The Amyloidosis Channel is supported through an educational grant from Alexion Pharma GmbH.
VJHemOnc is an independent medical education platform. Supporters, including channel supporters, have no influence over the production of content. The levels of sponsorship listed are reflective of the amount of funding given to support the channel.
ESC 2026 | Exploring an AI-guided screening approach for identifying patients at high risk of cardiac ATTR
Ilia Davarashvili, MD, Leumit Health Services and Leumit Start, Tel Aviv, Israel, shares insights into an artificial intelligence (AI)-guided screening approach that incorporates clinical, demographic, and echocardiographic parameters to identify patients at high risk for cardiac transthyretin amyloidosis (ATTR-CM). Dr Davarashvili highlights that, while the algorithm identified more cases than in the general screening population, AI should be combined with good clinical practice and cardiologist expertise. This interview took place during the 2026 European Society of Cardiology (ESC) Congress in Munich, Germany.
These works are owned by Magdalen Medical Publishing (MMP) and are protected by copyright laws and treaties around the world. All rights are reserved.
Transcript
I think I’m about one day and a half at the ESC Congress and ATTR amyloidosis is one of the talked-about issues, one of the developing issues nowadays, and it’s very important to make a round, our round as well. The idea behind our project was very simple. We integrated and designed an algorithm which incorporated the clinical demographic and echocardiographic parameters as well...
I think I’m about one day and a half at the ESC Congress and ATTR amyloidosis is one of the talked-about issues, one of the developing issues nowadays, and it’s very important to make a round, our round as well. The idea behind our project was very simple. We integrated and designed an algorithm which incorporated the clinical demographic and echocardiographic parameters as well. So, for instance, it included age, left ventricle systolic function, diastolic dysfunction, and pulmonary artery systolic pressure as well. We’re integrated as well well established clinical red flags like atrial fibrillation, conduction disturbances, spinal stenosis, and carpal tunnel syndrome as well. And the most important learning point is no single parameter can discriminate the ATTR; however, when we make a combination and we’ve made about 74 modifications by the AI system, still we identified that we can reach six times more than in the general pre-specified Israeli population, the yield, achieving even about 10 times more than in the general screen population, not in a heart failure population. So it’s a great achievement. But we have to understand that AI can help to identify the high-risk patient, but it cannot replace the diagnostic tool and the pathway as well. So AI with good clinical practice and a good cardiologist can give a yield much higher than only AI or only a pathway alone.
This transcript is AI-generated. While we strive for accuracy, please verify this copy with the video.
Read more...
