Dr Lin Yee Chen (University of Minnesota Medical School, Minneapolis, MN, US) joins us to examine which artificial intelligence (AI) applications in heart failure are ready for clinical use today, and which remain experimental. As AI moves from research settings into the clinic, separating genuine clinical utility from hype has become a pressing question for heart failure specialists.

In this interview, Dr Chen sets out where AI-enhanced electrocardiography (AI-ECG) is already informing screening and risk stratification, most notably in detecting asymptomatic left ventricular systolic dysfunction before symptoms develop, and in identifying patients at risk of atrial fibrillation, a major driver of heart failure. Dr Chen also addresses the validation any new tool must satisfy before clinicians can rely on it: generalisability across populations, calibration as well as discrimination, freedom from subgroup bias, and explainability to earn physician trust.

Interview Questions:

1. In 2026, where is ECG-based AI already changing heart failure screening or risk stratification?
   Which AI-derived rhythm or atrial signals do you currently trust most for flagging heart failure risk?
2. For a new heart failure AI tool, what checks around population fit, calibration, bias, and interpretability must be in place before you rely on it?
3. In the next two to three years, which AI applications do you expect to enter routine heart failure care, and which will likely remain experimental?
4. For a busy heart failure clinic today, which one or two AI tools clearly add value without increasing workflow burden?
5. If every clinic could adopt one AI tool for heart failure, which would you choose, and what is the biggest risk of using it uncritically?

Editors: Jordan Rance
Videographer: Tom Green, David Ben-Harosh
Support: This is an independent interview produced by Radcliffe Cardiology.