Dataset Information

Pathologies affect the performance of ECG signals compression.

ABSTRACT: The performance of ECG signals compression is influenced by many things. However, there is not a single study primarily focused on the possible effects of ECG pathologies on the performance of compression algorithms. This study evaluates whether the pathologies present in ECG signals affect the efficiency and quality of compression. Single-cycle fractal-based compression algorithm and compression algorithm based on combination of wavelet transform and set partitioning in hierarchical trees are used to compress 125 15-leads ECG signals from CSE database. Rhythm and morphology of these signals are newly annotated as physiological or pathological. The compression performance results are statistically evaluated. Using both compression algorithms, physiological signals are compressed with better quality than pathological signals according to 8 and 9 out of 12 quality metrics, respectively. Moreover, it was statistically proven that pathological signals were compressed with lower efficiency than physiological signals. Signals with physiological rhythm and physiological morphology were compressed with the best quality. The worst results reported the group of signals with pathological rhythm and pathological morphology. This study is the first one which deals with effects of ECG pathologies on the performance of compression algorithms. Signal-by-signal rhythm and morphology annotations (physiological/pathological) for the CSE database are newly published.

SUBMITTER: Nemcova A

PROVIDER: S-EPMC8131635 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:IntroductionCardiovascular disease remains a significant problem in modern society. Among non-invasive techniques, the electrocardiogram (ECG) is one of the most reliable methods for detecting cardiac abnormalities. However, ECG interpretation requires expert knowledge and it is time-consuming. Developing a novel method to detect the disease early improves the quality and efficiency of medical care.MethodsThe paper presents various modern approaches for classifying cardiac diseases from ECG recordings. The first approach suggests the Poincaré representation of ECG signal and deep-learning-based image classifiers. Additionally, the raw signals were processed with the one-dimensional convolutional model while the XGBoost model was facilitated to predict based on the time-series features.ResultsThe Poincaré-based methods showed decent performance in predicting AF (atrial fibrillation) but not other types of arrhythmia. XGBoost model gave an acceptable performance in long-term data but had a long inference time due to highly-consuming calculations within the pre-processing phase. Finally, the 1D convolutional model, specifically the 1D ResNet, showed the best results in both studied CinC 2017 and CinC 2020 datasets, reaching the F1 score of 85% and 71%, respectively, and they were superior to the first-ranking solution of each challenge. The 1D models also presented high specificity. Additionally, our paper investigated efficiency metrics including power consumption and equivalent CO2 emissions, with one-dimensional models like 1D CNN and 1D ResNet being the most energy efficient. Model interpretation analysis showed that the DenseNet detected AF using heart rate variability while the 1D ResNet assessed the AF patterns in raw ECG signals.DiscussionDespite the under-performed results, the Poincaré diagrams are still worth studying further because of the accessibility and inexpensive procedure. In the 1D convolutional models, the residual connections are useful to keep the model simple but not decrease the performance. Our approach in power measurement and model interpretation helped understand the numerical complexity and mechanism behind the model decision.

Dataset Information

Pathologies affect the performance of ECG signals compression.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets