Reliable and robust detection of freezing of gait episodes with wearable electronic devices

A wearable wireless sensing system for assisting patients affected by Parkinson's disease is proposed. It uses integrated micro-electro-mechanical inertial sensors able to recognize the episodes of involuntary gait freezing. The system operates in real time and is designed for outdoor and indoor applications. Standard tests were performed on a noticeable number of patients and healthy persons and the algorithm demonstrated its reliability and robustness respect to individual specific gait and postural behaviors. The overall performances of the system are excellent with a specificity higher than 97%.