Study on Datamining Techinique for Foot Disease Prediction

Datamining is a method to focus on important and meaningful knowledge in large data. Decision tree, one of typical technique in datamining, is process to predict a couple of subgroup from object group by observing relation. The purpose of the study was to find out significant knowledge between two c...

Full description

Saved in:
Bibliographic Details
Published in2014 International Conference on IT Convergence and Security (ICITCS) pp. 1 - 4
Main Authors Jung-Kyu Choi, Chan Il Yoo, Kyung-Ah Kim, Yonggwan Won, Jung-Ja Kim
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2014
Subjects
Algorithm design and analysis
Analytical models
Decision trees
Diseases
Educational institutions
Foot
Predictive models
Online AccessGet full text
DOI10.1109/ICITCS.2014.7021816

Cover

More Information
Summary:Datamining is a method to focus on important and meaningful knowledge in large data. Decision tree, one of typical technique in datamining, is process to predict a couple of subgroup from object group by observing relation. The purpose of the study was to find out significant knowledge between two complex disease and symptoms in clinical data of the Foot clinic by decision tree. The first medical examination clinical data of 400 patients diagnosed with complex disease were used for analysis. A dependent variable was composed of four complex disease groups. Independent variables were selected with 14 variables closely related to disease. After object data were divided into training data and test data, C5.0 algorithm was applied for analysis. In conclusion, 13 diagnosis rules were created and major symptom information was verified. On the basis of this study, other decision tree algorithms will be applied to develop additional model and perform comparison analysis for producing an ideal model from now on.
DOI:10.1109/ICITCS.2014.7021816