Good question. Atrial fibrillation is the first clinical application, and my hope is that we'll have final publishable results in early 2017. Other studies have shown is that, in a population at high risk of atrial fibrillation but undiagnosed, it takes a median of about 80 days for the first episode to appear. So there's an argument there for continuous monitoring, much longer than the 24 hours typical of a Holter monitor or 2-4 weeks typical of ECG chest patches.

For other conditions like diabetes or sleep apnea, we definitely see correlations in our study between those conditions and heart rate variability (and the medical literature confirms the same thing), although we don't yet know how much time you need to build up an accurate risk score.

I think those other conditions are something we'd love to evaluate next!