Reproduce “Machine learning and AI research for Patient Benefit: 20 Critical Questions on Transparency, Replicability, Ethics and Effectiveness” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sebastian Vollmer, Bilal A. Mateen, Gergo Bohner, Franz J Király, Rayid Ghani, Pall Jonsson, Sarah Cumbers, Adrian Jonas and 10 more
The authors propose 20 questions to guide teams developing or evaluating health-related machine learning and artificial intelligence, from project design through implementation and review. Organized around transparency, replicability, ethics, and effectiveness, the questions address patient benefit, data, evaluation, fairness, and monitoring. An ICU mortality-prediction study illustrates reproducibility concerns, but its cohort differences prevent model comparisons and establish no patient-outcome benefit.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.