Research Article
Can the Regression Trees Be Used to Model Relation Between ECG Leads?
672 downloads
@INPROCEEDINGS{10.1007/978-3-319-47063-4_50, author={Ivan Tomasic and Roman Trobec and Maria Lind\^{e}n}, title={Can the Regression Trees Be Used to Model Relation Between ECG Leads?}, proceedings={Internet of Things. IoT Infrastructures. Second International Summit, IoT 360° 2015, Rome, Italy, October 27-29, 2015. Revised Selected Papers, Part I}, proceedings_a={IOT360}, year={2017}, month={1}, keywords={ECG Leads synthesis Derived electrocardiograms Regression trees Differential leads Electrocardiography Wireless electrodes}, doi={10.1007/978-3-319-47063-4_50} }- Ivan Tomasic
Roman Trobec
Maria Lindén
Year: 2017
Can the Regression Trees Be Used to Model Relation Between ECG Leads?
IOT360
Springer
DOI: 10.1007/978-3-319-47063-4_50
Abstract
Presented is a preliminary study that investigates regression trees application for the purpose of mapping relationship between three differential ECG leads and leads of the 12-lead ECG. The approach was evaluated on a single ECG measurement on which it was superior to two syntheses performed by universal and personalized linear transformations, in terms of correlation coefficients between the synthesized and measured leads. A prominent imperfection however is that the regression trees can output only a limited number of values equal to the number of leaf nodes. The paper indicates some ideas on how to overcome this deficiency.
Copyright © 2015–2025 ICST
