Each year, more than 100,000 strokes are caused by an abnormal heart rhythm called atrial fibrillation.
In atrial fibrillation, electrical conduction in the heart becomes disorganized. The upper chambers may beat 300-600 times per minute. The lower chambers may beat at a normal rate, but irregularly.
Atrial fibrillation is treatable, but many people don't feel symptoms, so it often goes undiagnosed.
Your heart's normal rhythm varies from beat to beat, and the pattern of variability depends on what's happening in your life—whether you're stressed, excited, exercising, or just drank coffee. Atrial fibrillation is highly variable, but in a way that's random.
Using a technique called semi-supervised deep learning, we're building an algorithm that can distinguish between the pattern of heart rate variability found in normal heart rhythm and that in atrial fibrillation.