Validation of Baseline Wander Removal and Isoelectric Correction in Electrocardiograms Using Clustering.

The removal of baseline wander from the electrocardiogram does not always correct the isoelectric level of the signal. That is, to enforce reference points for amplitude measurements to 0 volt. In this work new parameters and a modified clustering method is proposed to find the isoelectric bias, which is the amplitude difference between the reference point and 0 volt prior to the isoelectric correction. Validation with old parameters and previous iteration of the clustering method are also performed on the QT database from PhysioNet. Both methods are viable to find the isoelectric bias in the PQ-segment. 3 assessment criteria are used. The first criterion (A) is based on the location of the isoelectric bias with respect to the PQ-segment. The second criterion (B) is based on the absolute difference between the isoelectric bias and median amplitude of the PQ-segment. And the third criterion (C) is the mean and standard deviation of the absolute difference between the isoelectric bias and median amplitude of the PQ-segment.Best results are obtained with the new proposed method with a probability of true detection (PD) of 99.62 pct (A), PD of 98.40 pct (B), mean of 6.28 microvolt (C) and standard deviation of 12.03 microvolt (C) respectively for the criteria mentioned above.