Determination of factors related to coronary heart diseases by associative classification technique

Abstract

Objective:The goal of this study is to categorize CHD using the relational classification approach on a CHD dataset made up of open access patients with and without CHD, as well as to disclose the disease's relationship to the risk factors that cause CHD. Methods:The associative classification model was applied to the open-access data set "CHD" in this study. The performance of the model was evaluated by accuracy, specificity, negative predictive value. According to the results of the associative classification model, the factors associated with the disease were determined by specific rules. groups, examined using Mann-Whitney U, Pearson Chi-square test, and Fisher's Exact test. p<0.05 values were considered statistically significant. Results: For the associative classification model applied to the data set, the results of the performance metrics that specificity, accuracy, and negative predictive value were calculated as 0.995, 0.852, 0.854, respectively. Conclusion:The conclusions of this investigation revealed that the study conducted on the CHD data set with the associative classification model yielded successful results. Since the results obtained from the associative classification model reveal certain rules, it is very easy for users to understand and the results can be easily interpreted. Thus, the findings obtained with this model can be used quite easily in preventive medicine practices.