A Johns Hopkins-led AI model outperforms current clinical guidelines in predicting risk of sudden cardiac death using cardiac MRI and patient records.
Key Details
- 1MAARS AI model analyzes contrast-enhanced cardiac MRI and medical records.
- 2Hypertrophic cardiomyopathy, a leading cause of sudden cardiac death, was the focus.
- 3Current guidelines identify high-risk patients with only ~50% accuracy; the AI reached 89% accuracy overall and 93% in ages 40-60.
- 4AI identifies critical heart scarring patterns (fibrosis) missed by doctors.
- 5Study published in Nature Cardiovascular Research; multi-institutional collaboration.
- 6Potential to both save lives and reduce unnecessary interventions like defibrillators.
Why It Matters
This work demonstrates substantial value in integrating imaging AI with clinical data for cardiac risk stratification, both improving accuracy and enabling personalized management. Its validation could shift how radiologists and clinicians collaborate for risk prediction and treatment strategy.
Source
EurekAlert
Related News
•EurekAlert
AI Accelerates Radiopharmaceuticals, Boosts Personalized Dosimetry in Cancer
Machine learning is driving advancements in radiopharmaceutical drug discovery and optimizing patient-specific dosimetry for precision cancer therapy.
•EurekAlert
Physicians Overly Trust Erroneous AI, Ignore Contradictory Evidence
Physicians tend to trust incorrect AI advice, even when evidence contradicts it, suggesting risks in clinical decision-making with AI tools.
•EurekAlert
Concerns Raised Over Unverified Datasets in AI Health Prediction Models
A new study finds widely used AI health prediction models are built on datasets with unverifiable origins, raising safety and validity concerns.