On the choice of multiscale entropy algorithm for quantification of complexity in gait data

Raffalt, Peter C.; Denton, William; Yentes, Jennifer M.

doi:10.1016/j.compbiomed.2018.10.008

Cited by 10 publications

(18 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same considerations hold for the gradient (n) of the exponential function in FEn computation [39]. In addition, FEn was originally developed as a single-scale complexity measure [39] but its validity in recognizing the correct amount of complexity on multiple time scales remains a still discussed issue [40], [41].…”

Section: A Multiscale Entropymentioning

confidence: 96%

“…with α = 4. The SW was constructed by adding white noise to a sinusoidal waveform [41]. For each signal, a total of 30 timeseries were generated, made by 10 4 samples.…”

Section: Appendix a Suitability Of Msfen Over Large Scale Factorsmentioning

confidence: 99%

“…As a measure of regularity for the multiscale analysis, the Fuzzy entropy (FEn) was used. This represents an entropy metric yet employed for biological signals [22], [38], [39] and whose embedding in a MSEn framework was applied to EEG and gait timeseries [40], [41] but not to human sway data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multiscale Fuzzy Entropy Analysis of Balance: Evidences of Scale-Dependent Dynamics on Diabetic Patients With and Without Neuropathy

Mengarelli

Tigrini

Verdini

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Postural control is usually assessed by examining the fluctuations of the center of pressure (COP). Balance maintenance is based on sensory feedback and neural interactions, deployed over multiple temporal scales and producing less complex outputs with aging and disease. This paper aims to investigate postural dynamics and complexity on diabetic patients, since diabetic neuropathy (DN) affects the somatosensory system and impairs postural steadiness. A multiscale fuzzy entropy (MSFEn) analysis, over a wide range of temporal scales, was performed on COP timeseries during unperturbed stance in a group of diabetic individuals without neuropathy and two groups of DN patients, with and without symptoms. A parameterization of the MSFEn curve is also proposed. A significant loss of complexity was recognized for the medial-lateral direction in DN groups with respect to non-neuropathic population. For the anterior-posterior direction, symptomatic DN group showed a lowered sway complexity for longer time scales with respect to non neuropathic and asymptomatic patients. The MSFEn approach and the related parameters highlighted that the loss of complexity might be attributed to different factors depending on sway direction, i.e. related to the presence of neuropathy along the medial-lateral axis and to a symptomatic state on the anterior-posterior direction. Results of this study support the use of the MSFEn for gaining insights into balance control mechanisms for diabetic patients, in particular when comparing non neuropathic with neuropathic asymptomatic patients, whose identification by posturographic analysis would be of great value.

show abstract

Section: A Multiscale Entropymentioning

confidence: 96%

“…with α = 4. The SW was constructed by adding white noise to a sinusoidal waveform [41]. For each signal, a total of 30 timeseries were generated, made by 10 4 samples.…”

Section: Appendix a Suitability Of Msfen Over Large Scale Factorsmentioning

confidence: 99%

See 1 more Smart Citation

Multiscale Fuzzy Entropy Analysis of Balance: Evidences of Scale-Dependent Dynamics on Diabetic Patients With and Without Neuropathy

Mengarelli

Tigrini

Verdini

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…These two measures differ in the coarse graining procedure and the lowest scale, t used to create the rescaled series (36). Template length in Sm.En computation, m was set as 2, and the tolerance as r = 0.2 × standard deviation of the data window (38,39). Sample entropy was estimated over data windows of 15 min (Sm.En_S) to study signal fluctuations over short time scales.…”

Section: Descriptors Of Variabilitymentioning

confidence: 99%

Comparison of oxygen supplementation in very preterm infants: Variations of oxygen saturation features and their application to hypoxemic episode based risk stratification

Ramanand

Indic²,

Travers³

et al. 2023

Front. Pediatr.

View full text Add to dashboard Cite

BackgroundOxygen supplementation is commonly used to maintain oxygen saturation (SpO2) levels in preterm infants within target ranges to reduce intermittent hypoxemic (IH) events, which are associated with short- and long-term morbidities. There is not much information available about differences in oxygenation patterns in infants undergoing such supplementations nor their relation to observed IH events. This study aimed to describe oxygenation characteristics during two types of supplementation by studying SpO2 signal features and assess their performance in hypoxemia risk screening during NICU monitoring.Subjects and methodsSpO2 data from 25 infants with gestational age <32 weeks and birthweight <2,000 g who underwent a cross over trial of low-flow nasal cannula (NC) and digitally-set servo-controlled oxygen environment (OE) supplementations was considered in this secondary analysis. Features pertaining to signal distribution, variability and complexity were estimated and analyzed for differences between the supplementations. Univariate and regularized multivariate logistic regression was applied to identify relevant features and develop screening models for infants likely to experience a critically high number of IH per day of observation. Their performance was assessed using area under receiver operating curves (AUROC), accuracy, sensitivity, specificity and F1 scores.ResultsWhile most SpO2 measures remained comparable during both supplementations, signal irregularity and complexity were elevated while on OE, pointing to more volatility in oxygen saturation during this supplementation mode. In addition, SpO2 variability measures exhibited early prognostic value in discriminating infants at higher risk of critically many IH events. Poincare plot variability at lag 1 had AUROC of 0.82, 0.86, 0.89 compared to 0.63, 0.75, 0.81 for the IH number, a clinical parameter at observation times of 30 min, 1 and 2 h, respectively. Multivariate models with two features exhibited validation AUROC > 0.80, F1 score > 0.60 and specificity >0.85 at observation times ≥ 1 h. Finally, we proposed a framework for risk stratification of infants using a cumulative risk score for continuous monitoring.ConclusionAnalysis of oxygen saturation signal routinely collected in the NICU, may have extensive applications in inferring subtle changes to cardiorespiratory dynamics under various conditions as well as in informing clinical decisions about infant care.

show abstract

“…e MSE 2D algorithm has not been applied widely in various physiological conditions yet and may be used to detect complexity changes of plantar pressure during different pathophysiological conditions. Traditionally, gait pattern assessments, including plantar pressure patterns, are analyzed using linear methods [23]. Plantar pressure patterns may consist of linear and nonlinear components.…”

Section: Introductionmentioning

confidence: 99%

Effect of Walking Speeds on Complexity of Plantar Pressure Patterns

Liau

et al. 2021

Complexity

View full text Add to dashboard Cite

Various walking speeds may induce different responses on the plantar pressure patterns. Current methods used to analyze plantar pressure patterns are linear and ignore nonlinear features. The purpose of this study was to analyze the complexity of plantar pressure images after walking at various speeds using nonlinear bidimensional multiscale entropy (MSE2D). Twelve participants (age: 27.1 ± 5.8 years; height: 170.3 ± 10.0 cm; and weight: 63.5 ± 13.5 kg) were recruited for walking at three speeds (slow at 1.8 mph, moderate at 3.6 mph, and fast at 5.4 mph) for 20 minutes. A plantar pressure measurement system was used to measure plantar pressure patterns. Complexity index (CI), a summation of MSE2D from all time scales, was used to quantify the changes of complexity of plantar pressure images. The analysis of variance with repeated measures and Fisher’s least significant difference correction were used to examine the results of this study. The results showed that CI of plantar pressure images of 1.8 mph (1.780) was significantly lower compared with 3.6 (1.790) and 5.4 mph (1.792). The results also showed that CI significantly increased from the 1st min (1.780) to the 10th min (1.791) and 20th min (1.791) with slow walking (1.8 mph). Our results indicate that slow walking at 1.8 mph may not be good for postural control compared with moderate walking (3.6 mph) and fast walking (5.4 mph). This study demonstrates that bidimensional multiscale entropy is able to quantify complexity changes of plantar pressure images after different walking speeds.

show abstract

On the choice of multiscale entropy algorithm for quantification of complexity in gait data

Cited by 10 publications

References 48 publications

Multiscale Fuzzy Entropy Analysis of Balance: Evidences of Scale-Dependent Dynamics on Diabetic Patients With and Without Neuropathy

Multiscale Fuzzy Entropy Analysis of Balance: Evidences of Scale-Dependent Dynamics on Diabetic Patients With and Without Neuropathy

Comparison of oxygen supplementation in very preterm infants: Variations of oxygen saturation features and their application to hypoxemic episode based risk stratification

Effect of Walking Speeds on Complexity of Plantar Pressure Patterns

Contact Info

Product

Resources

About