Deriving the 12-lead ECG from an EASI-lead system via support vector regression

Abstract

The measuring of all 12-lead electrocardiogram (ECG) is often cumbersome and impractical especially on a long term monitoring. In 1988, Gordon Dower has introduced an EASI-lead system, where only 5 electrodes are used. In order to gain all 12-lead ECG back from this EASI-lead system, Dower’s equation was proposed then. Ever since various attempts have been explored to improve the synthesis accuracy, mostly via Linear regression. This paper presents how Support Vector Regression (SVR) is used to find a set of transfer function for deriving the 12-lead ECG from EASI-lead system. The experiments were conducted to compare the results those of SVR against those of Linear regression and those of Dower’s method. The experimental results have shown that the best performance amongst those methods with the minimum of RMSE for all signals with the standard 12-lead ECG was obtained by SVR, followed by Linear regression and Dower’s equation, respectively.