Back

Reinforcement learning with GSPO enables vision language model (VLM) to detect structural heart disease from 12-lead electrocardiography

28 August 2026 (13:15 - 14:00)
Organised by: Logo
Congress Presentation Part of: State-of-the-art in artificial intelligence for electrocardiography research Deep Learning ESC2026 Premium Access ESC Congress 2026 European Society of Cardiology

About the speaker

Photo
Mr Wai Chak Wong

The University of Hong Kong, Hong Kong (Hong Kong)

4 More presentations in this session

Presentation thumbnail
Electrocardiographic aging based on artificial intelligence and the risk of heart failure and its subtypes: a multi-national study
Doctor S. Chung (Seoul, KR)
Abstract Slides
Presentation thumbnail
Improving ECG diagnostic performance under ambulatory noise with scalable long-range state-space denoising modelling
Doctor S. Ruiperez-Campillo (Zurich, CH)
Abstract Slides
Presentation thumbnail
Deep learning detection of cardiac amyloidosis from ECG images: validation across diverse clinical and prospective cohorts
Mr P. Croon (New Haven, US)
Abstract Slides
Presentation thumbnail
Reliability of snapshot AI-ECG predictions: test-retest reproducibility across seven prediction tasks in three hospital cohorts
Doctor H. Aggour (London, GB)
Abstract Slides

Access the full session

Session thumbnail
State-of-the-art in artificial intelligence for electrocardiography research

The Event

Event poster

ESC Congress 2026

28 August 2026 13:15 CET
You may be interested in
thumbnail
Congress Presentation
Deep learning-enabled electrocardiogram assessment of valvular heart disease
13 December 2024
thumbnail
Congress Presentation
Overview on vision-language models for automatic reporting in cardiovascular imaging
22 November 2025
thumbnail
Congress Presentation
Evaluation of AI-based ECG analysis accuracy using Chat GPT-4 and Gemini AI models
1 April 2025
thumbnail
Congress Presentation
Trends in artificial intelligence for cardiovascular research: a topic modelling study using BERTopic
22 November 2025

ESC 365 is supported by

novartis Explore sponsored resources
novo-nordisk Explore sponsored resources

ESC 365 is supported by

novartis Explore sponsored resources
novo-nordisk Explore sponsored resources