Application of Adaptive Filtering and Linear Regression for Determining T-Wave Limits in Neonatal ECG

Abstract

Two algorithms have been identified, namely the adaptive filtering method and tangent method, which can be used to automatically detect the end of T-wave in neonatal ECG for determining the QT and QTc duration. By modifying the initial conditions and parameters in the algorithms, both algorithms have been successfully applied in real time to process real neonatal ECGs with various noise levels. The accuracy and the precision of both algorithms were examined by comparing the result with manual readings done by a cardiologist. The algorithms can be used to analyze neonatal ECG for long QT syndrome in real time and automatically to aid early diagnosis, subjected to further test and verification.