Enhanced Parkinson's Disease Prediction Using Feature Selection, SMOTE, and Machine Learning with Deep Learning Models

This research leverages the UCL Parkinson's Disease clinical dataset to predict Parkinson's illness with the application of both deep learning and machine learning techniques. To address class imbalance, SMOTE was applied, and feature selection was conducted using the sci2 tool. The study assessed six deep learning algorithms, such as LSTM, PLSTM, and MLP, as well as six machine learning classifiers, including SVM, KNN, Logistic Regression, Naive Bayes, Decision Tree, and AdaBoost. MLP outperformed the others in terms of accuracy for deep learning models. With 97.20% accuracy, 97.44% precision, 97.20% recall, and 97.32% F1-score, KNN was the most successful overall, nonetheless. These findings show how well KNN detects Parkinson's disease and emphasize the technology's potential for early diagnosis and monitoring.