Method and Process Mining Based Software for ECG Analysis and Arrhythmia Detection

Currently, the use of neural network based solutions in medical decision support systems remains popular. In order to overcome the hidden decision-making process called “black box”, the authors propose to use the “white box” principle based on the process mining approach. The aim of the work is to develop and implement a process mining based method of electrocardiosignal analysis and arrhythmia detection. Pan-Tompkins algorithm for electrocardiosignal signal analysis and ProM 6.11 framework for software implementation were used. As a results a new intelligent process mining based electrocardiosignal analysis method is proposed. It consists of conversion of digital data of cardiac signal into event log, construction of Petri net and construction of diagnostic decision tree. The original plugin generates the event log in the .xes format using Pan-Tompkins algorithm. ProM 6.11 AlphaMiner plugin generates a Petri net that reflects the relationship of events in the log. The resulting event log allows building a diagnostic decision tree using ProM 6.11 discovery of the process data-flow plugin. The study demonstrates the applicability of the proposed method using normal and arrhythmic cardiac signal records from PhysioNet database. The proposed solution on the base of process mining technology and ProM 6.11 framework allows implementing software for transparent analysis of cardiac signals data for medical decision support systems. The next step is to conduct statistical assessments of the effectiveness of the proposed solution and to expand the number of informative parameters used for analysis.