End-to-End Deep Learning Method for Detection of Invasive Parkinson’s Disease

Abstract

Parkinson’s disease directly affects the nervous system are causes a change in voice, lower efficiency in daily routine tasks, failure of organs, and death. As an estimate, nearly ten million people are suffering from Parkinson’s disease worldwide, and this number is increasing day by day. The main cause of an increase in Parkinson’s disease patients is the unavailability of reliable procedures for diagnosing Parkinson’s disease. In the literature, we observed different methods for diagnosing Parkinson’s disease such as gait movement, voice signals, and handwriting tests. The detection of Parkinson’s disease is a difficult task because the important features that can help in detecting Parkinson’s disease are unknown. Our aim in this study is to extract those essential voice features which play a vital role in detecting Parkinson’s disease and develop a reliable model which can diagnose Parkinson’s disease at its early stages. Early diagnostic systems for the detection of Parkinson’s disease are needed to diagnose Parkinson’s disease early so that it can be controlled at the initial stages, but existing models have limitations that can lead to the misdiagnosing of the disease. Our proposed model can assist practitioners in continuously monitoring the Parkinson’s disease rating scale, known as the Total Unified Parkinson’s Disease Scale, which can help practitioners in treating their patients. The proposed model can detect Parkinson’s disease with an error of 0.10 RMSE, which is lower than that of existing models. The proposed model has the capability to extract vital voice features which can help detect Parkinson’s disease in its early stages.

Assessment of Voice Disorders Using Machine Learning and Vocal Analysis of Voice Samples Recorded through Smartphones

“…Studies have explored the development of artificial intelligence tools for predicting vocal cord pathology in primary care settings [63]. Additionally, the application of convolutional neural network ensembles and deep learning methods has been investigated for the detection of Parkinson's disease from voice recordings, demonstrating the potential of smartphone-based voice analysis in disease detection [64,65]. Furthermore, research has shown the association of noninvasive vocal biomarkers with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection [66], highlighting the potential of smartphone-based voice analysis in infectious disease detection [67].…”