Ischemia diagnosis using fuzzy association rule mining on ECG signal

A method based on fuzzy association rule mining is proposed for ischemia diagnosis on ECG signal. The proposal provides interpretable and understandable information to doctors as a reference, while rule mining on fuzzy itemsets guarantees that features segmentation before rule extraction is feasible and effective. A set of fuzzy association rules are mined through experiments on the data from European ST-T database, and classification results of ischemia and normal beats using extracted rules obtain values of 83.4%, 80.7%, and 81.4% for sensitivity, specificity, and accuracy, respectively. The proposal aims to become a helpful tool to accelerate the diagnosis of ischemia on ECG signal, and to be expanded to other heart disease diagnosis areas such as hypertensive heart disease and arrhythmia.