A new approach for TU complex characterization

In this paper, we present a new TU complex detection and characterization a lgorithm that consists of two stages; the first is a mathematical modeling of the electrocardiographic segment after QRS complex; the second uses clas sic threshold comparison techniques, over the signal and its first and seco nd derivatives, to determine the significant points of each wave. Later, bo th T and U waves are morphologically classified. Amongst the principal innovations of this algorithm is the inclusion of U-w ave characterization and a mathematical modeling stage, that avoids many of the problems of classic techniques when there is a ton signal-to-noise rat io or when wave morphology is atypical. The results of the algorithm validation with the recently appeared QT datab ase are also shown, For T waves these results are better when compared to o ther existing algorithms. U-wave results cannot be contrasted with other al gorithms as, to our know ledge, none are available, Examples showing the ca uses of principal discrepancies between our algorithm and the QT database a nnotations are also given, and some ways of attempting to improve and benef it from the proposed algorithm are suggested.