Automatic detection of atrial fibrillation and other arrhythmias in holter ECG recordings using rhythm features and neural networks

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68081731%3A_____%2F17%3A00487041" target="_blank" >RIV/68081731:_____/17:00487041 - isvavai.cz</a>

Result on the web

<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.2017.364-057" target="_blank" >10.22489/CinC.2017.364-057</a>

Result language

angličtina

Original language name

Automatic detection of atrial fibrillation and other arrhythmias in holter ECG recordings using rhythm features and neural networks

Original language description

Atrial fibrillation (AF) is a disease affecting 1-2 % of the population. Due to its episodic behavior, it is usually detected using Holter recordings. While various AF detection methods have been described in the past, it still remains problematic because holter recordings may contain other arrhythmias (OA) and, moreover, they may be influenced by patient movements. In accordance with the Physionet Challenge 2017, we propose an autonomous and robust method of distinguishing between pathological and normal recordings. First, QRS complexes are identified using envelograms (8-25 Hz and 70-90 Hz). Detected QRS complexes are clustered into morphology groups using a raw ECG signal. If too many morphology groups are produced or less than four QRS complexes are detected, the process is aborted and the recording is considered too noisy. Next, a median shape for the first and the second morphological group of QRS complexes is built. Features are extracted from averaged shapes, from the rhythm of major morphology QRS complexes, from QRS correlation to template shapes and from the convolutional neural network. 277 features are fed into the neural network, resulting in three outputs. The 120 most important features, as well as outputs from the neural network, are fed into a bagged tree ensemble. Machine-learning algorithms and logical rules were trained using 8,138 files from a reduced training set. The resultant F1 score measured using hidden test set (3,658 recordings) was 0.81 (normal 0.91, AF 0.80, OA 0.74)

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

20602 - Medical laboratory technology (including laboratory samples analysis; diagnostic technologies) (Biomaterials to be 2.9 [physical characteristics of living material as related to medical implants, devices, sensors])

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

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

Publication year

2017

Confidentiality

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

Article name in the collection

Computing in Cardiology 2017

ISBN

—

ISSN

2325-887X

e-ISSN

—

Number of pages

4

Pages from-to

1-4

Publisher name

Computing in Cardiology

Place of publication

Rennes

Event location

Rennes

Event date

Sep 24, 2017

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000450651100320