Nicolas PASQUIER ♦ Université Côte d'Azur

Atherosclerosis Risk Factors

These datasets were constructed from the publicly available PKDD 2004 Discovery Challenge datasets to study atherosclerosis risk factors:

  • Social-demographic data (age, education, etc.) on 1417 patients with class information on atherosclerosis risk (normal, risk, pathologic) for 1228 patients.
  • Behavioral data (smoking habits, alcohol consumption, sport practice, etc.) for 1417 patients.
  • Biomedical data (blood pressure, cholesterol, glycemia, etc.) resulting from medical analysis for 1417 patients.

The original datasets were pre-processed to generate variables indicating temporal changes in the behavioral and biomedical data for each patient.

Data Files
File Description
Atherosclerosis (ARFF) Archive containing all data in the ARFF (Weka) data format.
Atherosclerosis (MDB) Microsoft Access database containing all data.
Data description Description of the datasets.
Reference

HASAR: Mining sequential association rules for atherosclerosis risk factor analysis, Laurent Brisson, Nicolas Pasquier, Céline Hebert and Martine Collard, Discovery Challenge of the PKDD international conference on Principles of Knowledge Discovery in Databases, 2004.