Cardiovascular-Risk-Prediction

Project Overview

This project aims to predict the 10-year risk of future coronary heart disease (CHD) in patients using machine learning techniques. By analyzing various health indicators and lifestyle factors, we develop a model that can assist healthcare professionals in identifying high-risk individuals and implementing preventive measures.

Skills and Technologies:

• Python

• Data Analysis: Using Python libraries such as Pandas and NumPy for data manipulation and analysis.

• Data Visualization: Employing Matplotlib and Seaborn for creating insightful visualizations of the dataset.

• Machine Learning: Implementing various classification algorithms including Logistic Regression, K-Nearest Neighbors, Decision Trees, and Random Forests using Scikit-learn.

• Feature Engineering: Performing data preprocessing tasks such as handling missing values, encoding categorical variables, and scaling numerical features.

• Model Evaluation: Utilizing cross-validation techniques and various performance metrics (accuracy, F1-score, ROC-AUC) to assess model performance.

• Hyperparameter Tuning: Applying Grid Search to optimize model parameters for improved performance.

• Statistical Analysis: Using libraries like StatsModels for in-depth statistical modeling.

Business Impact

1. Early Risk Identification: By accurately predicting the 10-year risk of coronary heart disease, healthcare providers can identify high-risk patients early, enabling timely interventions and preventive care.
2. Resource Allocation: Healthcare systems can use these predictions to allocate resources more efficiently, focusing on patients with higher risk profiles.
3. Personalized Care Plans: The model's insights can help in developing personalized treatment and lifestyle modification plans for patients based on their risk factors.
4. Cost Reduction: Early intervention and prevention strategies based on accurate risk prediction can potentially reduce the long-term healthcare costs associated with treating advanced heart disease.

Dataset

The dataset used in this project contains information about patients, with 17 features for each individual. These features include:

• id: Unique identifier for each patient
• age: Age of the patient
• education: Education level (1-4)
• sex: Gender (M/F)
• is_smoking: Smoking status (YES/NO)
• cigsPerDay: Number of cigarettes smoked per day
• BPMeds: Blood pressure medication usage (0/1)
• prevalentStroke: History of stroke (0/1)
• prevalentHyp: Presence of hypertension (0/1)
• diabetes: Presence of diabetes (0/1)
• totChol: Total cholesterol level
• sysBP: Systolic blood pressure
• diaBP: Diastolic blood pressure
• BMI: Body Mass Index
• heartRate: Heart rate
• glucose: Glucose level
• TenYearCHD: 10-year risk of coronary heart disease (target variable, 0/1)

This comprehensive dataset includes demographic information, lifestyle factors, medical history, and various health measurements, providing a solid foundation for developing an accurate predictive model.

Key Features of the Project

• Exploratory Data Analysis (EDA): Thorough analysis to uncover patterns and relationships in the dataset.
• Feature Engineering: Advanced techniques to capture complex interactions between health indicators.
• Machine Learning Models: Implementation of various models to predict CHD risk.
• Model Evaluation and Interpretation: Providing insights into the most important risk factors and the model’s performance.

Thank You. Let’s keep learning and growing together!