• Jinesh Chudasama
• Sahil More
• Chinmay Shinde
• Sanika Auti
• Krupa Chotai

Parkinson’s Disease, originating from James Parkinson’s 1817 work, represents a pivotal milestone in neurodegenerative disorder history. Understanding its complexities, including both non-motor and motor symptoms, has evolved, emphasising the substantia nigra’s critical involvement in dopaminergic neuron loss. Recent interest focuses on speech analysis for early Parkinson’s detection and monitoring, given the subtle speech alterations preceding motor symptoms. Machine learning, alongside wearable sensor tech, enhances speech analysis tools for accurate Parkinson’s detection. This research paper provides a comprehensive review of speech-based biomarkers, machine learning algorithms, and clinical findings in Parkinson’s disease diagnosis. Notably, Gradient Boosting emerges as the most effective classifier, with superior accuracy and precision, facilitating early intervention and improved patient outcomes.

Parkinson’s disease, Non-Motor Symp tom, Speech Analysis, Early Detection, Machine Learn ing, Gradient Boosting.

"Parkinson's Disease Prediction Using Speech Dataset", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.K181-K188, July-2024, Available :http://www.jetir.org/papers/JETIR2406A22.pdf

"Parkinson's Disease Prediction Using Speech Dataset", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. ppK181-K188, July-2024, Available at : http://www.jetir.org/papers/JETIR2406A22.pdf