A comparison of entropy approaches for AF discrimination

Liu, Chengyu; Oster, Julien; Reinertsen, Erik; Li, Qiao; Zhao, Lina; Nemati, Shamim; Clifford, Gari D.

doi:10.1088/1361-6579/aacc48

Cited by 42 publications

(34 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consistent with the results for the test data from the ALLSTAR database, a peak positive likelihood ratio was observed at the segment window length of 85 beats, where the classi cation accuracy was 0.979 and the AUC of ROC curve was 0.987. Table 7 also shows the performance of AF detection reported by earlier studies that used the PhysioNet database [9,11,13]. The classi cation performance of the CNN models developed in the present study was comparable to or slightly better than those of the earlier studies.…”

Section: Estimation Of Af Burdensupporting

confidence: 64%

“…The comparison of the performance using common dataset from the PhysioNet database showed that the classi cation performance of our models was comparable to or slightly better than those reported for the sophisticated metrics derived from the feature of beat interval time series [9,11,13]. Additionally, the optimal segment window length was 85 beats even for the PhysioNet database.…”

Section: Discussionmentioning

confidence: 53%

“…709). The PhysioNet database were used only for the test data for the comparisons with earlier studies [9,11,13].…”

Section: Data Selectionsmentioning

confidence: 99%

“…The strict criteria were used for the test data from the ALLSTAR database to examine the optimal segment window length for PAF detection. The non-strict criteria were used for the test data from both ALLSTAR and PhysioNet databases to compare the classi cation performance between the models developed in the present study and those reported by earlier studies [9,11,13].…”

Section: Classi Cation Of Test Datamentioning

confidence: 99%

See 3 more Smart Citations

Optimal Length of R-R Interval Segment Window for Lorenz Plot Detection of Paroxysmal Atrial Fibrillation by Machine Learning

Kisohara

Yuda

Ueda

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Heartbeat interval Lorenz plot (LP) imaging is a promising method for detecting atrial fibrillation (AF) in long-term monitoring, but the optimal segment window length for the LP images is unknown. We examined the performance of AF detection by LP images with different segment window lengths by machine learning with convolutional neural network (CNN). LP images with a 32 x 32-pixel resolution of non-overlapping segments with lengths between 10 and 500 beats were created from R-R intervals of 24-h ECG in 52 patients with chronic AF and 58 non-AF controls as training data and in 53 patients with paroxysmal AF and 52 non-AF controls as test data. For each segment window length, discriminant models were made by 5-fold cross-validation subsets of the training data and its classification performance was examined with the test data.Results: In machine learning with the training data, the averages of cross-validation scores were 0.995 and 0.999 for 10 and 20-beat LP images, respectively, and >0.999 for 50 to 500-beat images. The classification of test data showed good performance for all segment window lengths with an accuracy from 0.970 to 0.988. Positive likelihood ratio for detecting AF segments, however, showed a convex parabolic curve linear relationship to log segment window length and peaked at 85 beats, while negative likelihood ratio showed monotonous increase with increasing segment window length.Conclusions: This study suggests that the optimal segment window length that maximizes the positive likelihood ratio for detecting paroxysmal AF with 32 x 32-pixel LP image is 85 beats.

show abstract

Section: Estimation Of Af Burdensupporting

confidence: 64%

Section: Discussionmentioning

confidence: 53%

“…709). The PhysioNet database were used only for the test data for the comparisons with earlier studies [9,11,13].…”

Section: Data Selectionsmentioning

confidence: 99%

Section: Classi Cation Of Test Datamentioning

confidence: 99%

See 2 more Smart Citations

Optimal Length of R-R Interval Segment Window for Lorenz Plot Detection of Paroxysmal Atrial Fibrillation by Machine Learning

Kisohara

Yuda

Ueda

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In contrast, ventricular response analysis only use the RR interval information derived from the most obvious amplitude feature of QRS complexes [11]. In the past decade, many ventricular response analysis-based AF detectors have developed [8,[11][12][13][14]. Park et al proposed a Poincare plot method using the inter-beat intervals and extracted three features form the Poincare plot to classify AF and non-AF rhythms (sensitivity 91.4% and specificity 92.9%) [15].…”

Section: Introductionmentioning

confidence: 99%

A New Entropy-Based Atrial Fibrillation Detection Method for Scanning Wearable ECG Recordings

Zhao

Liu

Wei

et al. 2018

Entropy

Self Cite

View full text Add to dashboard Cite

Entropy-based atrial fibrillation (AF) detectors have been applied for short-term electrocardiogram (ECG) analysis. However, existing methods suffer from several limitations. To enhance the performance of entropy-based AF detectors, we have developed a new entropy measure, named EntropyAF, which includes the following improvements: (1) use of a ranged function rather than the Chebyshev function to define vector distance, (2) use of a fuzzy function to determine vector similarity, (3) replacement of the probability estimation with density estimation for entropy calculation, (4) use of a flexible distance threshold parameter, and (5) use of adjusted entropy results for the heart rate effect. EntropyAF was trained using the MIT-BIH Atrial Fibrillation (AF) database, and tested on the clinical wearable long-term AF recordings. Three previous entropy-based AF detectors were used for comparison: sample entropy (SampEn), fuzzy measure entropy (FuzzyMEn) and coefficient of sample entropy (COSEn). For classifying AF and non-AF rhythms in the MIT-BIH AF database, EntropyAF achieved the highest area under receiver operating characteristic curve (AUC) values of 98.15% when using a 30-beat time window, which was higher than COSEn with AUC of 91.86%. SampEn and FuzzyMEn resulted in much lower AUCs of 74.68% and 79.24% respectively. For classifying AF and non-AF rhythms in the clinical wearable AF database, EntropyAF also generated the largest values of Youden index (77.94%), sensitivity (92.77%), specificity (85.17%), accuracy (87.10%), positive predictivity (68.09%) and negative predictivity (97.18%). COSEn had the second-best accuracy of 78.63%, followed by an accuracy of 65.08% in FuzzyMEn and an accuracy of 59.91% in SampEn. The new proposed EntropyAF also generated highest classification accuracy when using a 12-beat time window. In addition, the results from time cost analysis verified the efficiency of the new EntropyAF. This study showed the better discrimination ability for identifying AF when using EntropyAF method, indicating that it would be useful for the practical clinical wearable AF scanning.

show abstract

Entropy Analysis in Health Informatics

Humeau-Heurtier

2020

Intelligent Systems Reference Library

View full text Add to dashboard Cite

A comparison of entropy approaches for AF discrimination

Abstract: Our results demonstrate that the new developed normalized fuzzy entropy is an accurate measure for detecting AF.

Cited by 42 publications

References 53 publications

Optimal Length of R-R Interval Segment Window for Lorenz Plot Detection of Paroxysmal Atrial Fibrillation by Machine Learning

Optimal Length of R-R Interval Segment Window for Lorenz Plot Detection of Paroxysmal Atrial Fibrillation by Machine Learning

A New Entropy-Based Atrial Fibrillation Detection Method for Scanning Wearable ECG Recordings

Entropy Analysis in Health Informatics

Contact Info

Product

Resources

About