SVM Based ECG Classification Using Rhythm and Morphology Features, ClusternAnalysis and Multilevel Noise Estimation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68081731%3A_____%2F17%3A00487043" target="_blank" >RIV/68081731:_____/17:00487043 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.cinc.org/archives/2017/" target="_blank" >http://www.cinc.org/archives/2017/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.22489/CinC.2017.172-200" target="_blank" >10.22489/CinC.2017.172-200</a>

Jazyk výsledku

angličtina

Název v původním jazyce

SVM Based ECG Classification Using Rhythm and Morphology Features, ClusternAnalysis and Multilevel Noise Estimation

Popis výsledku v původním jazyce

Smartphone-based ECG devices comprise great potential in screening for arrhythmias. However, its feasibility is limited by poor signal quality leading to incorrect rhythm classification. In this study, advanced method for automatic classification of normal rhythm (N), atrial fibrillation (A), other rhythm (O), and noisy records (P) is introduced. Methods: Two-step SVM approach followed by simple threshold based rules was used for data classification. In the first step, various features were derived from separate beats to represent particular events (normal as well as pathological and artefacts) in more detail. Output of the first classifier was used to calculate global features describing entire ECG. These features were then used to train the second classification model. Both classifiers were evaluated on training set via cross-validation technique, and additionally on hidden testing set. Results: In the Phase II of challenge, total F1 score of the method is 0.81 and 0.84 within hidden challenge dataset and training set, respectively. Particular F1 scores within hidden challenge dataset are 0.90 (N), 0.81 (A), 0.72 (O), and 0.55 (P). Particular F1 scores within training set are 0.91 (N), 0.85 (A), 0.76 (O), and 0.73 (P).

Název v anglickém jazyce

SVM Based ECG Classification Using Rhythm and Morphology Features, ClusternAnalysis and Multilevel Noise Estimation

Popis výsledku anglicky

Smartphone-based ECG devices comprise great potential in screening for arrhythmias. However, its feasibility is limited by poor signal quality leading to incorrect rhythm classification. In this study, advanced method for automatic classification of normal rhythm (N), atrial fibrillation (A), other rhythm (O), and noisy records (P) is introduced. Methods: Two-step SVM approach followed by simple threshold based rules was used for data classification. In the first step, various features were derived from separate beats to represent particular events (normal as well as pathological and artefacts) in more detail. Output of the first classifier was used to calculate global features describing entire ECG. These features were then used to train the second classification model. Both classifiers were evaluated on training set via cross-validation technique, and additionally on hidden testing set. Results: In the Phase II of challenge, total F1 score of the method is 0.81 and 0.84 within hidden challenge dataset and training set, respectively. Particular F1 scores within hidden challenge dataset are 0.90 (N), 0.81 (A), 0.72 (O), and 0.55 (P). Particular F1 scores within training set are 0.91 (N), 0.85 (A), 0.76 (O), and 0.73 (P).

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20601 - Medical engineering

Projekt

<a href="/cs/project/GAP102%2F12%2F2034" target="_blank" >GAP102/12/2034: Analýza vztahu mezi elektrickými ději a průtokem krve u srdečních komor</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Computing in Cardiology 2017

ISBN

—

ISSN

2325-887X

e-ISSN

—

Počet stran výsledku

4

Strana od-do

1-4

Název nakladatele

Computing in Cardiology

Místo vydání

Rennes

Místo konání akce

Rennes

Datum konání akce

24. 9. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000450651100150