Dark Mode
UCI Multi-Site Cardiology Indicators
Patient Health Records & Digital Health
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Clinical data collected from four distinct international medical centres focusing on cardiovascular health indicators. It features key physiological measurements and diagnostics compiled to facilitate the prediction and study of heart disease incidence. The dataset aggregates various patient characteristics and vital signs, making it an excellent resource for developing machine learning models aimed at early risk assessment and diagnosis.
Columns
- Age: The age of the individual, ranging from 20 to 80.
- Sex: The gender of the individual, represented as a binary value (1 for male, 0 for female).
- ChestPainType: Categorises the type of chest pain experienced. Values include Typical angina (1), Atypical angina (2), Non-anginal pain (3), and Asymptomatic (4).
- RestingBP: The individual’s resting blood pressure, measured in mm Hg.
- Cholesterol: The individual’s cholesterol level, measured in mg/dl.
- FastingBS: Indicates whether the individual’s fasting blood sugar is greater than 120 mg/dl (1=true, 0=false).
- RestingECG: Data related to the individual’s electrocardiogram.
- MaxHR: The maximum heart rate achieved by the individual.
- ExerciseAngina: Indicates whether the individual experiences chest pain induced by exercise (1=yes, 0=no).
- Oldpeak: Data concerning the slope.
- HeartDisease: The binary target variable indicating the presence (1) or absence (0) of heart disease.
Distribution
The primary data file is generally distributed in CSV format, specifically named
UCI_Heart_Disease_Dataset_Combined.csv, and has a total file size of 91.37 kB. It contains 11 columns and consists of 2,943 valid records. All features show 0% missing or mismatched data, indicating high data quality suitable for immediate analysis. The expected update frequency for this specific aggregation is never.Usage
This data is highly suitable for building and testing predictive models for cardiovascular conditions. Ideal applications include creating classification algorithms to assess a patient's risk of heart disease based on clinical indicators, performing statistical analysis to identify primary risk factors across different demographics, and developing educational tools in biostatistics and health informatics.
Coverage
The underlying data is compiled from studies conducted across four locations: Cleveland, Hungary, Switzerland, and the VA Long Beach facility. Demographically, the records cover individuals whose ages span from 20 to 80. There is a noted imbalance in the gender distribution, with approximately 75% of records corresponding to male subjects.
License
Attribution 4.0 International (CC BY 4.0)
Who Can Use It
- Machine Learning Engineers: For training robust diagnostic models.
- Medical Researchers: For epidemiological studies of cardiac health risk factors.
- Data Scientists: For advanced statistical modelling and feature importance ranking in clinical settings.
- Students: For academic projects requiring real-world health data.
Dataset Name Suggestions
- UCI Multi-Site Cardiology Indicators
- Combined Cardiovascular Risk Factors
- Clinical Heart Disease Prediction Data
Attributes
Original Data Source: UCI Multi-Site Cardiology Indicators
QUALITYLoading...