Detection of Atrial Fibrillation Episodes in Long-Term Heart Rhythm Signals Using a Support Vector Machine

Autor: Radana Kahankova, Tomasz Kupka, Janusz Jezewski, Janusz Wrobel, Michal Jezewski, Robert Czabanski, Adam Matonia, Radek Martinek, Krzysztof Horoba, Jacek M. Leski
Jazyk: angličtina
Rok vydání: 2020
Předmět:
medicine.medical_specialty
Support Vector Machine
Databases
Factual
Feature vector
02 engineering and technology
030204 cardiovascular system & hematology
lcsh:Chemical technology
Biochemistry
Asymptomatic
Article
Analytical Chemistry
03 medical and health sciences
Electrocardiography
0302 clinical medicine
Heart arrhythmia
Heart Rate
Internal medicine
Heart rate
Atrial Fibrillation
0202 electrical engineering
electronic engineering
information engineering
Medicine
Humans
lcsh:TP1-1185
Diagnosis
Computer-Assisted
Electrical and Electronic Engineering
Instrumentation
AF detection
business.industry
Atrial fibrillation
Signal Processing
Computer-Assisted
HRV features
medicine.disease
Atomic and Molecular Physics
and Optics
Heart Rhythm
Support vector machine
atrial fibrillation (AF)
Cardiology
atrial fibrillation (AF)
cardiovascular system
020201 artificial intelligence & image processing
support vector machine (SVM)
medicine.symptom
business
Classifier (UML)
Algorithms
heart rate variability (HRV)
Zdroj: Sensors
Volume 20
Issue 3
Sensors (Basel, Switzerland)
Sensors, Vol 20, Iss 3, p 765 (2020)
ISSN: 1424-8220
DOI: 10.3390/s20030765
Popis: Atrial fibrillation (AF) is a serious heart arrhythmia leading to a significant increase of the risk for occurrence of ischemic stroke. Clinically, the AF episode is recognized in an electrocardiogram. However, detection of asymptomatic AF, which requires a long-term monitoring, is more efficient when based on irregularity of beat-to-beat intervals estimated by the heart rate (HR) features. Automated classification of heartbeats into AF and non-AF by means of the Lagrangian Support Vector Machine has been proposed. The classifier input vector consisted of sixteen features, including four coefficients very sensitive to beat-to-beat heart changes, taken from the fetal heart rate analysis in perinatal medicine. Effectiveness of the proposed classifier has been verified on the MIT-BIH Atrial Fibrillation Database. Designing of the LSVM classifier using very large number of feature vectors requires extreme computational efforts. Therefore, an original approach has been proposed to determine a training set of the smallest possible size that still would guarantee a high quality of AF detection. It enables to obtain satisfactory results using only 1.39% of all heartbeats as the training data. Post-processing stage based on aggregation of classified heartbeats into AF episodes has been applied to provide more reliable information on patient risk. Results obtained during the testing phase showed the sensitivity of 98.94%, positive predictive value of 98.39%, and classification accuracy of 98.86%. Web of Science 20 3 art. no. 765
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje