Classification of heart rate signals of healthy and pathological subjects using threshold based symbolic entropy

Aziz, Wajid; Rafique, Muhammad; Ahmad, Ishtiaq; Arif, Muhammad; Habib, Nazneen; Nadeem, Malik Sajjad Ahmed

doi:10.1556/abiol.65.2014.3.2

Cited by 16 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, complexity clearly decreases with disease severity and age. These results are in good agreement with the ''loss of complexity with aging and disease'' hypothesis [26], [32], [33].…”

Section: Resultssupporting

confidence: 87%

Analysing the Dynamics of Interbeat Interval Time Series Using Grouped Horizontal Visibility Graph

et al. 2019

Self Cite

View full text Add to dashboard Cite

Horizontal visibility graph (HVG) motifs have been recently introduced to analyze the dynamical information encoded by biological signals. However, the result of the analysis strongly depends on the selected window size of the motifs. Different sizes ranging from 3 to 5 have been previously used, but such small window sizes are insufficient to cope with the complexity of biological systems and often fail to extract salient features of the encoded information. It is known that larger window size increases the total number of possible motifs, and it leads to the distribution of the statistics into too many motifs, which causes each individual motif to contain too little information and make it even more difficult to reliably detect system dynamics. To resolve this problem, we group the motifs based on the number of edges. Using the grouped motifs, we propose grouped horizontal visibility entropy (GHVE) to quantify the complexity based on the probability distribution of the observations within these groups. We apply GHVE to quantify the complexity of simulated white and 1/f noise. The results reveal that the 1/f noise time series exhibits a higher complexity than white noise time series, which indicates that the 1/f noise is structurally more complex than white Gaussian noise. We apply the method for analyzing interbeat intervals time series. The results show that the proposed GHVE measure is more accurate in distinguishing healthy and pathological subjects than its non-grouped counterpart HVG. It is, therefore, better suited to detect changes in aging, disease severity, and activity levels (sleep and wake period). INDEX TERMS Complex network, HVG motifs, HRV analysis, time series data.

show abstract

Section: Resultssupporting

confidence: 87%

Analysing the Dynamics of Interbeat Interval Time Series Using Grouped Horizontal Visibility Graph

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus, it is necessary to establish a threshold value, y bound , to define the class limits. There are several ways to set the threshold, for example, such as Bayes’ theorem [40], receiver-operating characteristic (ROC) curves [41], threshold-based classification rule [42, 43] or by establishing confidence limits for each sample classified. These confidence intervals can be calculated by re-sampling techniques, such as bootstrap.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Classification of biodegradable materials using QSAR modelling with uncertainty estimation

Rocha

Sheen

2016

SAR and QSAR in Environmental Research

View full text Add to dashboard Cite

The ability to determine the biodegradability of chemicals without resorting to expensive tests is ecologically and economically desirable. Models based on quantitative structure-activity relations (QSAR) provide some promise in this direction. However, QSAR models in the literature rarely provide uncertainty estimates in more detail than aggregated statistics such as the sensitivity and specificity of the model’s predictions. Almost never is there a means of assessing the uncertainty in an individual prediction. Without an uncertainty estimate, it is impossible to assess the trustworthiness of any particular prediction, which leaves the model with a low utility for regulatory purposes. In the present work, a QSAR model with uncertainty estimates is used to predict biodegradability for a set of substances from a publicly available data set. Separation was performed using a partial least squares discriminant analysis model, and the uncertainty was estimated using bootstrapping. The uncertainty prediction allows for confidence intervals to be assigned to any of the model’s predictions, allowing for a more complete assessment of the model that would be possible through a traditional statistical analysis. The results presented here are broadly applicable to other areas of modeling as well, because the calculation of the uncertainty will clearly demonstrate where additional tests are needed.

show abstract

“…Extraction of physiological and clinical information hidden in biological signals, such as heart rate, respiratory rate, and stride intervals is an important and fascinating field of research [3][4][5][6][7]. Non-invasive assessment of the physiological parameters of a subject enables us to study the physiology and pathophysiology of the investigated system with minimum interference and inconvenience.…”

Section: Introductionmentioning

confidence: 99%

“…The traditional linear times series analysis techniques do not provide appropriate information about the dynamics of physiological systems. With the advent of non-linear dynamical analysis, many researchers have attempted to find the non-linear behavior of the biological systems [3][4][5][6][7]. Extensive scientific efforts have been made for understanding the physiology and pathophysiology of the cardiovascular system.…”

Section: Introductionmentioning

confidence: 99%

Extraction of Dynamical Information and Classification of Heart Rate Variability Signals Using Scale Based Permutation Entropy Measures

Shah¹,

Habib²,

Nadeem³

et al. 2020

Self Cite

View full text Add to dashboard Cite

The dynamical fluctuations in the Heart Rate Variability (HRV) signals show structures at multiple time scales revealing that complexity of the autonomic nervous system control of the heart is multiscale and hierarchical. Multiscale Entropy (MSE) and its variant Composite MSE (CMSE) were proposed to quantify the complexity at multiple time scales, however, these measures failed to quantify complexity accurately for short duration signals at large temporal scales. To address the downsides of MSE and CMSE, Multiscale Permutation Entropy (MPE) and Improved MPE (IMPE) were proposed. The preliminary results reveal that MPE and IMPE were able to distinguish healthy and pathological subjects, however, further studies are needed to investigate the robustness of these measures. In this study, we investigate the robustness of scale based PE measures in terms of dynamical information, induction of undefined entropy estimates for short duration signals and to classify HRV signals under different physiological and pathological conditions. The results were compared with SE, PE, MSE and CMSE. The MPE and IMPE along with MSE and CMSE provided accurate dynamical information. The results revealed that MPE and IMPE resolved the issue of inducing undefined entropy estimates and are robust in classifying healthy and different pathological subjects.

show abstract

Classification of heart rate signals of healthy and pathological subjects using threshold based symbolic entropy

Cited by 16 publications

References 20 publications

Analysing the Dynamics of Interbeat Interval Time Series Using Grouped Horizontal Visibility Graph

Analysing the Dynamics of Interbeat Interval Time Series Using Grouped Horizontal Visibility Graph

Classification of biodegradable materials using QSAR modelling with uncertainty estimation

Extraction of Dynamical Information and Classification of Heart Rate Variability Signals Using Scale Based Permutation Entropy Measures

Contact Info

Product

Resources

About