Researchers have developed ECGLight, a lightweight, on-device framework designed to digitize paper electrocardiogram (ECG) printouts and screen for myocardial infarction (MI). This system can convert a smartphone photo of a paper ECG into a calibrated 12-lead signal and identify MI pathologies with high accuracy. ECGLight runs on CPU-only resources in under 30 seconds per ECG, making it suitable for remote clinics with limited connectivity and computational power. The framework also incorporates Shapley Additive Explanations (SHAP) for interpretability. AI
IMPACT Enables remote clinics to leverage AI for cardiovascular disease screening using legacy paper records.
RANK_REASON The item describes a new framework presented in an arXiv paper for ECG digitization and screening. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
