A novel device for peripheral neuropathy assessment and rehabilitation

The aim of this work is the development of a noninvasive device which can be used in the diagnostic and the rehabilitation of the patients who exhibit peripheral neuropathy at the level of the upper limb. According to the National Institute of Neurological Disorders and Stroke, more than one hundred types of peripheral neuropathy have been identified, each with its own symptoms. The device presented in this paper is based on the acquisition, analysis and classification of the symptom of tremor at the hands level, and also on the hand grip force. The device is built in the form of a ball which can be handheld based on a 3D accelerometer sensor and three force capacitive sensors. The acceleration and force are analyzed using the specific methods such as FFT transform in order to analyze the frequency spectra of the tremor when increasing the hand grip force. Vectors of features are classified according to the classification algorithms, using the Artificial Neural Networks (ANNs). In our case, in all three stages of ANN testing, we obtained the root mean square error value smaller than 0.5%, with 100 percent identification of classes.