Parkinson's Disease Prediction employs advanced machine learning algorithms to analyze data, offering accurate forecasts of potential cases. Through meticulous analysis and model selection, it provides a proactive tool for early detection and intervention. Through rigorous Exploratory Data Analysis (EDA) and the implementation of sophisticated machine learning algorithms, this project endeavors to uncover the underlying causes of Parkinson's disease while simultaneously forecasting potential future cases.
The aim of this project is to delve into the intricate factors contributing to Parkinson's disease and develop a predictive model to identify individuals at risk.
Utilizing a combination of EDA techniques and machine learning algorithms, we have meticulously analyzed data to discern patterns and correlations associated with Parkinson's disease. Key steps include data cleaning, feature engineering, and insightful visualization to extract meaningful insights.
- Logistic Regression
- K-Nearest Neighbors (KNN)
- Random Forest Regressor
- Decision Tree Regressor
- numpy: For efficient numerical operations
- pandas: For data manipulation and analysis
- seaborn: For visually appealing statistical graphics
- matplotlib: For comprehensive data visualization
- Sklearn: For implementing machine learning algorithms
- Logistic Regression: Achieved a test set accuracy of 85.0%
- K-Nearest Neighbors: Demonstrated superior performance with a test set accuracy of 94.0%
- Random Forest Regressor: Equally impressive accuracy of 94.0%
- Decision Tree Regressor: Achieved a commendable accuracy of 91.0%
Through rigorous analysis and experimentation, it has been determined that K-Nearest Neighbors and Random Forest Regressor models exhibit the highest predictive accuracy for Parkinson's disease.