
Reconstruction of Limb Leads Recorded on The Subject’s Torso
Author(s) -
Judyta Salamon,
Zuzanna Puzio,
Lukasz Koltowski,
Grzegorz Wroblewski,
Adrian Maciejewski
Publication year - 2020
Publication title -
2019 computing in cardiology (cinc)
Language(s) - English
Resource type - Conference proceedings
SCImago Journal Rank - 0.257
H-Index - 55
ISSN - 2325-887X
ISBN - 978-1-7281-6936-1
DOI - 10.22489/cinc.2019.262
Subject(s) - bioengineering , computing and processing , signal processing and analysis
Standard limb electrode position may be challenging when a patient is subjected to a stress test, due to limb movement. Mason-Likar position compensates for such difficulties, as all limbs electrodes are placed on the torso. On the other hand, such recordings show a number of differences when compared to standard placement. We wanted to find a compromise between them, by placing limb leads closer together on the human body to avoid motion artifacts and using signal reconstruction to make the trace diagnostic.Reconstruction has been performed based on conversion matrices, that were created using linear and lasso regression, polynomials fitting and Support Vector Regression (SVR).For each method, the reconstructed signal has been compared to the one recorded in reference positions. The results of each method showed results with a mean difference between all points from 0.019 mV to 0.045 mV. For linear regression the mean difference between R wave amplitudes was 0.1 mV, 0.03 mV for Q waves and 0.08 mV for S wave. The best results were achieved with the use of linear regression.