Parkinson's disease prediction based on hand tremor analysis

Parkinson's disease is a progressive disorder of the nervous system marked by tremor, muscular rigidity and slow, imprecise movement, chiefly affecting middle-aged and elderly people. This paper presents a non-invasive, reliable method for the prediction of Parkinson's disease by analysis of hand tremors using an accelerometer type of sensor. The frequency of the tremors experienced in Parkinson's disease lies between the range of 3–8 Hertz. The accelerometer is used to measure these tremors and further computation is done in MATLAB. This obtained time domain signal is then converted into frequency domain using Fast Fourier Transform and the dominant frequency component is determined. Data of 7 subjects is collected out of which 3 subjects are suffering from Parkinson's disease and remaining 4 are normal subjects. The results obtained proved that the frequency of the hand tremors in Parkinson's patient lies between 3–8 Hertz and the readings obtained on all the three axes are almost same. The proposed system can be used by the general physicians for the prediction of Parkinson's disease without the conventional and expensive diagnostic tools.