No abstract

Parkinson’s disease is one of the most prevalent and harmful neurodegenerative conditions (PD). Even today, PD diagnosis and monitoring remain pricy and inconvenient processes. With the unprecedented progress of artificial intelligence algorithms, there is an opportunity to develop a cost-effective system for diagnosing PD at an earlier stage. There is no permanent remedy established yet; however, an earlier diagnosis helps to lead a better life. The three most responsible symptoms of Parkinson’s Disease are tremors, rigidity, and body bradykinesia. Therefore, to diagnose PD patients at the beginning stage, we investigate the 53 unique features of Parkinson’s Progression Markers Initia- tive (PPMI) dataset. Furthermore, we utilize Machine Learning (ML), Ensemble Learning (EL), and Artificial Neural Network (ANN) for classification. As feature selection is an integral part in developing generalize model, we investigate including and excluding feature selection. Four feature selection methods are incorporated - Low Variance Filter, Wilcoxon rank-sum test, Principle Component Analysis, and Chi-Square test. Our proposed ANN model attains the best mean accuracy of 99.51%, 98.17% mean specificity, 0.9830 mean Kappa Score, 0.99 mean AUC, and 99.70% mean F1-score. The efficiency of our suggested technique on diverse data modalities is demonstrated by comparison with recent publications. Finally, we established a trade-off between classification time and accuracy

Parkinson's disease is one of the most prevalent and harmful neurodegenerative conditions (PD). Even today, PD diagnosis and monitoring remain pricy and inconvenient processes. With the unprecedented progress of artificial intelligence algorithms, there is an opportunity to develop a cost-effective system for diagnosing PD at an earlier stage. There is no permanent remedy established yet; however, an earlier diagnosis helps to lead a better life. The three most responsible symptoms of Parkinson's Disease are tremors, rigidity, and body bradykinesia. Therefore, to diagnose PD patients at the beginning stage, we investigate the 53 unique features of Parkinson's Progression Markers Initiative (PPMI) dataset. Furthermore, we utilize Machine Learning (ML), Ensemble Learning (EL), and Artificial Neural Network (ANN) for classification. As feature selection is an integral part in developing generalize model, we investigate including and excluding feature selection. Four feature selection methods are incorporated -Low Variance Filter, Wilcoxon rank-sum test, Principle Component Analysis, and Chi-Square test. Our proposed ANN model attains the best mean accuracy of 99.51%, 98.17% mean specificity, 0.9830 mean Kappa Score, 0.99 mean AUC, and 99.70% mean F1-score. The efficiency of our suggested technique on diverse data modalities is demonstrated by comparison with recent publications. Finally, we established a trade-off between classification time and accuracy.