This abstract outlines the application of a Convolutional Neural Network (CNN) algorithm for predicting Parkinson’s disease and calculating the F1-score. The process involves multiple stages, starting with data preprocessing, where the dataset is prepared and divided into training and testing subsets. The CNN model is constructed with convolutional layers, pooling layers, and fully connected layers. The model is compiled using appropriate loss functions and optimizers. Data augmentation techniques can be applied to enhance model generalization. After training the model using the training dataset, it is evaluated using the testing dataset. Predictions are generated for the testing data, and the F1-score is calculated using the derived predictions and true labels. The F1-score, which balances precision and recall, provides insight into the model’s performance in predicting Parkinson’s disease. A higher F1-score signifies a better trade-off between false positives and false negatives. The outlined process offers a comprehensive approach to employing CNNs in Parkinson’s disease prediction and performance assessment through the F1-score.