In a recent study, MIT Media Lab‘s Max Little used machine learning tools to indicate early Parkinson’s Disease in a group of smartphone users. Phones were given to Parkinson’s patients and a healthy control group. The built in accelerometer enabled Little to distinguish between those with and with out the disease with 99% accuracy. The detection method relied on subtle differences in a patient’s movement, including rigidity and impaired balance.
In another Parkinson’s Voice Initiative study, 50 people were asked to say “ahh” into the phone for a few weeks. The audio recordings allowed Little to estimate disease progression using the Unified Parkinson’s Disease Rating Scale.
Wearable Tech + Digital Health NYC 2015 – June 30 @ New York Academy of Sciences