ANN-Assisted Deep Learning Approaches and DNN Classifiers for Parkinson’s Disease (PD) Diagnosis and Prediction

Parkinson’s disease (PD), a degenerative neurological condition that severely impairs movement and cognitive abilities, must be diagnosed early and accurately in order to be properly managed. Due to the complexity and diversity of PD symptoms, conventional diagnostic methods often fall short. In order to increase the accuracy of PD diagnosis and prediction, this research suggests a hybrid form that incorporates Deep Neural Networks (DNNs) with Artificial Neural Networks (ANNs). Through the use of multimodal datasets, such as clinical assessments, speech features, and imaging data, the proposed ANN-assisted DNN architecture outperforms conventional machine learning techniques. With significant gains in sensitivity and specificity, this model attains an overall diagnosis accuracy of 97.4%, underscoring its promising potential for use in clinical diagnostic systems.