An AI model developed by biomedical engineer Murray B. Sachs Professor Natalia Trayanova and her team is more accurate than doctors at spotting which patients with hypertrophic cardiomyopathy—a common inherited condition that thickens the heart muscle—are most likely to suffer from sudden cardiac death. The linchpin is the system’s ability to analyze long underused heart imaging, alongside full medical records.
1. Hypertrophic cardiomyopathy, the condition at the study’s center, affects:
A. 1 in every 2,000 people
B. 1 in every 200–500 people
C. 1 in every 20,000 people
Answer: B
About 1 in 200–500 people worldwide live with this disease. Most lead normal lives, but some face a much higher risk of sudden cardiac death, particularly young people and athletes.
2. Current guidelines for spotting high-risk patients are accurate about:
A. 90% of the time
B. 50% of the time
C. 25% of the time
Answer: B
Just 50%—“not much better than throwing dice,” says Trayanova, senior author of the study, which was published in Nature Cardiovascular Research.
3. What makes the new Johns Hopkins AI model, nicknamed MAARS (for Multimodal AI for ventricular Arrhythmia Risk Stratification), different?
A. It studies DNA sequences
B. It can read MRI heart scans in a way doctors cannot
C. It listens to heartbeats through smartwatches
Answer: B
For the first time, AI can detect scarring patterns in MRI images that doctors have struggled to interpret, combining that with other medical data to sharpen risk predictions.
4. When tested on real patients, how accurate was MAARS?
A. 63%
B. 75%
C. 89%
Answer: C
89% overall—and 93% for patients aged 40 to 60, the group most at risk.
5. Beyond saving lives, what’s another benefit of MAARS?
A. It eliminates MRIs
B. It could spare patients unnecessary defibrillator implants
C. It requires no medical records
Answer: B
Many patients receive defibrillators that they may never need. By predicting outcomes more precisely, MAARS could help doctors avoid the cost and risks of those unnecessary procedures. The team plans to expand the model to other heart conditions, potentially transforming clinical care.