New EchoRisk dataset targets early detection of therapy-induced cardiotoxicity

Researchers have introduced EchoRisk, a new dataset and benchmark designed for early detection of cardiotoxicity in cancer patients undergoing therapy. This dataset, derived from the CARDIOCARE study, includes longitudinal echocardiography videos from over 400 patients across five European sites. It supports three tasks: estimating ejection fraction, classifying left ventricular dysfunction, and predicting cardiotoxicity from baseline imaging, with initial baselines showing strong performance in functional assessment but highlighting early cardiotoxicity prediction as an open challenge. AI

IMPACT This dataset could accelerate AI-driven advancements in early detection and prevention of cardiotoxicity in cancer patients.

RANK_REASON The item is a research paper introducing a new dataset and benchmark for a specific medical application. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• CARDIOCARE
• CatalyzeX
• DagsHub
• EchoRisk
• Gotit.pub
• Grigorios Kalliatakis
• Hugging Face
• Kinetics-400
• MICCAI 2026
• ScienceCast

• paper
• product
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →