In 1842, Carlo Matteucci, Professor of Physics at the University of Pisa, shows that an electric current accompanies each heartbeat. The first electrocardiogram was recorded from man in 1887 by Augustus Waller in Switzerland. During its history of over 150 years, the basic principle of electrocardiography, recording the electric potentials generated by the depolarizing and repolarizing cardiac cells on the surface of the thorax, has remained unchanged. This method is so simple and diagnostically powerful that ECG is still the most frequently applied clinical method in diagnosing cardiac diseases and in monitoring the patient's health. Despite the simple basic principle, our understanding of the generation of the ECG signal, its connection to the clinical status of the patient and the recording instrumentation has progressed tremendously. For a great deal this progress has been accelerated by the developing technology and computer science. Much of the research effort has been so far aimed at the automated interpretation of electrocardiograms (ECG's), for which the interpretative rationale is well established. Thanks to the latest advances in technology, a group of far more informative techniques, namely Body Surface Mapping (BSM), or more precisely Body Surface Potential Mapping (BSPM), Non-Invasive Electrical Imaging of Heart (NEIH) and ECG Imaging (ECGI), are becoming more widely available. Main automated interpretation of electrocardiograms techniques are all model based. A review of main source model approaches is presented, including latest results based on Machine Learning, on Fuzzy Logic, Kernel Machines (KM), and Support Vector Machines (SVM). Main Syntactic vs. Statistical Pattern Recognition approaches are reviewed and discussed.

Automated ECG Classification and Interpretation

FIORINI, RODOLFO
2005-01-01

Abstract

In 1842, Carlo Matteucci, Professor of Physics at the University of Pisa, shows that an electric current accompanies each heartbeat. The first electrocardiogram was recorded from man in 1887 by Augustus Waller in Switzerland. During its history of over 150 years, the basic principle of electrocardiography, recording the electric potentials generated by the depolarizing and repolarizing cardiac cells on the surface of the thorax, has remained unchanged. This method is so simple and diagnostically powerful that ECG is still the most frequently applied clinical method in diagnosing cardiac diseases and in monitoring the patient's health. Despite the simple basic principle, our understanding of the generation of the ECG signal, its connection to the clinical status of the patient and the recording instrumentation has progressed tremendously. For a great deal this progress has been accelerated by the developing technology and computer science. Much of the research effort has been so far aimed at the automated interpretation of electrocardiograms (ECG's), for which the interpretative rationale is well established. Thanks to the latest advances in technology, a group of far more informative techniques, namely Body Surface Mapping (BSM), or more precisely Body Surface Potential Mapping (BSPM), Non-Invasive Electrical Imaging of Heart (NEIH) and ECG Imaging (ECGI), are becoming more widely available. Main automated interpretation of electrocardiograms techniques are all model based. A review of main source model approaches is presented, including latest results based on Machine Learning, on Fuzzy Logic, Kernel Machines (KM), and Support Vector Machines (SVM). Main Syntactic vs. Statistical Pattern Recognition approaches are reviewed and discussed.
2005
Proc. 2005 Elaborazione dei Segnali Biomedici ed Interpretazione Diagnostica
ECG; Model Based Automated Interpretation; BSM; BSPM; NEIH; ECGI; KM; SVM; Statistical Pattern recognition; Sybtactic Pattern Recognition
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/657969
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact