Classifying subclinical depression using EEG spectral and connectivity measures.

Detecting depression on its early stages helps preventing the onset of severe depressive episodes. In this study, we propose an automatic classification pipeline to detect subclinical depression (i.e., dysphoria) through the electroencephalography (EEG) signal. To this aim, we recorded the EEG signals in resting condition from 26 female participants with dysphoria and 38 female controls. The EEG signals were processed to extract several spectral and functional connectivity features to feed a nonlinear Support Vector Machine (SVM) classifier embedded with a Recursive Feature Elimination (RFE) algorithm. Our recognition pipeline obtained a maximum classification accuracy of 83.91% in recognizing dysphoria patients with a combination of connectivity and spectral measures. Moreover, an accuracy of 76.11% was achieved with only the 4 most informative functional connections, suggesting a central role of cortical connectivity in the theta band for early depression recognition. The present study can facilitate the diagnosis of subclinical conditions of depression and may provide reliable indicators of depression for the clinical community.

Gaussian Processes with Physiologically-Inspired Priors for Physical Arousal Recognition.

While machine learning algorithms are able to detect subtle patterns of interest in data, expert knowledge may contain crucial information that is not easily extracted from a given dataset, especially when the latter is small or noisy. In this paper we investigate the suitability of Gaussian Process Classification (GPC) as an effective model to implement the domain knowledge in an algorithm's training phase. Building on their Bayesian nature, we proceed by injecting problem- specific domain knowledge in the form of an a-priori distribution on the GPC latent function. We do this by extracting handcrafted features from the input data, and correlating them to the logits of the classification problem through fitting a prior function informed by the physiology of the problem. The physiologically-informed prior of the GPC is then updated through the Bayes formula using the available dataset. We apply the methods discussed here to a two-class classification problem associated to a dataset comprising Heart Rate Variability (HRV) and Electrodermal Activity (EDA) signals collected from 26 subjects who were exposed to a physical stressor aimed at altering their autonomic nervous systems dynamics. We provide comparative computational experiments on the selection of appropriate physiologically-inspired GPC prior functions. We find that the recognition of the presence of the physical stressor is significantly enhanced when the physiologically-inspired prior knowledge is injected into the GPC model.

Quantifying the lagged Poincaré plot geometry of ultrashort heart rate variability series: automatic recognition of odor hedonic tone.

The application of Poincaré plot analysis to characterize inter-beat interval dynamics has been successfully proposed in the scientific literature for the assessment of humans' physiological states and related aberrations. In this study, we proposed novel descriptors to trace the evolution of Poincaré plot shape over the lags. Their reliability in ultra-short cardiovascular series analysis was validated on synthetic inter-beat series generated through a physiologically plausible integral pulse frequency modulation model. Furthermore, we used the proposed approach for the investigation of the direct relationship between autonomic nervous system (ANS) dynamics and hedonic olfactory elicitation, in a group of 30 healthy subjects. Participants with a similar olfactory threshold were selected, and were asked to score 5-s stimuli in terms of arousal and valence levels according to the Russell's circumflex model of affect. Their ANS response was investigated in 35-s windows after the elicitation. Experimental results showed a gender-specific, high discriminant power of the proposed approach, discerning between pleasant and unpleasant odorants with an accuracy of 83.33% and 73.33% for men and for women, respectively. Graphical Abstract Olfaction plays a crucial role in our life and is strictly related to the Autonomic Nervous System (ANS) activity, which can be monitored studying Heart Rate Variability. We used the Lagged Poincare Plot approach to recognize gender-specific ANS response in 35-second windows after the elicitation through pleasant/unpleasant odorants.

The Complexity of Dreams: a Multiscale Entropy Study on Cardiovascular Variability Series.

Uncovering the physiological correlates of dreams is one of the most ambitious aim of multidisciplinary neuroscientific research. Here we investigated Autonomic Nervous System (ANS) dynamics associated with a dream recall, with a particular focus on the complexity assessment on cardiovascular control. We recorded electrocardiogram and arterial blood pressure signals from eight healthy subjects during rapid-eye-movement sleep before awakenings. Recordings were then split into two groups: the ones with a dream experience, and the ones without recall of dream experiences. The randomness of cardiovascular variability series was assessed through Sample Entropy metrics, which did not show any statistical difference between groups. On the other hand, a multiscale complexity analysis based on Distribution Entropy and Fuzzy Entropy revealed that a higher cardiovascular complexity is associated with a dreaming experience.

Heartbeat Dynamics Analysis under Cold-Pressure Test using Wavelet p-Leader Non-Gaussian Multiscale Expansions.

Multiscale and multifractal (MF) analyses have been proven an effective tool for the characterisation of heartbeat dynamics in physiological and pathological conditions. However, pre-processing methods for the unevenly sampled heartbeat interval series are known to affect the estimation of MF properties. In this study, we employ a recently proposed method based on wavelet p-leaders MF spectra to estimate MF properties from cardiovascular variability series, which are also pre-processed through an inhomogeneous point-process modelling. Particularly, we exploit a non-Gaussian multiscale expansion to study changes in heartbeat dynamics as a response to a sympathetic elicitation given by the cold-pressor test. By comparing MF estimates from raw heartbeat series and the point-process model, results suggest that the proposed modelling provides features statistically discerning between stress and resting condition at different time scales. These findings contribute to a comprehensive characterization of autonomic nervous system activity on cardiovascular control during cold-pressor elicitation.

Quantification of Different Regulatory Pathways Contributing to Heartbeat Dynamics during Multiple Stimuli: a Proof of the Concept.

The dynamical interplay between brain and heart is mediated by several feedback mechanisms including the central autonomic network and baroreflex loop at a peripheral level, also for a short-term regulation. State of the art focused on the characterization of each regulatory pathway through a single stressor elicitation. However, no studies targeted the actual quantification of different mediating routes leading to the generation of heartbeat dynamics, particularly in case of combined exogenous stimuli. In this study, we propose a new approach based on computational modeling to quantify the contribution of multiple concurrent stimuli in modulating cardiovascular dynamics. In this preliminary attempt, the model estimates the high-frequency power of heartbeat dynamics, and derives disentangling coefficients quantifying the effect of multiple elicitations. Model evaluation is performed on healthy rate variability (HRV) series from fourteen healthy subjects undergoing physical (tilt-table) and mental stressors (aritmetics), as well as their combined administration. Results indicate that, at a group-wise level, in base of concurrent physical and mental elicitations, the physical stressor contributes for the 85% of the resulting heartbeat dynamics. These findings are in agreement with the current knowledge on heartbeat regulatory systems, providing valuable perspectives on the quantification of underlying generative mechanisms of HRV.

Wavelet p-Leader Non-Gaussian Multiscale Expansions for EEG series: an Exploratory Study on Cold-Pressor Test.

Brain dynamics recorded through electroencephalography (EEG) have been proven to be the output of a nonstationary and nonlinear system. Thus, multifractality of EEG series has been exploited as a useful tool for a neurophysiological characterization in health and disease. However, the role of EEG multifractality under peripheral stress is unknown. In this study, we propose to make use of a novel tool, the recently defined non-Gaussian multiscale analysis, to investigate brain dynamics in the range of 4-8Hz following a cold-pressor test versus a resting state. The method builds on the wavelet p-leader multifractal spectrum to quantify different types of departure from Gaussian and linear properties, and is compared here to standard linear descriptive indices. Results suggest that the proposed non-Gaussian multiscale indices were able to detect expected changes over the somatosensory and premotor cortices, over regions different from those detected by linear analyses. They further indicate that preferred responses for the contralateral somatosensory cortex occur at scales 2.5s and 5s. These findings contribute to the characterization of the so-called central autonomic network, linking dynamical changes at a peripheral and a central nervous system levels.

Cardiovascular assessment of supportive doctor-patient communication using multi-scale and multi-lag analysis of heartbeat dynamics.

Emphatic doctor-patient communication has been associated with improved psycho-physiological well-being involving cardiovascular and neuroendocrine responses. Nevertheless, a comprehensive assessment of heartbeat linear and nonlinear dynamics throughout the communication of a life-threatening disease has not been performed yet. To this extent, we studied linear heartbeat dynamics through the extraction of time-frequency domain measurements, as well as heartbeat nonlinear and complex dynamics through novel approaches to compute multi-scale and multi-lag series analyses: namely, the multi-scale distribution entropy and lagged Poincaré plot symbolic analysis. Heart rate variability series were recorded from 54 healthy female subjects who were blind to the aim of the experiment. Participants were randomly assigned into two groups: 27 subjects watched a video where an oncologist discloses the diagnosis of a cancer metastasis to a patient, whereas the remaining 27 watched the same video including four additional supportive comments by the clinician. Considering differences between the beginning and the end of each communication video, results from non-parametric Wilcoxon tests demonstrated that, at a group level, significant differences occurred in heartbeat linear and nonlinear dynamics, with lower complexity during nonsupportive communication. Furthermore, a support vector machine algorithm, validated using a leave-one-subject-out procedure, was able to discern the supportive experience at a single-subject level with an accuracy of 83.33% when nonlinear features were considered, dropping to 51.85% when using standard HRV features only. In conclusion, heartbeat nonlinear and complex dynamics can be a viable tool for the psycho-physiological evaluation of supportive doctor-patient communication. Graphical Abstract Scheme of the three main stages of the study: signal acquisition during doctor-patient communication, ECG signal processing and pattern recognition results.

A New Sympathovagal Balance Index from Electrodermal Activity and Instantaneous Vagal Dynamics: A Preliminary Cold Pressor Study.

Sympathovagal balance, an autonomic index resulting from the sympathetic and parasympathetic influences on cardiovascular control, has been extensively used in the research practice. The current assessment is based on analyzing Heart Rate Variability (HRV) series in the frequency domain by regarding the ratio between the low and high frequency components (LF/HF). Nevertheless, LF and HF powers are known to be both influenced by vagal activity which strongly bias the accuracy of this method. To this extent, in this study we combine time-varying estimates from electrodermal activity (EDA) and HRV to propose a novel index of sympathovagal balance. Particularly, sympathetic activity is estimated from the EDA power calculated within the 0.045-0.25Hz bandwidth $(EDA_{Symp})$, whereas parasympathetic dynamics is measured instantaneously through a point-process modeling framework devised for heartbeat dynamics $(HF_{pp})$. We test our new index $SV = EDA_{Symp/HF_{pp}}$ on data gathered from 22 healthy subjects (7 females and 15 males) undergoing a 3 minutes gold standard protocol for sympathetic elicitation as the cold-pressor test (CPT). Results show that the activation of the proposed sympathovagal tone is consistent with CPT elicitation and is associated with a significantly higher statistical discriminant power than the standard LF/HF ratio, also revealing different dynamics between female and male subjects.

A new Modelling Framework to Study Time-Varying Directional Brain-Heart Interactions: Preliminary Evaluations and Perspectives.

We propose a novel modelling framework to study non-stationary, directional brain-heart interplay in a time varying fashion. Considering electroencephalographic (EEG) signals and Heart Rate Variability (HRV) series as inputs, a new multivariate formulation is derived from proper coupling functions linking cortical electrical activity and heartbeat dynamics generation models. These neural-autonomic coupling rules are formalised according to the current knowledge on the central autonomic network and fully parametrised in adaptive coefficients quantifying the information outflow from-brain-to- heart as well as from-heart-to-brain. Such coefficients can be effectively estimated by solving the model inverse problem, and profitably exploited for a novel assessment of brain-heart interactions. Here we show preliminary experimental results gathered from 27 healthy volunteers undergoing significant sympatho-vagal perturbations through cold-pressor test and discuss prospective uses of this novel methodological frame- work. Specifically, we highlight how the directional brain-heart coupling significantly increases during prolonged baroreflex elicitation with specific time delays and throughout specific brain areas, especially including fronto-parietal regions and lateralisation mechanisms in the temporal cortices.

A Multiclass Arousal Recognition using HRV Nonlinear Analysis and Affective Images.

This paper reports on a multiclass arousal recognition system based on autonomic nervous system linear and nonlinear dynamics during affective visual elicitation. We propose a new hybrid method based on Lagged Poincaré Plot (LPP) and symbolic analysis, hereinafter called LPPsymb. This tool uses symbolic analysis to evaluate the irregularity of the trends of Lagged Poincaré Plot (LPP) quantifiers over the lags, and is here applied to investigate complex Heart Rate Variability (HRV) changes during emotion stimuli. In the experimental protocol 22 healthy subjects were elicited through a passive visualization of affective images gathered from the international affective picture system. LPPsymb and standard HRV analysis (defined in time and frequency domains) were applied to HRV series of one minute length. Then, an ad-hoc pattern recognition algorithm based on quadratic discriminant classifier was implemented and validated through a leave-onesubject-out procedure. The best performance of the proposed classification algorithm for recognizing the four classes of arousal was obtained using nine features comprising heartbeat complex dynamics, achieving an accuracy of 71.59%.

A novel Heart Rate Variability analysis using Lagged Poincaré plot: A study on hedonic visual elicitation.

This paper reports on a novel method for the analysis of Heart Rate Variability (HRV) through Lagged Poincaré Plot (LPP) theory. Specifically a hybrid method, LPPsymb, including LPP quantifiers and related symbolic dynamics was proposed. LPP has been applied to investigate the autonomic response to pleasant and unpleasant pictures extracted from the International Affective Picture System (IAPS). IAPS pictures are standardized in terms of level of arousal, i.e. the intensity of the evoked emotion, and valence, i.e. the level of pleasantness/unpleasantness, according to the Circumplex model of Affects (CMA). Twenty-two healthy subjects were enrolled in the experiment, which comprised four sessions with increasing arousal level. Within each session valence increased from positive to negative. An ad-hoc pattern recognition algorithm using a Leave-One-Subject-Out (LOSO) procedure based on a Quadratic Discriminant Classifier (QDC) was implemented. Our pattern recognition system was able to classify pleasant and unpleasant sessions with an accuracy of 71.59%. Therefore, we can suggest the use of the LPPsymb for emotion recognition.

Investigation of Lagged Poincaré Plot reliability in ultra-short synthetic and experimental Heart Rate Variability series.

This study reports on the reliability of Lagged Poincaré Plot (LPP) parameters calculated from ultra-short cardiovascular time series (from 30 to 180 seconds). ity (HRV) signals, whereas a few studies have studied nonlinear approaches. Particularly, methods derived from the phase-space theory, especially the ones employing multi-lag analyses, are usually considered to be inaccurate with a low number of samples. Here we propose a comprehensive study about LPP, using both synthetic and real RR series. Specifically, we considered 109 5-minutes HRV series: 60 synthetic series generated through the Integral Pulse Frequency Modulation (IPFM) model and 49 experimental series acquired from healthy subjects during resting-state. Three parameters have been extracted through the ellipse-fitting method, SD1, SD2 and S, using ten values of lag. All LPP parameters were estimated by averaging estimates gathered from segments of 30, 120 and 180 seconds, and compared with the once from 5-minute series. Results showed Spearman's correlation coefficients higher than 0.9 in both synthetic and real series. In conclusion, SD1 gave promising results in terms of percentage absolute error, when it was extracted from series with a duration less than three minutes.

Inhomogeneous Point-Processes to Instantaneously Assess Affective Haptic Perception through Heartbeat Dynamics Information.

This study proposes the application of a comprehensive signal processing framework, based on inhomogeneous point-process models of heartbeat dynamics, to instantaneously assess affective haptic perception using electrocardiogram-derived information exclusively. The framework relies on inverse-Gaussian point-processes with Laguerre expansion of the nonlinear Wiener-Volterra kernels, accounting for the long-term information given by the past heartbeat events. Up to cubic-order nonlinearities allow for an instantaneous estimation of the dynamic spectrum and bispectrum of the considered cardiovascular dynamics, as well as for instantaneous measures of complexity, through Lyapunov exponents and entropy. Short-term caress-like stimuli were administered for 4.3-25 seconds on the forearms of 32 healthy volunteers (16 females) through a wearable haptic device, by selectively superimposing two levels of force, 2 N and 6 N, and two levels of velocity, 9.4 mm/s and 65 mm/s. Results demonstrated that our instantaneous linear and nonlinear features were able to finely characterize the affective haptic perception, with a recognition accuracy of 69.79% along the force dimension, and 81.25% along the velocity dimension.

Combining electroencephalographic activity and instantaneous heart rate for assessing brain-heart dynamics during visual emotional elicitation in healthy subjects.

Emotion perception, occurring in brain areas such as the prefrontal cortex and amygdala, involves autonomic responses affecting cardiovascular dynamics. However, how such brain-heart dynamics is further modulated by emotional valence (pleasantness/unpleasantness), also considering different arousing levels (the intensity of the emotional stimuli), is still unknown. To this extent, we combined electroencephalographic (EEG) dynamics and instantaneous heart rate estimates to study emotional processing in healthy subjects. Twenty-two healthy volunteers were elicited through affective pictures gathered from the International Affective Picture System. The experimental protocol foresaw 110 pictures, each of which lasted 10 s, associated to 25 different combinations of arousal and valence levels, including neutral elicitations. EEG data were processed using short-time Fourier transforms to obtain time-varying maps of cortical activation, whereas the associated instantaneous cardiovascular dynamics was estimated in the time and frequency domains through inhomogeneous point-process models. Brain-heart linear and nonlinear coupling was estimated through the maximal information coefficient (MIC). Considering EEG oscillations in theθband (4-8 Hz), MIC highlighted significant arousal-dependent changes between positive and negative stimuli, especially occurring at intermediate arousing levels through the prefrontal cortex interplay. Moreover, high arousing elicitations seem to mitigate changes in brain-heart dynamics in response to pleasant/unpleasant visual elicitation.

Predicting seizures in untreated temporal lobe epilepsy using point-process nonlinear models of heartbeat dynamics.

Symptoms of temporal lobe epilepsy (TLE) are frequently associated with autonomic dysregulation, whose underlying biological processes are thought to strongly contribute to sudden unexpected death in epilepsy (SUDEP). While abnormal cardiovascular patterns commonly occur during ictal events, putative patterns of autonomic cardiac effects during pre-ictal (PRE) periods (i.e. periods preceding seizures) are still unknown. In this study, we investigated TLE-related heart rate variability (HRV) through instantaneous, nonlinear estimates of cardiovascular oscillations during inter-ictal (INT) and PRE periods. ECG recordings from 12 patients with TLE were processed to extract standard HRV indices, as well as indices of instantaneous HRV complexity (dominant Lyapunov exponent and entropy) and higher-order statistics (bispectra) obtained through definition of inhomogeneous point-process nonlinear models, employing Volterra-Laguerre expansions of linear, quadratic, and cubic kernels. Experimental results demonstrate that the best INT vs. PRE classification performance (balanced accuracy: 73.91%) was achieved only when retaining the time-varying, nonlinear, and non-stationary structure of heartbeat dynamical features. The proposed approach opens novel important avenues in predicting ictal events using information gathered from cardiovascular signals exclusively.

Brain-heart linear and nonlinear dynamics during visual emotional elicitation in healthy subjects.

This study investigates brain-heart dynamics during visual emotional elicitation in healthy subjects through linear and nonlinear coupling measures of EEG spectrogram and instantaneous heart rate estimates. To this extent, affective pictures including different combinations of arousal and valence levels, gathered from the International Affective Picture System, were administered to twenty-two healthy subjects. Time-varying maps of cortical activation were obtained through EEG spectral analysis, whereas the associated instantaneous heartbeat dynamics was estimated using inhomogeneous point-process linear models. Brain-Heart linear and nonlinear coupling was estimated through the Maximal Information Coefficient (MIC), considering EEG time-varying spectra and point-process estimates defined in the time and frequency domains. As a proof of concept, we here show preliminary results considering EEG oscillations in the θ band (4-8 Hz). This band, indeed, is known in the literature to be involved in emotional processes. MIC highlighted significant arousal-dependent changes, mediated by the prefrontal cortex interplay especially occurring at intermediate arousing levels. Furthermore, lower and higher arousing elicitations were associated to not significant brain-heart coupling changes in response to pleasant/unpleasant elicitations.

Point-process nonlinear autonomic assessment of depressive states in bipolar patients.

INTRODUCTION: This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Studying Cardiovascular and Respiratory Systems". OBJECTIVES: The goal of this work is to apply a computational methodology able to characterize mood states in bipolar patients through instantaneous analysis of heartbeat dynamics. METHODS: A Point-Process-based Nonlinear Autoregressive Integrative (NARI) model is applied to analyze data collected from five bipolar patients (two males and three females, age 42.4 ± 10.5 range 32 -56) undergoing a dedicated affective elicitation protocol using images from the International Affective Picture System (IAPS) and Thematic Apperception Test (TAT). The study was designed within the European project PSYCHE (Personalised monitoring SYstems for Care in mental HEalth). RESULTS: RESULTS demonstrate that the inclusion of instantaneous higher order spectral (HOS) features estimated from the NARI nonlinear assessment significantly improves the accuracy in successfully recognizing specific mood states such as euthymia and depression with respect to results using only linear indices. In particular, a specificity of 74.44% using the instantaneous linear features set, and 99.56% using also the nonlinear feature set were achieved. Moreover, IAPS emotional elicitation resulted in a more discriminant procedure with respect to the TAT elicitation protocol. CONCLUSIONS: A significant pattern of instantaneous heartbeat features was found in depressive and euthymic states despite the inter-subject variability. The presented point-process Heart Rate Variability (HRV) nonlinear methodology provides a promising application in the field of mood assessment in bipolar patients.

Quantitative EEG analysis in minimally conscious state patients during postural changes.

Mobilization and postural changes of patients with cognitive impairment are standard clinical practices useful for both psychic and physical rehabilitation process. During this process, several physiological signals, such as Electroen-cephalogram (EEG), Electrocardiogram (ECG), Photopletysmography (PPG), Respiration activity (RESP), Electrodermal activity (EDA), are monitored and processed. In this paper we investigated how quantitative EEG (qEEG) changes with postural modifications in minimally conscious state patients. This study is quite novel and no similar experimental data can be found in the current literature, therefore, although results are very encouraging, a quantitative analysis of the cortical area activated in such postural changes still needs to be deeply investigated. More specifically, this paper shows EEG power spectra and brain symmetry index modifications during a verticalization procedure, from 0 to 60 degrees, of three patients in Minimally Consciousness State (MCS) with focused region of impairment. Experimental results show a significant increase of the power in ß band (12 - 30 Hz), commonly associated to human alertness process, thus suggesting that mobilization and postural changes can have beneficial effects in MCS patients.

On the deconvolution analysis of electrodermal activity in bipolar patients.

People affected by bipolar disorders experience alternating states of depression with episodes of mania or hypomania. This mental can lead to a poor handling of daily routines, can worsen personal relationships, and often can be life-threatening. This preliminary study aims at investigating how the autonomic nervous system, in terms of electrodermal activity, responds to specific controlled emotional stimuli in bipolar patients. More specifically, we present here a method to deploy the analysis of ElectroDermal Activity (EDA) to discriminate clinical mood states. EDA was analyzed by using a deconvolution method to separate tonic from phasic components. The three subjects recruited and the experimental protocol used here is part of the European project PSYCHE. Preliminary results show that the bipolar mood states can be related to electrodermal tonic activity.