2022
DOI: 10.3390/app12147248
|View full text |Cite
|
Sign up to set email alerts
|

Ventricular Fibrillation and Tachycardia Detection Using Features Derived from Topological Data Analysis

Abstract: A rapid and accurate detection of ventricular arrhythmias is essential to take appropriate therapeutic actions when cardiac arrhythmias occur. Furthermore, the accurate discrimination between arrhythmias is also important, provided that the required shocking therapy would not be the same. In this work, the main novelty is the use of the mathematical method known as Topological Data Analysis (TDA) to generate new types of features which can contribute to the improvement of the detection and classification perfo… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
10
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
8

Relationship

2
6

Authors

Journals

citations
Cited by 8 publications
(10 citation statements)
references
References 69 publications
0
10
0
Order By: Relevance
“…In paper [21], two input data to the classifier are evaluated: TDA features and Persistence Diagram Image (PDI). Using the reduced TDA-obtained features, a high average accuracy near 99% was observed when discriminating four types of rhythms and specificity values higher than 97.16% in all cases.…”
Section: Discussionmentioning
confidence: 99%
“…In paper [21], two input data to the classifier are evaluated: TDA features and Persistence Diagram Image (PDI). Using the reduced TDA-obtained features, a high average accuracy near 99% was observed when discriminating four types of rhythms and specificity values higher than 97.16% in all cases.…”
Section: Discussionmentioning
confidence: 99%
“…Xia et al [ 72 ] obtained high performance values (Sen = 98.15% and Spe = 96.01% for VF, and Sen = 96.01% and Spe = 98.15% for ) using Lempel–Ziv and Empirical Mode Decomposition (EMD) with selected clean episodes of and . Mjahad et al [ 73 ] achieved an accuracy, sensitivity, and specificity values of 98.68%, 92.72%, and 99.53%, respectively employing TDA. Kaur and Singh [ 74 ] used Empirical Mode Decomposition (EMD) and approximate entropy with selected and episodes from the MIT-BIH database, achieving moderate classification performance (Sen = 90.47%, Spe = 91.66%, and Acc = 91.17%).…”
Section: Discussionmentioning
confidence: 99%
“…This set of works primarily targets the implementation on external defibrillators (AEDs) and implantable cardioverter defibrillators (ICDs), distinguishing between shockable and non-shockable rhythms (considering both and as shockable). Mjahad et al [ 73 ] utilized TDA and obtained Sens = 99.03%, Spe = 99.67%, and Acc = 99.51% in discriminating episodes. Acharya et al [ 76 ] proposed an eleven-layer convolutional neural network (CNN) for shockable and non-shockable arrhythmia classification, obtaining Sen = 95.32%, Spe = 91.04%, and Acc = 93.20%.…”
Section: Discussionmentioning
confidence: 99%
“…A similar approach was taken by Mjahad, et al [22], who applied TDA to generate novel features contributing to improve both detection and classification performance of cardiac arrhythmias such as Ventricular Fibrillation (VF) and Ventricular Tachycardia (VT). The electrocardiographic (ECG) signals used for this evaluation were obtained from the standard MIT-BIH and AHA databases.…”
Section: Ecg Data and Heart Rate Signalsmentioning
confidence: 99%