Reproduce “Facial Foundational Model Advances Early Warning of Coronary Artery Disease from Live Videos with DigitalShadow” 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
Juexiao Zhou, Zhongyi Han, Mankun Xin, Xingwei He, Guotao Wang, Jiaoyan Song, Gongning Luo, Wenjia He and 14 more
DigitalShadow uses live facial video to estimate coronary artery disease (CAD) risk and compare successive scores with a person’s history. It registers a user, processes that person’s face with LiveCAD, and aggregates multiple images. In five-fold cross-validation, AUC rose from 0.82 at image level to 0.87 at patient level; external validation and prospective clinical benefit remain unestablished.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.