Reproduce “Explainable Cross-Disease Reasoning for Cardiovascular Risk Assessment from Low-Dose Computed Tomography” 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

Yifei Zhang, Jiashuo Zhang, Mojtaba Safari, Xiaofeng Yang, Liang Zhao

The authors develop a model combining lung findings, cardiac features, and lung-cancer risk to estimate cardiovascular risk from low-dose chest CT. A retrieval-grounded module links pulmonary findings to possible cardiopulmonary mechanisms; its rationale is an intermediate input, not a diagnosis. In NLST, ResNet-50 achieved screening AUC 0.919 versus 0.892 for M3FM; this result is limited to the evaluated cohort.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.