Automatic QT interval measurement using rule-based gradient method

In this work, we address the problem of fully automated QT-interval measurement. The method is based on detecting the Q and T points via gradient method accordingly to the beat morphology. Development and validation of the algorithm has been done using the PTB Diagnostic ECG Database prepared for Computers in Cardiology Challenge 2006. RR analysis is used for selection of the beat on which QT interval is measured. The beginning of the Q-wave is detected on all 12-leads. Considering T_off detection, morphology of repolarization phase of the beat is determined. Based on the morphology, rules are applied to particular gradients of repolarization phase to determine the T-wave end. Additional rules were applied to omit signals with high probability of the wrong QT interval measurement. With our method we have reached the score of 35.58 ms.