Using decision tree for diagnosing heart disease patients

Authors:
Mai Shouman;Tim Turner;Rob Stocker
Affiliations:
University of New South Wales at the Australian Defence Force Academy, Canberra ACT;University of New South Wales at the Australian Defence Force Academy, Canberra ACT;University of New South Wales at the Australian Defence Force Academy, Canberra ACT
Venue:
AusDM '11 Proceedings of the Ninth Australasian Data Mining Conference - Volume 121
Year:
2011

Citing 11
Cited 3

On the Handling of Continuous-Valued Attributes in Decision Tree Generation

Machine Learning
A Comparative Analysis of Methods for Pruning Decision Trees

IEEE Transactions on Pattern Analysis and Machine Intelligence
Decision Trees: An Overview and Their Use in Medicine

Journal of Medical Systems
A Primer for Understanding and Applying Data Mining

IT Professional
Multi-interval Discretization Methods for Decision Tree Learning

SSPR '98/SPR '98 Proceedings of the Joint IAPR International Workshops on Advances in Pattern Recognition
Data Mining: Concepts and Techniques

Data Mining: Concepts and Techniques
Identification of ischemic heart disease via machine learning analysis on magnetocardiograms

Computers in Biology and Medicine
Effective diagnosis of heart disease through neural networks ensembles

Expert Systems with Applications: An International Journal
ChiMerge: discretization of numeric attributes

AAAI'92 Proceedings of the tenth national conference on Artificial intelligence
Data mining techniques for cancer detection using serum proteomic profiling

Artificial Intelligence in Medicine
Artificial neural networks and risk stratification: A promising combination

Mathematical and Computer Modelling: An International Journal

A data mining approach for diagnosis of coronary artery disease

Computer Methods and Programs in Biomedicine
An approach for Ewing test selection to support the clinical assessment of cardiac autonomic neuropathy

Artificial Intelligence in Medicine
Improving classifications for cardiac autonomic neuropathy using multi-level ensemble classifiers and feature selection based on random forest

AusDM '12 Proceedings of the Tenth Australasian Data Mining Conference - Volume 134

Quantified Score

Hi-index	0.00

Visualization

Abstract

Heart disease is the leading cause of death in the world over the past 10 years. Researchers have been using several data mining techniques to help health care professionals in the diagnosis of heart disease. Decision Tree is one of the successful data mining techniques used. However, most research has applied J4.8 Decision Tree, based on Gain Ratio and binary discretization. Gini Index and Information Gain are two other successful types of Decision Trees that are less used in the diagnosis of heart disease. Also other discretization techniques, voting method, and reduced error pruning are known to produce more accurate Decision Trees. This research investigates applying a range of techniques to different types of Decision Trees seeking better performance in heart disease diagnosis. A widely used benchmark data set is used in this research. To evaluate the performance of the alternative Decision Trees the sensitivity, specificity, and accuracy are calculated. The research proposes a model that outperforms J4.8 Decision Tree and Bagging algorithm in the diagnosis of heart disease patients.