Towards Early Diagnosis Of Parkinson’s Disease Through Speech Signals’ Analysis Based on Advanced Deep Learning Techniques

The utilization of Artificial Intelligence ‘AI’ techniques for analyzing speech signals is so promising nowadays especially for various medical applications. In our proposed research, dealing with early diagnosis of Parkinson’s disease using speech analysis is a highly promising and innovative approach that has demonstrated considerable potential in identifying the disease during its initial phases. This study uses a combined methodology that utilizes Deep Learning ‘DL’ approach for speech features’ extraction followed by one Machine Learning approach as for final classification. In order to cultivate these profound features, a deep auto-encoder was hence utilized as a technique for feature extraction, while a multi-layer perceptron (MLP) was employed as a classifier. Our empirical findings indicate that the DL models proposed in this study yielded favorable outcomes, achieving a success rate of $90 \%$. The preliminary findings of this study indicate that the proposed approach has the potential to early identifying Parkinson’s disease through the analysis of speech signals. Such an important finding will not only help neurologists and considerably during their clinical investigations but also will enrich medical further assessments. A clinical aided tool could be conceived consequently in correlation with the future clinical feedback.