ECGLight Compute-Light Framework For Paper ECG Digitization and Myocardial Infarction Screening

Q: What problem does ECGLight address in remote or low-resource clinics?

It targets the inability of many legacy paper ECGs to be analyzed by AI decision support due to limited connectivity and computing resources.

Q: How does ECGLight process paper ECG inputs?

It converts a smartphone photo or scan of a paper ECG into a calibrated 12-lead signal using an end-to-end lightweight on-device digitization-to-diagnosis pipeline.

Q: How is interpretability handled and what performance is reported?

SHAP is used to support interpretability. The system runs in under 30 seconds per ECG on CPU-only hardware, reporting strong accuracy for MI detection on PTB-XL and OMI detection on ECG-Matrix.

Jul 16, 2026

Upload by Clementine

ECGLight presents a compute-light, on-device pipeline to convert smartphone photos or scans of paper ECGs into calibrated 12-lead signals and screen for myocardial infarction (MI) pathologies. The system pairs end-to-end lightweight digitization with interpretability via SHapley Additive exPlanations (SHAP), enabling clinicians to understand model decisions. Trained and evaluated on 21,799 ECGs from PTB-XL and validated on the hospital-acquired ECG-Matrix dataset, it achieves sub-30-second CPU-only inference and strong MI and OMI detection performance.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages26

Reading Time1 h 6 min

Introduction

Clinical context and need for early ACS/MI detection

Limitations of legacy paper ECGs in remote settings

ECG as a diagnostic signal and MI/OMI waveform markers

ECGLight: Compute-Light Framework For Paper ECG Digitization and Myocardial Infarction Screening Shreyasvi Natraj 1 ,2∗, Cyrus Achtari 1 ,2 , Felice Gragnano3 , Andrea Milzi4 , Marco Valgimigli4 , and Diego Paez-Granados 1 ,2∗ arXiv :2607 .07683v 1 [ cs .LG] 8 Jul 2026 Abstract—Electrocardiography (ECG) is one of the most widely used tests for diagnosing cardiovascular disease. Yet several remote clinics still utilize paper ECG printouts for their analysis due to limited connectivity and computational capacity. As a result, vast numbers of physical ECGs obtained in remote areas still remain incapable of being accessed by contemporary artificial-intelligence (AI)–based decision support as they require high computational resources or strong high-speed internet connectivity. This causes several cases where conditions like acute coronary occlusion (ACS) is overlooked and reperfusion therapy delayed. Although prior work has tackled digitization and diagnosis separately, and utilized advanced AI models for them, there still remains a lack of a compute-light, on-device framework that reconstructs paper ECGs at high fidelity, while accurately supporting multiple clinically relevant endpoints. We address this need with an end-to-end lightweight on-device digitization-todiagnosis pipeline that converts a smartphone photo or scan of a paper ECG into a calibrated 12-lead signal and screens for Myocardial Infarction (MI) pathologies, with SHapley Additive exPlanations (SHAP) to support interpretability. Trained and evaluated on 21,799 ECGs from the PTB-XL dataset and further validated on hospital-acquired ECG-Matrix dataset, the complete system runs in <30 s per ECG on CPU-only resources, achieving 95.51% accuracy (F1 = 0.9519) for MI detection on PTB-XL and 88.89% accuracy (F1 = 0.8862) for OMI detection on ECG-Matrix. This work showcases that legacy paper records can be reliably democratized in any part of the world, providing a scalable decision support when digital ECG export, connectivity, or high-end compute are unavailable Index Terms—Electrocardiography, YOLO, offline inference, CPU-only deployment, edge AI, time-series classification, myocardial infarction detection, acute coronary syndrome, ECG-Matrix, PTB-XL, PhysioNet Challenge I. INTRODUCTION Cardiovascular diseases (CVDs), particularly Acute Coronary Syndromes (ACS), remain the leading cause of mortality worldwide, accounting for approximately 33% of all deaths, or nearly 20 million fatalities annually[1], [2] . Within the broad spectrum of CVDs, ACS encompassing unstable angina as well as ST-elevation and non–ST-elevation myocardial infarction, represent some of the most prevalent and lifethreatening clinical manifestations, affecting roughly one in five individuals globally. Given the immense clinical and socioeconomic burden associated with CVDs and ACS, there 1 Spinal Cord and Artificial Intelligence (SCAI) Lab, ETH Zürich, Zürich, Switzerland 2 Swiss Paraplegic Research, Nottwil, Luzern, Switzerland 3Department of Translational Medical Sciences, University of Campania“Luigi Vanvitelli”, Naples, Italy 4Department of Biomedical Sciences, University of Italian Switzerland, Cardiocentro Ticino Institute, Lugano, Switzerland ∗ Corresponding author email: [snatraj@ethz.ch](snatraj@ethz.ch) is a pressing need for advanced diagnostic modalities that enable early detection, continuous monitoring, and timely intervention. In this context, the electrocardiogram (ECG) remains a cornerstone of cardiovascular and ACS diagnostics due to its capacity to non-invasively record the heart’s bioelectrical activity over time [3] . ECG analysis yields critical information about the electrophysiological behavior of the myocardium and supports the detection of a wide range of cardiac pathologies, including arrhythmias, myocardial ischemia or infarction, ACS-related ischemic changes, and structural or conduction abnormalities [4] . Building on this physiological founda

FAQs

What problem does ECGLight address in remote or low-resource clinics?

It targets the inability of many legacy paper ECGs to be analyzed by AI decision support due to limited connectivity and computing resources.

How does ECGLight process paper ECG inputs?

It converts a smartphone photo or scan of a paper ECG into a calibrated 12-lead signal using an end-to-end lightweight on-device digitization-to-diagnosis pipeline.

How is interpretability handled and what performance is reported?

SHAP is used to support interpretability. The system runs in under 30 seconds per ECG on CPU-only hardware, reporting strong accuracy for MI detection on PTB-XL and OMI detection on ECG-Matrix.

Jul 16, 2026

Upload by Clementine