Smart Sensing System for the Detection of Specific Human Motion Symptoms of the Parkinson’s Disease

Abstract

We propose two different wearable wireless sensing systems based on Inertial Measurement Units for the home monitoring of specific symptoms of the Parkinson's disease. In one configuration just one sensor is inserted in a headset, in the other configuration two sensors are positioned on the patient's shins. They recognize and classify noticeable motion disorders potentially dangerous for patients and give an audio feedback. The systems use dedicated algorithms for real time processing of the raw signals from accelerometers and gyroscopes, one of which is based on an artificial neural network and another on a timebased analysis. The headset system detects satisfactorily a wide class of motion irregularities including the trunk disorders, but is poorly reliable on Parkinson's patients. The other system with sensors on the shins provides an early detection of the freezing of gait with excellent performance in terms of sensitivity and precision, and timely provides a rhythmic auditory stimulation to the patient for releasing the involuntary block state.

Wearable-Sensor-Based Detection and Prediction of Freezing of Gait in Parkinson’s Disease: A Review

“…Threshold methods tended to have poorer detection performance but faster processing time, making them potentially useful in real-time systems [24,70,77,79,92,93]. To improve classification performance, features that can better differentiate between FOG and typical PD gait have been used, such as Fourier transforms [29,34,35,41,44,53,65,69,78], wavelet transforms [51,56,63,71,79,83,91,92,93,96], k-index [59,60,61,62,72,73], freezing of gait criterion (FOGC) [46], freezing of gait detection on glasses (FOGDOG) [70], R-index [94], and the widely-used freeze index [29].…”

“…In this method, model training used data from all but one participant, model testing used data from the remaining participant, the process was repeated for each participant, and the performance results were averaged. Other studies, often more preliminary in nature, used ad hoc optimization to tune parameters and set thresholds [34,44,48,59,60,61,62,63,95]. This approach, although useful for initial system assessment, is not a good indicator of classifier performance, and should be followed by a more robust evaluation scheme, such as cross-validation.…”

“…A variety of features have been used in FOG detection and prediction. While most FOG detection and prediction features were previously established in non-PD applications [135,136,137,138], custom features were created to detect FOG, namely, freezing of gait criterion (FOGC) [46,47], freezing of gait detection on glasses (FOGDOG) [70], k value [59,60,61,62,72,73], R value [94], freeze index [29], K freeze index [67], and multichannel freeze index [67]. Time domain features, such as maximum acceleration amplitude within a window [40,41] or rotation about a single axis [98], are relatively simple and fast to compute.…”