A new AI algorithm leveraging cardiac MRI and health data significantly outperforms current clinical guidelines in predicting risk of sudden cardiac arrest in hypertrophic cardiomyopathy patients.
Key Details
- 1The AI model, MAARS, uses cardiac MRI, electronic health records, and echocardiogram data.
- 2Developed and validated on cohorts of 553 and 284 patients, respectively.
- 3MAARS achieved 89% overall accuracy and 93% accuracy for high-risk patients aged 40-60.
- 4Outperformed traditional clinical guidelines (approx. 50% accuracy) and other tools in sensitivity, specificity, and AUROC (0.89 for MAARS).
- 5Could reduce unnecessary implantable defibrillators and more precisely identify at-risk patients.
Why It Matters
This development demonstrates the power of multimodal AI to improve risk stratification in cardiac imaging, potentially leading to better patient outcomes and more tailored medical interventions in radiology and cardiology practice.
Source
AuntMinnie
Related News
•AuntMinnie
Paul Chang Discusses Foundation Models and Agentic AI at RSNA 2025
Dr. Paul Chang shares his insights on the role of foundation models and agentic AI in radiology at RSNA 2025.
•AuntMinnie
Toronto Study: LLMs Must Cite Sources for Radiology Decision Support
University of Toronto researchers found that large language models (LLMs) such as DeepSeek V3 and GPT-4o offer promising support for radiology decision-making in pancreatic cancer when their recommendations cite guideline sources.
•AuntMinnie
AI Model Using Mammograms Enhances Five-Year Breast Cancer Risk Assessment
A new image-only AI model more accurately predicts five-year breast cancer risk than breast density alone, according to multinational research presented at RSNA 2025.