Early Detection of Parkinson’s Disease Based on Voice Disorders Using Deep Learning

Parkinson's disease is a serious health issue worldwide, especially as populations age. Detecting it early and accurately is crucial for effective management. This research project aims to improve existing methods by using custom deep learning models like Logistic regression, Bagging classifier, AdaBoost and XGB classifier to classify Parkinson's disease. Deep learning has shown promise in automating disease detection from medical images. In this study, a performance comparison of different machine learning(ML) models such as Artificial Neural Networks (ANN), logistic regression, Gaussian NB, Decision Tree, AdaBoost, XGB classifier etc has been done. ANN stands out, achieving an impressive accuracy of 97.13% as it emphasizes the need for specialized models to tackle the complexities of disease detection. By using advanced deep learning techniques, this research aims to improve the accuracy and reliability of Parkinson's disease using the voice recording dataset.