A comparative analysis of parkinson disease prediction using machine learning approaches
Abstract
Objective:The primary objective of the study is to inspect the exhibition of three supervised algorithms for improving Parkinson disease analysis by detection.Methods:I utilized three AI methods for the detection of Parkinson disease datasets. SVM, KNN, and LR were utilized for the forecast of Parkinson Disease. The exhibition of the classifiers was assessed via recall, precision, f 1 extent, and precision. Results:SVM shows the accuracy level of 100% for Parkinson disease prediction. LR achieved the second-highest classification accuracy of 97%. Also, as far as precision for dissecting Parkinson illness datasets, KNN acquired the worst performance (i.e. 60%).Conclusion:My findings showed that the SVM obtained the highest performance for analyzing the Parkinson datasets. This perusal has emphasized the current of Parkinson research aptitude and scope in connection to clinical research fields by machine learning techniques. That will be a viable effect in the field of Parkinson disease