Downloads: 0 | Views: 170
Research Paper | Computer Science & Engineering | India | Volume 12 Issue 4, April 2023
Detecting Parkinson's Disease Using XGBoost
Utkarsh Jain | Manveer Singh Malhi | Dr. Nithya [11]
Abstract: Parkinson'sdisease is a progressive neurodegenerative disorder that affects motor system, causing symptoms such as tremors, stiffness and difficulty in movement. Early detection of the disease is crucial for effective treatment and management. In recent years, machine learning techniques have been applied to accurately diagnose Parkinson's disease using various data sources, including clinical features, neuroimaging, and biological markers. The aim of study was to develop a machine learning algorithm model for detecting Parkinson's disease (PD) using the XGBoost algorithm. The study used data from the UCI ML Parkinson's disease dataset, which contains biomedical measurement from individuals with and without PD. The dataset was preprocessed and then split into training and testing sets. XGBoost was applied to the training data and tuned using cross-validation to optimize its performance. We used an XGBClassifier for this and made use of the sklearn library to prepare the dataset. This gives us an accuracy of 94.87%, which is great considering the number of lines of code in this python project. The results of this study suggest that XGBoost can be a promising approach for early diagnosis of Parkinson's disease, which can lead to better patient outcomes and improved quality of life.
Keywords: Machine learning, Deep Learning, Decision tree, Logistic Regression, Gradient Boosting Algorithm
Edition: Volume 12 Issue 4, April 2023,
Pages: 1339 - 1343