Reproduce “ECGJev: Question-Conditioned Option Scoring for 12-Lead ECG Interpretation” 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

Zhuoyuan Li, Xidong Wu, Hanyu Cui, Jiansong Gao, Rongrong Fu, Mingke Yan, Haotian Tang

ECGJev turns targeted twelve-lead ECG questions into scored choices by compressing waveform and spectrogram features into question-conditioned tokens and scoring True and False options with a pretrained decision decoder. On CPSC2018 it reaches macro-F1 of 80.46 ± 0.67%, compared with Q-Heart’s 76.06 ± 1.07%. It leads three benchmark datasets but not small-sample PTB, where xECG scores higher.

Summary by alphaXiv.

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