Researchers have developed ECGLight, a compute-light framework designed to digitize paper electrocardiogram (ECG) printouts and screen for myocardial infarction (MI). This on-device system converts smartphone photos of ECGs into calibrated 12-lead signals, enabling diagnosis even in remote clinics with limited connectivity or computational resources. The framework achieves high accuracy, with 95.51% for MI detection on the PTB-XL dataset and 88.89% for OMI detection on the ECG-Matrix dataset, running in under 30 seconds per ECG on CPU-only resources. AI
IMPACT Enables AI-powered cardiac diagnostics in low-resource settings, democratizing access to critical health information.
RANK_REASON The cluster contains a research paper detailing a new AI framework for medical diagnosis.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
