AI Spots Deadly Heart Risk Most Doctors Can't See
- Researchers at Johns Hopkins have developed an AI model called MAARS that utilizes MRI scans and medical information to predict the risk of sudden cardiac death; their findings appear in the latest issue of Nature Cardiovascular Research.
- The work addresses the low accuracy of current clinical guidelines, which identify at-risk patients correctly about 50% of the time, a rate described as 'not much better than throwing dice.'
- MAARS detects critical patterns of fibrosis in hypertrophic cardiomyopathy patients, a common inherited heart condition affecting 1 in 200 to 500 people and increasing sudden death risk.
- The AI model showed 89% accuracy across all patients and 93% accuracy for ages 40 to 60, a group at highest risk, and co-author Jonathan Crispin said it can transform clinical care.
- The team plans to test MAARS further and apply it to other heart diseases, aiming to better protect patients and reduce unnecessary interventions like unneeded defibrillators.
14 Articles
14 Articles
Eko Health’s AI for Cardiac Diagnoses Earns CMS Reimbursement Rate
This week, CMS established a reimbursement code for Eko Health’s AI platform, which seeks to aid clinicians in the diagnosis of heart conditions. The goal behind the technology is to help catch heart disease earlier, when it’s easier to treat, and to make high quality diagnostic care more accessible. The post Eko Health’s AI for Cardiac Diagnoses Earns CMS Reimbursement Rate appeared first on MedCity News.
AI spots deadly heart risk most doctors can't see
An advanced Johns Hopkins AI model called MAARS combs through underused heart MRI scans and complete medical records to spot hidden scar patterns that signal sudden cardiac death, dramatically outperforming current dice-roll clinical guidelines and promising to save lives while sparing patients unnecessary defibrillators.


AI Model Better Predicts Sudden Deaths in Hypertrophic Cardiomyopathy
(MedPage Today) -- Artificial intelligence (AI) showed promise for substantially improving risk prediction in hypertrophic cardiomyopathy (HCM) beyond what clinicians can do with current tools, researchers reported. A deep learning model, Multimodal...
Multimodal AI to forecast arrhythmic death in hypertrophic cardiomyopathy
Sudden cardiac death from ventricular arrhythmias is a leading cause of mortality worldwide. Arrhythmic death prognostication is challenging in patients with hypertrophic cardiomyopathy (HCM), a setting where current clinical guidelines show low performance and inconsistent accuracy. Here, we present a deep learning approach, MAARS (Multimodal Artificial intelligence for ventricular Arrhythmia Risk Stratification), to forecast lethal arrhythmia …
AI predicts patients likely to die of sudden cardiac arrest
A new AI model is much better than doctors at identifying patients likely to experience cardiac arrest. The linchpin is the system's ability to analyze long-underused heart imaging, alongside a full spectrum of medical records, to reveal previously hidden information about a patient's heart health.
Coverage Details
Bias Distribution
- 100% of the sources are Center
To view factuality data please Upgrade to Premium