A survey of data mining algorithms used in cardiovascular disease diagnosis from multi-lead ECG data

Remote cardiovascular disease (CVD) diagnosis from ECG plays an important role in healthcare domain. Data mining, the major step in the process of the extraction of knowledge usingdescriptive and predictive algorithms that aid in making proactive decisions, has also been usedfor CVD diagnosis. Recently, diverse techniques have been developed for analyzing the ECGsignals. However, due to the diversity of techniques used, terminologies, performance measuresused in different techniques makes analysis and comparing of results thwarting. The aim of thiswork is to essentially explore and present the analysis of different data mining algorithmsproposed earlier in literature for CVD diagnosis, their advantages and limitations. This paperpresents various techniques for CVD diagnosis using data mining from an ECG signal underfour major phases – ECG Acquisition, ECG Compression, ECG Feature Extraction and ECGdiagnosis. The primary aim of this paper is to categorize the various researches done in thisregard to provide a glossary for interested researchers and to aid in identifying their potentialresearch direction.