Problem
Identify high-risk patients of Heart Disease for early screening and preventive care triage.
Dataset
Heart disease dataset containing patient features such as age, chest pain type, blood pressure, cholesterol, heart rate, and other clinical parameters (~300+ records).
Tools
Python, Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn
Key Steps
- Cleaned and preprocessed dataset
- Performed exploratory data analysis to understand feature relationships
- Built Decision Tree and Random Forest classification models
- Evaluated model performance using accuracy and classification metrics
- Identified key features influencing heart disease prediction
Key Insights
Identified important risk factors such as chest pain type, cholesterol level, and maximum heart rate. Built classification models to support early risk detection and healthcare analytics.