From there, the sensor sends its data to a smart watch (in this case an Apple Watch) where the AI intervenes. The automatic learning of the watch can detect various signs of Parkinson's disease, such as tremors, bradykinesia (slow onset of voluntary movement) and dyskinesia (reduction of voluntary movements). IBM added that it can use a neural network to accurately detect finger-written numbers, which could help identify health problems associated with cognitive function and motor skills.
While the sensor was initially developed in the spirit of Parkinson's disease, IBM clearly sees a range of uses that could in particular help detect the development of many diseases as well as the effectiveness of treatments designed to slow down these conditions. It also served as a basis for a communication device for quadriplegics. There is no mention of when this sensor could become a practical reality, but at least it makes sense. Skin sensors often pose a problem for the elderly, whose hands and arms may be relatively fragile. A nail sensor would sit on a relatively safe area where you do not have to worry about removing it or a loose fit.