Parkinsons Disease Prediction With Spiral Drawings and Wave Frequency Using Deep Conformal Neural Networks

In this study, present a system that combines two independent data sources wave frequency and spiral drawing picture datasets to improve prediction accuracy for Parkinson's disease (PD) diagnosis. A complete data fusion technique is used to combine information from both modalities, resulting in a more robust dataset. To improve prediction reliability, we present Deep Conformal Neural Networks (DCNN), which not only forecast PD status but also offer confidence ratings for each prediction, resulting in increased transparency and interpretability. The technology uses voice recordings for frequency analysis and picture data from medical scans for visual analysis. The DCNN model successfully processes and classifies different data types by using sophisticated deep learning methods such as convolutional operations, pooling layers, and activation functions. The model's performance is assessed using a variety of measures, including accuracy, precision, recall, and F-measure. The DCNN surpasses standard machine learning models, with 99% accuracy, 98% precision, 99% recall, and 96% F-measure, exhibiting greater diagnostic skills for Parkinson's disease diagnosis. These results emphasize DCNNs' potential for enhancing the reliability of early Parkinson's disease diagnosis, hence facilitating more effective clinical decision-making.