Back

Electrocardiogram complexity determines large language model diagnostic accuracy: a pathology-stratified analysis of 599 cases across 22 diagnostic categories

31 August 2026 (11:15 - 12:00)
Organised by: Logo
Congress Presentation Part of: Artificial intelligence in cardiovascular imaging: methods, performance, and clinical readiness Large Language Model ESC Professional Premium Access ESC Congress 2026 European Society of Cardiology

About the speaker

Photo
Doctor Harish Kamalanathan

Prince of Wales hospital, Sydney (Australia)

4 More presentations in this session

Presentation thumbnail
Optimizing echocardiography workflow to increase access to high quality care for patients
Miss C. Alonso Casero (Madrid, ES)
Abstract Slides Video
Presentation thumbnail
A dual modal collaborative learning network for echocardiography video segmentation
Mr X. Zhou (Beijing, CN)
Abstract Slides Video
Presentation thumbnail
Deep learning for x-ray coronary angiography: a systematic review of methods, validation, and clinical readiness
Doctor C. Goelz (Munich, DE)
Abstract Slides Video
Presentation thumbnail
Artificial intelligence versus clinicians for the diagnosis of cardiac amyloidosis: a systematic review and meta-analysis
Mr A. Chauhan (New Delhi, IN)
Abstract Slides Video

Access the full session

Session thumbnail
Artificial intelligence in cardiovascular imaging: methods, performance, and clinical readiness

The Event

Event poster

ESC Congress 2026

31 August 2026 11:15 CET
You may be interested in
thumbnail
Congress Presentation
Multimodal large language models demonstrate consistently low accuracy for 12-lead electrocardiogram interpretation: a 599-case benchmark study
29 August 2026
thumbnail
Congress Presentation
Development and external validation of an AI- model to triage echocardiograms
31 August 2026
thumbnail
Congress Presentation
Artificial intelligence for automated baseline cardiovascular condition identification: accuracy, confidence, and discordance
29 August 2026
thumbnail
Congress Presentation
Reinforcement learning with GSPO enables vision language model (VLM) to detect structural heart disease from 12-lead electrocardiography
28 August 2026

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