Back

PulseFormer: curriculum learning guided bimodal co-attention and graph-augmented hierarchical ECG strip classification

21 November 2025 (08:00 - 18:00)
Organised by: Logo
Congress Presentation Part of: Developing and evaluating AI-models in ECG analysis Electrocardiogram (ECG) and Arrhythmia Analysis Open Access ESC Digital & AI Summit 2025 European Society of Cardiology

About the speaker

Photo
Doctor Sai Upadhyayula

Bangalore (India)

5 More presentations in this session

Presentation thumbnail
Artificial intelligence-assisted QT interval measurement in 12-lead ECGs
Associate Professor Y. Kim (Gwangju, KR)
Abstract Slides
Presentation thumbnail
Incorporating respiratory dynamics into context-aware QTc assessment using a wearable sensor
Mr T. Van Den Broek (Leiden, NL)
Abstract Slides
Presentation thumbnail
External validation of the PMcardio AI-ECG model for detecting occlusion myocardial infarction in a portuguese cohort
Doctor E. Figueiredo (Porto, PT)
Abstract Slides
Presentation thumbnail
How well do large language models interpret ECGs? A comparative benchmark of chatGPT - 4o, claude, and gemini using standardised teaching cases
Doctor H. Kamalanathan (Sydney, AU)
Abstract Slides
Presentation thumbnail
Deep learning-enabled ECG fingerprinting of low-voltage substrate in atrial fibrillation patients
Mr S. Ruiperez-Campillo (Zurich, CH)
Abstract Slides

Access the full session

Session thumbnail
Developing and evaluating AI-models in ECG analysis

The Event

Event poster

ESC Digital & AI Summit 2025

21 November - 22 November 2025
You may be interested in
thumbnail
Congress Presentation
Digital 12-lead ECG: what is hidden behind the clinical report
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

ESC 365 is supported by

novartis Explore sponsored resources

ESC 365 is supported by

novartis Explore sponsored resources