Reproduce “Foundation Artificial Intelligence Models for Health Recognition Using Face Photographs (FAHR-Face)” 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
Fridolin Haugg, Grace Lee, John He, Leonard Nürnberg, Dennis Bontempi, Danielle S. Bitterman, Paul Catalano, Vasco Prudente and 9 more
FAHR-Face learns from more than 40 million unlabeled facial images, then adapts to estimate age-relative appearance and survival risk. In cancer radiotherapy cohorts, the biomarkers separated survival groups; in the Harvard cohort, estimates at five years ranged from 78.1% to 17.7% across risk quartiles. Both remained associated with survival together in Maastro, but broader validation and prospective trials are needed.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.