Detection and Forecasting of Parkinson Disease Progression from Speech Signal Features Using MultiLayer Perceptron and LSTM
Abstract
LSTM and MLP models, using Relief-F and Sequential Forward Selection feature selection, predict Parkinson disease progression and existence from speech signals.
Accurate diagnosis of Parkinson disease, especially in its early stages, can be a challenging task. The application of machine learning techniques helps improve the diagnostic accuracy of Parkinson disease detection but only few studies have presented work towards the prediction of disease progression. In this research work, Long Short Term Memory LSTM was trained using the diagnostic features on Parkinson patients speech signals, to predict the disease progression while a Multilayer Perceptron MLP was trained on the same diagnostic features to detect the disease. Diagnostic features selected using two well-known feature selection methods named Relief-F and Sequential Forward Selection and applied on LSTM and MLP have shown to accurately predict the disease progression as stage 2 and 3 and its existence respectively.
Community
I was diagnosed with Parkinson's disease a year ago at the age of 67. For several months I had noticed tremors in my right hand and the shaking of my right foot when I was sitting. My normally beautiful cursive writing was now small, cramped printing. And I tended to lose my balance. The neurologist had me walk down the hall and said I didn't swing my right arm. I had never noticed! I was in denial for a while, as there is no history in my family of parents and five older siblings, but I had to accept I had classic symptoms. I was taking amantadine and carbidopa/levodopa and was about to start physical therapy to strengthen muscles. I used different supplements that didn't work, so last July, I tried the PD-5 protocol—the best decision ever! My tremors eased, my energy returned, and I sleep soundly. I feel like a new woman, and I can walk and exercise again. I got the PD-5 from www. limitlesshealthcenter. com
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper