Heart‑UCI‑Dataset Overview

Basic Information

• Name: Heart‑UCI‑Dataset
• Problem Type: Binary Classification
• Domain: Health, Biology
• Categories: Machine Learning > Classification, Natural and Physical Sciences > Biology, Social and Cognitive Sciences > Society > Health

Content

• Number of Attributes: 76 total, 14 commonly used
• Target Field: Presence of heart disease, integer values 0 (none) to 4

Common Attribute Information

1. Age
2. Sex
3. Chest Pain Type (4 values)
4. Resting Blood Pressure
5. Serum Cholesterol (mg/dl)
6. Fasting Blood Sugar > 120 mg/dl
7. Resting ECG Results (0,1,2)
8. Maximum Heart Rate
9. Exercise‑Induced Angina
10. ST Depression Relative to Rest
11. ST Slope at Peak Exercise
12. Number of Major Vessels (0‑3) – fluoroscopy
13. Thal: 3 = normal; 6 = fixed defect; 7 = reversible defect

Source and Acknowledgments

• Creators:
  1. Hungarian Institute of Cardiology, Budapest: Andras Janosi, M.D.
  2. University Hospital Zurich, Switzerland: William Steinbrunn, M.D.
  3. University Hospital Basel, Switzerland: Matthias Pfisterer, M.D.
  4. V.A. Medical Center, Long Beach and Cleveland Clinic Foundation: Robert Detrano, M.D., Ph.D.
• Donor: David W. Aha (aha@ics.uci.edu) (714) 856‑8779

Usage

• Research Focus: Distinguish presence (values 1‑4) vs. absence (value 0) of heart disease
• Exploratory Directions: Identify additional trends for predicting cardiovascular events or discovering clear health indicators