Back

Are AI-generated electrocardiograms clinically accurate? Benchmarking accuracy of AI-generated ECGs: a multiplatform performance study of public LLMs

22 November 2025 (09:30 - 10:15)
Organised by: Logo
Congress Presentation Part of: Advances in synthetic data and genAI Electrocardiogram (ECG) and Arrhythmia Analysis Open Access ESC Digital & AI Summit 2025 European Society of Cardiology

About the speaker

Photo
Doctor Harish Kamalanathan

Prince of Wales hospital, Sydney (Australia)

6 More presentations in this session

Presentation thumbnail
Beyond visual realism: assessing coronary artery dominance diversity in Al-generated synthetic coronary computed tomography angiography images
Mr M. Seyfarth (Heidelberg, DE)
Abstract Slides
Presentation thumbnail
CardioSynth: privacy-preserving generation and evaluation of multimodal synthetic data for cardiovascular research
Mr K. Kechagias (Marousi, GR) Mr M. Miranda (IT)
Abstract Slides
Presentation thumbnail
Latent diffusion for single-pass full 4D cine cardiac magnetic resonance imaging synthesis with spatiotemporal autoencoding
Mr M. Seyfarth (Heidelberg, DE)
Abstract Slides
Presentation thumbnail
Synthetic data integration in cardiovascular research: enhancing analysis accuracy and data privacy with EPICOSAI
Professor A. Kanik (Houston, US)
Abstract Slides
Presentation thumbnail
Generative counterfactual framework for explainable artificial intelligence-ECG predictions
Doctor M. Lee (Seoul, KR)
Abstract Slides

Access the full session

Session thumbnail
Advances in synthetic data and genAI

The Event

Event poster

ESC Digital & AI Summit 2025

22 November 2025 09:30 CET
You may be interested in
thumbnail
Congress Session
Why signal quality matters? The importance of ECG and intracardiac signal quality to empower emerging AI technologies
thumbnail
Congress Session
Evolutions in arrythmia and syncope management
thumbnail
Congress Session
Artificial intelligence in arrhythmia care: good news for EPeeps?

ESC 365 is supported by

novartis Explore sponsored resources

ESC 365 is supported by

novartis Explore sponsored resources