• Riya Ganesh Sevekar
• Nihal Arvind Baranwal
• Dr. Santosh Kumar Singh
• Mr.Amit Kunar Pandey

Parkinson's disease (PD) is a progressive neurodegenerative disorder associated with an apparent dilemma in the precise prediction of clinical outcomes. In this study, the performance of five different machine learning models—Random Subspace, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Naive Bayes, and Ridge Regression—is evaluated using clinical data related to PD patients. The considered machine learning models covered both traditional statistical approaches and modern deep learning techniques. In comparison with other models, Random Subspace could learn best about 94.87% and thus perform well with large complex data. As CNN and RNN are deep learning architectures, their accuracies were at 89.74% and 79.49%, respectively. Other architectures were proven to be successful in the exploration of complex patterns in clinical features. A linear approach, Ridge Regression, reached an accuracy of 92.31%, and Naive Bayes had the lowest accuracy of 71.79%, as it was modeling high-dimensional and non-linear data. The results do thus indicate the great potential of the deep learning models, such as CNN and RNN, and ensemble techniques like Random Subspace, in enhancing predictive modeling for Parkinson's disease. From such a comparative analysis, there can be contributory insights toward developing more accurate and reliable tools in clinical decision-making and personalized patient care in PD management.

Machine Learning, Random Subspace, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Naive Bayes, Ridge Regression, Clinical Outcome Prediction

"Deep Learning Models for Predicting Clinical Outcomes in Parkinson’s Diseases", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 10, page no.c226-c237, October-2024, Available :http://www.jetir.org/papers/JETIR2410325.pdf

"Deep Learning Models for Predicting Clinical Outcomes in Parkinson’s Diseases", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 10, page no. ppc226-c237, October-2024, Available at : http://www.jetir.org/papers/JETIR2410325.pdf