Dark Mode
Heart Attack Risk Assessment Dataset
Patient Health Records & Digital Health
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This synthetic dataset contains 1,000 patient records generated for health risk assessment and predictive modelling. It includes vital demographic, lifestyle, and biometric health indicators commonly used in cardiovascular and general health research. Each record captures key factors influencing cardiovascular diseases, such as age, cholesterol levels, blood pressure, smoking habits, diabetes status, and heart attack history. It is ideal for research and educational purposes, but users should note it does not represent real patients.
Columns
- age: Patient's age (years).
- sex: Biological sex, encoded as 0 for Female and 1 for Male.
- total_cholesterol: Total cholesterol level (mg/dL).
- ldl: Low-Density Lipoprotein (LDL) cholesterol (mg/dL).
- hdl: High-Density Lipoprotein (HDL) cholesterol (mg/dL).
- systolic_bp: Systolic blood pressure (mmHg).
- diastolic_bp: Diastolic blood pressure (mmHg).
- smoking: Smoking status, with 0 for Non-Smoker and 1 for Smoker.
- diabetes: Diabetes status, with 0 for No and 1 for Yes.
- heart_attack: History of heart attack, with 0 for No and 1 for Yes.
Distribution
This dataset is provided as a CSV file ('updated_version.csv') and is approximately 103.11 kB in size. It comprises 1,000 synthetic patient records and 10 columns, structured for tabular data analysis.
Usage
This dataset is highly suitable for a variety of applications and use cases, including:
- Exploratory Data Analysis (EDA).
- Predictive modelling for heart disease risk.
- Machine learning classification tasks.
- Feature engineering and statistical analysis within the healthcare domain.
- General health risk prediction and cardiovascular analysis.
Coverage
The dataset focuses on synthetic patient data, encompassing a wide age range from 18 to 94 years and including both female and male biological sexes. As it is synthetically generated, it does not represent a specific geographic region or time period, making it generally applicable for research and educational purposes globally.
License
Attribution 4.0 International (CC BY 4.0) License.
Who Can Use It
This dataset is primarily intended for:
- Researchers in health and medical fields.
- Students undertaking data science or machine learning projects.
- Data Scientists and Machine Learning Engineers developing healthcare predictive models.
- Healthcare analysts and statisticians exploring health indicators.
Dataset Name Suggestions
- Heart Attack Risk Assessment Dataset
- Cardiovascular Health Prediction Data
- Synthetic Patient Health Indicators
- Predictive Healthcare Modelling Dataset
- Health Risk Factor Data
Attributes
Original Data Source: Heart Attack Risk Assessment Dataset
QUALITY