Early Warning Signs Of Parkinson’s Disease Prediction Using Machine Learning Technique

Abstract

Brain cells breakdown is primary cause of Parkinson's disease (PD) that create dopamine. A neurotransmitter that allows brain cells to connect with each other. Dopamine-producing cells in the brain are in control of adaptability, movement regulation, and fluency. Active ageing is a concept that has arisen to optimise many areas of fitness prospects throughout the ageing development in order to improve eminence of life. However, best initiatives have focused on normal ageing, with little attention dedicated to the elderly (ageing) suffering from a chronic condition such as PD. These tactics may be able to assist people with PD in better managing their illness in the context of active ageing. The datasets have extensively depicted parkinson disease  by utilising a range of data-derived perspectives. According to the results, our suggested technique beats other techniques. In order to achive our aim we have suggested an ensemble learning technique. The suggested model outperforms existing machine learning approaches such as SVM(support vector machine), KNN(K-nearest neighbour), RF(Random-Forest), DT(Decision-Tree), MLP(multilayer perceptron), (SC)StackingClassifier, (LR)Logistic-Regression. when accuracy, matthews correlation coefficient (MCC), and f1score are calculated. According to the results of our research, the technique we described, the ensemble model, outperforms other machine learning models. We achieved 94.87% accuracy, 81.99% MCC , and 94.52% f1score.