arxiv.org/abs/1907.01463 Artificial intelligence (AI) and machine learning (ML) for healthcare (ML4H)must be reproducible for reliable clinical use. We evaluate over 200 ML4Hresearch papers and find that health compares poorly to other application areas for AI and ML, particularly concerning data and code accessibility, and propose recommendations for reproducible research
BibTeX
@inproceedings{mcdermott2021reproducibility,
  author = {Matthew B. A. McDermott and Wang and Marinsek and Ranganath and Foschini and Ghassemi},
  title = {{Reproducibility in Machine Learning and Healthcare Paper Annotation Datasets}},
  booktitle = {Zenodo},
  year = {2021},
  doi = {10.5281/zenodo.4574280},
}

Loading related content...

Figure