Physiological Time Series Research Articles

Improve concentration of frequency and time (ConceFT) by novel complex spherical designs

Concentration of frequency and time (ConceFT) is a generalized multitaper algorithm introduced to analyze complicated non-stationary time series. To avoid the randomness in the original ConceFT algorithm, we apply the novel complex spherical design technique to standardize ConceFT, which we coin CQU-ConceFT . The proposed CQU-ConceFT is applied to visualize the spindle structure in the electroencephalogram signal during the N2 sleep stage and other physiological time series.

On using the modularity of recurrence network communities to detect change-point behaviour

The behaviour of a dynamical system can be examined from time series using the technique of recurrence plots through visualization and quantification methods. One such method is the quadrant scan in which a recurrence plot of a time series is converted into a second time series whose local maxima can be identified and interpreted as possible transitions in dynamic behaviour. A recurrence plot can also be represented as a complex network. A quadrant scan can similarly be thought of as a partition of the network vertices into two communities. Here, we argue that different dynamic behavioural regimes can be realized as network communities and the quality of such partitions can be assessed using modularity. Thereby, community modularity can be used as an alternative to the quadrant scan. We investigate this correspondence with respect to two promising arenas for quadrant scan uptake, namely, concept drift detection from machine learning and tipping point or failure and damage monitoring in system maintenance. We also examine two additional data sets to highlight the potential of the methods. These are a geophysical time series of earth tremor data and a physiological time series of an electrocardiogram.

Time-Reversibility, Causality and Compression-Complexity.

Detection of the temporal reversibility of a given process is an interesting time series analysis scheme that enables the useful characterisation of processes and offers an insight into the underlying processes generating the time series. Reversibility detection measures have been widely employed in the study of ecological, epidemiological and physiological time series. Further, the time reversal of given data provides a promising tool for analysis of causality measures as well as studying the causal properties of processes. In this work, the recently proposed Compression-Complexity Causality (CCC) measure (by the authors) is shown to be free of the assumption that the "cause precedes the effect", making it a promising tool for causal analysis of reversible processes. CCC is a data-driven interventional measure of causality (second rung on the Ladder of Causation) that is based on Effort-to-Compress (ETC), a well-established robust method to characterize the complexity of time series for analysis and classification. For the detection of the temporal reversibility of processes, we propose a novel measure called the Compressive Potential based Asymmetry Measure. This asymmetry measure compares the probability of the occurrence of patterns at different scales between the forward-time and time-reversed process using ETC. We test the performance of the measure on a number of simulated processes and demonstrate its effectiveness in determining the asymmetry of real-world time series of sunspot numbers, digits of the transcedental number and heart interbeat interval variability.

Multiscale Sample Entropy of Two-Dimensional Decaying Turbulence.

Multiscale sample entropy analysis has been developed to quantify the complexity and the predictability of a time series, originally developed for physiological time series. In this study, the analysis was applied to the turbulence data. We measured time series data for the velocity fluctuation, in either the longitudinal or transverse direction, of turbulent soap film flows at various locations. The research was to assess the feasibility of using the entropy analysis to qualitatively characterize turbulence, without using any conventional energetic analysis of turbulence. The study showed that the application of the entropy analysis to the turbulence data is promising. From the analysis, we successfully captured two important features of the turbulent soap films. It is indicated that the turbulence is anisotropic from the directional disparity. In addition, we observed that the most unpredictable time scale increases with the downstream distance, which is an indication of the decaying turbulence.

Fractal and multifractal characterization of in vitro respiratory recordings of the pre-Bötzinger complex

The pre-Bötzinger complex is a neural network located in the ventrolateral brainstem that generates the respiratory rhythm. Under normoxic conditions, this area shows two inspiratory burst patterns, sigh and non-sigh. Several studies have shown that in vitro application of peptides, such as bombesin, stimulates the respiratory rate and increases the appearance of sighs. However, it is difficult to distinguish between sighs and non-sighs waveforms, which makes it difficult to study their properties under experimental conditions. The fractal and multifractal analysis have proven to be valuable tools for studying physiological time series, thus in this study, we applied this methodology to characterize sighs and non-sighs. Our results regarding fractality, shown that the sighs and non-sighs have similar Hurst exponents and that the application of bombesin only decreased the Hurst exponent of non-sighs. On the other hand, our results on multifractality parameters scaling exponent (τ(q)) and generalized Hurst exponent (H(q)) shown that both sighs and non-sighs were multifractal and this remained even after the application of bombesin. Further analysis showed that sighs and non-sighs had different H(q) values, which changed after the bombesin application. To quantitatively analyzed the multifractal spectrum, we calculated the area of the spectrum (Iα), which was similar between sighs and non-sighs and the application of bombesin did not change this. Altogether, these results show that the analysis of fractal and multifractal parameters allows to characterize and find statistical differences of sighs and non-sighs within and between different experimental conditions. Statement of SignificanceThe characterization of the respiratory recordings is very difficult and time consuming when is done manually by a researcher. An automated software that can aid this can be very useful. Furthermore, this gives some parameters that can help to statistically differentiate between sighs and non sighs. One interesting finding was that multifractality show differences in the same condition between sighs and non sighs. Also, we found that the neuropeptide bombesin increases the number of sighs without changing the intrinsic structure of the respiration system. This is important to avoid the collapse of the lungs that can be incorporated in mechanical ventilators. We hope that you will find our paper suitable for publication in Brain Multiphysics and will look forward to receiving your response.

When our hearts beat together: Cardiac synchrony as an entry point to understand dyadic co-regulation in couples.

The degree to which romantic partners' autonomic responses are coordinated, represented by their pattern of physiological synchrony, seems to capture important aspects of the reciprocal influence and co-regulation between spouses. In this study, we analyzed couple's cardiac synchrony as measured by heart rate (HR) and heart rate variability (HRV). A sample of 27 couples (N=54) performed a structured interaction task in the lab where they discussed positive and negative aspects of the relationship. During the interaction, their cardiac measures (HR and HRV) were recorded using the BIOPAC System. Additional assessment, prior to the lab interaction task, included self-report measures of empathy (Interpersonal Reactivity Index and Interpersonal Reactivity Index for Couples) and relationship satisfaction (Revised Dyadic Adjustment Scale). Synchrony computation was based on the windowed cross-correlation of both partner's HR and HRV time series. In order to control for random synchrony, surrogate controls were created using segment-wise shuffling. Our results confirmed the presence of cardiac synchrony during the couple's interaction when compared to surrogate testing. Specifically, we found evidence for negative (antiphase) synchrony of couple's HRV and positive (in-phase) synchrony of HR. Further, both HRV and HR synchronies were associated with several dimensions of self-report data. This study suggests that cardiac synchrony, particularly, the direction of the covariation in the partners' physiological time series, may have an important relational meaning in the context of marital interactions.

SleepPrintNet: A Multivariate Multimodal Neural Network Based on Physiological Time-Series for Automatic Sleep Staging

Sleep is one of the most fundamental physiological activities of human beings. Sleep assessment based on physiological time-series can efficiently assist human experts to diagnose the sleep health of people. However, most of the existing methods only considered one or two kinds of time-domain, frequency-domain, and spatial-domain information from electroencephalogram (EEG). Besides, existing deep learning methods share the feature extraction module of EEG with other modalities, which ignore the discriminative features of electrooculogram (EOG) and electromyography (EMG). Therefore, how to make full use of the complementarity of different features of EEG and capture the discriminative features from other modalities is challenging. To tackle this challenge, we design SleepPrintNet to capture the SleepPrint in physiological time-series, which represents the complementarity among different features of EEG and discriminative features from other modalities in different sleep stages. SleepPrintNet consists of an EEG temporal feature extraction module, an EEG spectral-spatial feature extraction module for the temporal-spectral-spatial representation of EEG signals, and two multimodal feature extraction modules including EOG and EMG feature extraction module. To the best of our knowledge, it is the first attempt to integrate EEG temporal-spectral-spatial as well as the multimodal features simultaneously in a unified model for sleep staging. Experiments on the benchmark dataset MASS-SS3 demonstrate that SleepPrintNet outperforms all baseline models. The implementation code of SleepPrintNet is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/xiyangcai/SleepPrintNet</uri> . <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><i>Impact Statement–</i> Sleep staging helps sleep experts assess sleep quality and diagnose sleep health. The polysomnography, which contains the physiological signal recordings during sleep, is a kind of multimodal multivariant physiological time-series for sleep staging. However, existing methods treat physiological time-series from different parts of the body equally, which ignore the abundant information in multimodal signals. The SleepPrintNet proposed in this article has improved the accuracy of sleep staging with the help of the discriminative characteristics from different physiological time-series, which is made up of several independent modules for the extraction of different modalities signals. SleepPrintNet is also a universal framework for the classification of multivariate and multimodal signals. It can be applied in the diagnosis and treatment of other diseases based on physiological signals. The high-accuracy classification of physiological signals has great significance in the field of intelligent medical diagnostics.

Gated temporal convolutional neural network and expert features for diagnosing and explaining physiological time series: A case study on heart rates

Background and Objective: Physiological time series are common data sources in many health applications. Mining data from physiological time series is crucial for promoting healthy living and reducing governmental medical expenditure. Recently, research and applications of deep learning methods on physiological time series have developed rapidly because such data can be continuously recorded by smart wristbands or smartwatches. However, existing deep learning methods suffer from excessive model complexity and a lack of explanation. This paper aims to handle these issues.Methods: We propose TEG-net, which is a novel deep learning method for accurately diagnosing and explaining physiological time series. TEG-net constructs T-net (a multi-scale bi-directional temporal convolutional neural network) to model physiological time series directly, E-net (personalized linear model) to model expert features extracted from physiological time series, and G-net (gating neural network) to combine T-net and E-net for diagnosis. The combination of T-net and E-net through G-net improves diagnosis accuracy and E-net can be utilized for explanation.Results: Experimental results demonstrate that TEG-net outperforms the second-best baseline by 13.68% in terms of area under the receiver operating characteristic curve and 11.49% in terms of area under the precision-recall curve. Additionally, intuitive justifications can be provided to explain model predictions.Conclusions: This paper develops an ensemble method to combine expert features and deep learning method for modeling physiological time series. Improvements in diagnostic accuracy and explanation make TEG-net applicable to many real-world health applications.

Novel approaches to prediction in severe brain injury.

Recovery after severe brain injury is variable and challenging to accurately predict at the individual patient level. This review highlights new developments in clinical prognostication with a special focus on the prediction of consciousness and increasing reliance on methods from data science. Recent research has leveraged serum biomarkers, quantitative electroencephalography, MRI, and physiological time-series to build models for recovery prediction. The analysis of high-resolution data and the integration of features from different modalities can be approached with efficient computational techniques. Advances in neurophysiology and neuroimaging, in combination with computational methods, represent a novel paradigm for prediction of consciousness and functional recovery after severe brain injury. Research is needed to produce reliable, patient-level predictions that could meaningfully impact clinical decision making.

Utilization of the Signature Method to Identify the Early Onset of Sepsis From Multivariate Physiological Time Series in Critical Care Monitoring.

Patients in an ICU are particularly vulnerable to sepsis. It is therefore important to detect its onset as early as possible. This study focuses on the development and validation of a new signature-based regression model, augmented with a particular choice of the handcrafted features, to identify a patient's risk of sepsis based on physiologic data streams. The model makes a positive or negative prediction of sepsis for every time interval since admission to the ICU. The data were sourced from the PhysioNet/Computing in Cardiology Challenge 2019 on the "Early Prediction of Sepsis from Clinical Data." It consisted of ICU patient data from three separate hospital systems. Algorithms were scored against a specially designed utility function that rewards early predictions in the most clinically relevant region around sepsis onset and penalizes late predictions and false positives. The work was completed as part of the PhysioNet 2019 Challenge alongside 104 other teams. PhysioNet sourced over 60,000 ICU patients with up to 40 clinical variables for each hour of a patient's ICU stay. The Sepsis-3 criteria was used to define the onset of sepsis. None. The algorithm yielded a utility function score which was the first placed entry in the official phase of the challenge.

A hybrid intelligent model for acute hypotensive episode prediction with large-scale data

Acute hypotensive episode (AHE) is a common serious postoperative complication in ICU, which may raise multiple system failure (especially of cardiac and respiratory kinds), and even cause death. Timely and effective clinical intervention is obviously vital to the saving of patients. AHE detection involves physiological time-series monitoring, processing and prediction technologies, which can offer insights to neuroscientists, biologists, and even provide support for clinicians. This paper presents a hybrid artificial intelligence model combined with CEEMDAN (complete ensemble empirical mode decomposition with adaptive noise, a typical method for physiological signal decomposition), deep learning, multiple gene expression programming and fuzzy expert system for AHE detection. In this paper, the physiological signal is selected from a benchmark dataset, for example MIMIC-II (Multiparameter Intelligent Monitoring in Intensive Care II), which collects large scale real patients’ data for clinical research. In the hybrid model, a typical signal decomposition method is employed for AHE signal processing, and an autoencoder based deep neural network is established for feature extraction. Finally, a reliable and explainable classifier is presented by fusing gene expression programming and the fuzzy method. Experimental results based on real data set demonstrate that the proposed method outperforms state-of-the-art AHE detection methods by achieving the prediction accuracy of 88.14% in 2866 records.

Fractal analysis of muscle activity patterns during locomotion: pitfalls and how to avoid them.

Time-dependent physiological data sets are often difficult to interpret objectively. Biosignals such as electromyogram, electroencephalogram, or single-neuron recordings can be interpreted using various linear and nonlinear methods. Each analysis technique aims at the explanation of different data features that might be visible or not to the naked eye. Here, we used linear decomposition based on machine learning to extract motor primitives (the time-dependent coefficients of muscle synergies) from the hindlimb electromyographic activity of mice during normal and mechanically perturbed locomotion. We set out to investigate the effects of calculation parameters and data quality on two nonlinear metrics derived from fractal analysis: the Higuchi's fractal dimension (HFD) and the Hurst exponent (H). Both HFD and H proved to be exceptionally sensitive to changes in motor primitives induced by external perturbations to locomotion. We discuss the potential pitfalls that might arise from fractal analysis by using examples based on surrogate data. We conclude giving some simple, data-driven suggestions to reduce the chance of misinterpretations when metrics such as HFD and H are applied to any biological signal containing elements of periodicity.NEW & NOTEWORTHY Despite the lack of consensus on how to perform fractal analysis of physiological time series, many studies rely on this technique. Here, we shed light on the potential pitfalls of using the Higuchi's fractal dimension and the Hurst exponent. We expose and suggest how to solve the drawbacks of such methods when applied to data from normal and perturbed locomotion by combining in vivo recordings and computational approaches.

Modified multiscale fuzzy entropy: A robust method for short-term physiologic signals.

The introduction of the multiscale entropy (MSE) method was a milestone in the field of complex physiological signal analysis. However, since MSE is inapplicable for short signals, several variants of MSE have been proposed. One of the most important variants of MSE is the modified multiscale entropy (MMSE), even though it can still produce biased estimates due to the hard similarity criteria of sample entropy. Taking the advantages of MMSE and the concept of fuzzy entropy, we propose the modified multiscale fuzzy entropy (MMFE). We evaluated the robustness of MMSE and MMFE using segmented stochastic noises and actual heart rate variability series and compared it with the classical MSE results obtained with the full signals. Results show that MMFE is much more robust than MMSE for short physiological time series, resembling MSE for series as shorter as 400 samples. We also show the existence of an exponential relationship between the MMFE fuzzy parameter and the signal size. We suggest the use of this relationship to choose the optimal MMFE parameter as part of the method.

Phase Entropy Analysis of Electrohysterographic Data at the Third Trimester of Human Pregnancy and Active Parturition.

Phase Entropy (PhEn) was recently introduced for evaluating the nonlinear features of physiological time series. PhEn has been demonstrated to be a robust approach in comparison to other entropy-based methods to achieve this goal. In this context, the present study aimed to analyze the nonlinear features of raw electrohysterogram (EHG) time series collected from women at the third trimester of pregnancy (TT) and later during term active parturition (P) by PhEn. We collected 10-min longitudinal transabdominal recordings of 24 low-risk pregnant women at TT (from 35 to 38 weeks of pregnancy) and P (>39 weeks of pregnancy). We computed the second-order difference plots (SODPs) for the TT and P stages, and we evaluated the PhEn by modifying the k value, a coarse-graining parameter. Our results pointed out that PhEn in TT is characterized by a higher likelihood of manifesting nonlinear dynamics compared to the P condition. However, both conditions maintain percentages of nonlinear series higher than 66%. We conclude that the nonlinear features appear to be retained for both stages of pregnancy despite the uterine and cervical reorganization process that occurs in the transition from the third trimester to parturition.

Experimenting with Generative Adversarial Networks to Expand Sparse Physiological Time-Series Data.

Machine Learning research and its application have gained enormous relevance in recent years. Their usage in medical settings could support patients, increase patient safety and assist health professionals in various tasks. However, medical data is often sparse, which renders big data analytics methods like deep learning ineffective. Data synthesis helps to augment small data sets and potentially improves patient data integrity. The presented work illustrates how Generative Adversarial Networks can be applied specifically to small data sets for enlarging sparse data. Following a state-of-the-art analysis is conducted, experimental methods with such networks are documented, which have been applied to three different data sets. Results from all three sets are presented and take-away messages are summarized. Concluding, the results' quality and limitations of the work are discussed.

Physiological Time Series Processing via Empirical Wavelet Transform

This paper presents the efficacy of empirical wavelet transform (EWT) for physiological time series processing. At first, EWT is applied to multivariate heterogeneous physiological time series. Secondly, EWT is used for the removal of fast temporal scales in multiscale entropy analysis. Empirical mode decomposition is an adaptive data analysis method in the sense that it does not require prior information about the signal statistics and tend to decompose a signal into various constituent modes. The utility of Standard EMD algorithm is however limited to single channel data as it suffers from the problems of mode alignment and mode mixing when applied channel wise for multivariate data. The standard EMD algorithm was extended to multivariate Empirical mode decomposition (MEMD) that can be used analyze a multivariate data. The MEMD can only be applied to multivariate data in which all the channels have equal data length. EWT is another adaptive technique for mode extraction in a signal using empirical scaling and wavelet functions. The multiscale entropy (MSE) algorithm is generally used to quantify the complexity of a time series. The original MSE approach utilizes a coarse-graining process for the removal of fast temporal scales in a time series which is equivalent to applying a finite impulse response (FIR) moving average filter. In Refined Multiscale entropy (RMSE), the FIR filter was replaced with a low pass Butterworth filter which exhibits a better frequency response than that of a FIR filter. In this paper we have presented a new approach for the removal of fast temporal scales based on empirical wavelet transform. The empirical wavelet transform is also used as an innovative filtering approach in multiscale entropy analysis.

Patient clustering using dynamic partitioning on correlated and uncertain biomedical data

Background and objectivesHealth professionals look for specific patterns by correlating multiple physiological data in the process of deciding treatments to remedy clinical abnormalities. Biomedical data exhibit some common patterns in the event of identical clinical illnesses. The primary interest of this work is automatic discovery of such patterns in vital sign data (e.g. heart rate, blood pressure) using unsupervised learning and utilising them to identify patients with similar clinical conditions.MethodsA patient clustering method is developed that efficiently isolates patients into multiple groups by discovering dynamic patterns in multi-dimensional vital sign data. A dynamic partitioning algorithm and a patient clustering approach is proposed by introducing a measure namely aggregated instance-wise uncertainty (AIU) computed from multi-dimensional physiological time-series data.ResultsThe developed model is evaluated qualitatively using principal component analysis and silhouette value; and quantitatively in terms of its ability of clustering patients associated with different clinical situations. Experiments are conducted using real-world biomedical data of patients having various clinical conditions. Thee observed accuracy was 82.85% and 91.17% on two experimental datasets comprised of 35 and 34 patients data respectively.The comparisons show that the proposed approached outperformed than other methods in state-of-the-art approach.ConclusionsThe experimental outcomes demonstrate the effectiveness of the proposed approach in discovering distinct patterns with predictive significance.

An evaluation of time series summary statistics as features for clinical prediction tasks

BackgroundClinical prediction tasks such as patient mortality, length of hospital stay, and disease diagnosis are highly important in critical care research. The existing studies for clinical prediction mainly used simple summary statistics to summarize information from physiological time series. However, this lack of statistics leads to a lack of information. In addition, using only maximum and minimum statistics to indicate patient features fails to provide an adequate explanation. Few studies have evaluated which summary statistics best represent physiological time series.MethodsIn this paper, we summarize 14 statistics describing the characteristics of physiological time series, including the central tendency, dispersion tendency, and distribution shape. Then, we evaluate the use of summary statistics of physiological time series as features for three clinical prediction tasks. To find the combinations of statistics that yield the best performances under different tasks, we use a cross-validation-based genetic algorithm to approximate the optimal statistical combination.ResultsBy experiments using the EHRs of 6,927 patients, we obtained prediction results based on both single statistics and commonly used combinations of statistics under three clinical prediction tasks. Based on the results of an embedded cross-validation genetic algorithm, we obtained 25 optimal sets of statistical combinations and then tested their prediction results. By comparing the performances of prediction with single statistics and commonly used combinations of statistics with quantitative analyses of the optimal statistical combinations, we found that some statistics play central roles in patient representation and different prediction tasks have certain commonalities.ConclusionThrough an in-depth analysis of the results, we found many practical reference points that can provide guidance for subsequent related research. Statistics that indicate dispersion tendency, such as min, max, and range, are more suitable for length of stay prediction tasks, and they also provide information for short-term mortality prediction. Mean and quantiles that reflect the central tendency of physiological time series are more suitable for mortality and disease prediction. Skewness and kurtosis perform poorly when used separately for prediction but can be used as supplementary statistics to improve the overall prediction effect.

Towards the use of vector based GP to predict physiological time series

Prediction of physiological time series is frequently approached by means of machine learning (ML) algorithms. However, most ML techniques are not able to directly manage time series, thus they do not exploit all the useful information such as patterns, peaks and regularities provided by the time dimension. Besides advanced ML methods such as recurrent neural network that preserve the ordered nature of time series, a recently developed approach of genetic programming, VE-GP, looks promising on the problem in analysis. VE-GP allows time series as terminals in the form of a vector, including new strategies to exploit this representation. In this paper we compare different ML techniques on the real problem of predicting ventilation flow from physiological variables with the aim of highlighting the potential of VE-GP. Experimental results show the advantage of applying this technique in the problem and we ascribe the good performances to the ability of properly catching meaningful information from time series.

A combined measure to differentiate EEG signals using fractal dimension and MFDFA-Hurst

The analysis of the brain electrical activity measured by means of electroencephalographic (EEG) records is a fundamental technique for the understanding and diagnosis of neurological diseases. This paper adopts the Multifractal Detrended Fluctuation Analysis, Hurst exponent (H) and fractal dimension (D) to analyze the dynamics of the EEG signals of normal and epileptic patients using a set of physiological time series. Furthermore, a new measure, namely the Combined Index, is proposed. The results indicate that the indices H and D are useful for building a combined measure of the EEG both for healthy and epileptic cerebral activity.