A synthetic healthcare dataset containing 10,000 patient records and 30 carefully designed clinical, demographic, and lifestyle features for heart disease prediction.
This project was developed to support Machine Learning, Data Science, Healthcare Analytics, and Educational projects.
This repository provides a complete pipeline for generating a realistic synthetic heart disease dataset using Python. The generated dataset is suitable for:
- Machine Learning Classification
- Exploratory Data Analysis (EDA)
- Data Visualization
- Healthcare Analytics
- Educational and Research Projects
- Feature Engineering
The dataset simulates realistic relationships between patient characteristics, lifestyle habits, laboratory measurements, and cardiovascular risk factors.
| Property | Value |
|---|---|
| Records | 10,000 |
| Features | 30 |
| Missing Values | 0 |
| Duplicate Records | 0 |
| Target Variable | Heart_Disease |
- Patient_ID
- Age
- Gender
- Height_cm
- Weight_kg
- BMI
- Smoking
- Alcohol
- Physical_Activity
- Stress_Level
- Sleep_Hours
- Family_History
- Diabetes
- Hypertension
- Cholesterol
- HDL_Cholesterol
- LDL_Cholesterol
- Triglycerides
- Resting_BP
- Fasting_Blood_Sugar
- Max_Heart_Rate
- Oxygen_Saturation
- Resting_ECG
- Exercise_Angina
- ST_Depression
- Chest_Pain_Type
- Daily_Steps
- Water_Intake
- Medication
- Heart_Disease
Heart_Disease
- 0 → No Heart Disease
- 1 → Heart Disease
- Python
- Pandas
- NumPy
Heart-Disease-Dataset/
│
├── dataset.py
├── heart_disease_risk_prediction.csv
├── README.md
├── requirements.txt
└── LICENSE
- Clone this repository.
git clone https://github.com/yourusername/Heart-Disease-Dataset.git- Install dependencies.
pip install -r requirements.txt- Run the dataset generator.
python dataset.pyA new CSV file will be generated automatically.
- Heart Disease Prediction
- Machine Learning Projects
- Classification Tasks
- Healthcare Analytics
- Educational Tutorials
- Data Science Practice
- Kaggle Dataset: https://www.kaggle.com/datasets/mobeenfatimah/heart-disease-risk-prediction-dataset
- Kaggle Notebook: https://www.kaggle.com/code/mobeenfatimah/heart-disease-risk-prediction-eda-ml
This is a synthetically generated dataset created for educational, research, and machine learning purposes. It does not contain real patient records and should not be used for medical diagnosis or clinical decision-making.
Mobeen Fatima
Computer Science Student | Machine Learning & Data Science Enthusiast
⭐ If you found this project useful, consider giving it a Star.