Depression Recognition Using Daily Wearable-Derived Physiological Data

The objective identification of depression using physiological data has emerged as a significant research focus within the field of psychiatry. The advancement of wearable physiological measurement devices has opened new avenues for the identification of individuals with depression in everyday-life contexts. Compared to other objective measurement methods, wearables offer the potential for continuous, unobtrusive monitoring, which can capture subtle physiological changes indicative of depressive states. The present study leverages multimodal wristband devices to collect data from fifty-eight participants clinically diagnosed with depression during their normal daytime activities over six hours. Data collected include pulse wave, skin conductance, and triaxial acceleration. For comparison, we also utilized data from fifty-eight matched healthy controls from a publicly available dataset, collected using the same devices over equivalent durations. Our aim was to identify depressive individuals through the analysis of multimodal physiological measurements derived from wearable devices in daily life scenarios. We extracted static features such as the mean, variance, skewness, and kurtosis of physiological indicators like heart rate, skin conductance, and acceleration, as well as autoregressive coefficients of these signals reflecting the temporal dynamics. Utilizing a Random Forest algorithm, we distinguished depressive and non-depressive individuals with varying classification accuracies on data aggregated over 6 h, 2 h, 30 min, and 5 min segments, as 90.0%, 84.7%, 80.1%, and 76.0%, respectively. Our results demonstrate the feasibility of using daily wearable-derived physiological data for depression recognition. The achieved classification accuracies suggest that this approach could be integrated into clinical settings for the early detection and monitoring of depressive symptoms. Future work will explore the potential of these methods for personalized interventions and real-time monitoring, offering a promising avenue for enhancing mental health care through the integration of wearable technology.

Digital phenotyping in bipolar disorder: Using longitudinal Fitbit data and personalized machine learning to predict mood symptomatology

BACKGROUND

Effective treatment of bipolar disorder (BD) requires prompt response to mood episodes. Preliminary studies suggest that predictions based on passive sensor data from personal digital devices can accurately detect mood episodes (e.g., between routine care appointments), but studies to date do not use methods designed for broad application. This study evaluated whether a novel, personalized machine learning approach, trained entirely on passive Fitbit data, with limited data filtering could accurately detect mood symptomatology in BD patients.

METHODS

We analyzed data from 54 adults with BD, who wore Fitbits and completed bi-weekly self-report measures for 9 months. We applied machine learning (ML) models to Fitbit data aggregated over two-week observation windows to detect occurrences of depressive and (hypo)manic symptomatology, which were defined as two-week windows with scores above established clinical cutoffs for the Patient Health Questionnaire-8 (PHQ-8) and Altman Self-Rating Mania Scale (ASRM) respectively.

RESULTS

As hypothesized, among several ML algorithms, Binary Mixed Model (BiMM) forest achieved the highest area under the receiver operating curve (ROC-AUC) in the validation process. In the testing set, the ROC-AUC was 86.0% for depression and 85.2% for (hypo)mania. Using optimized thresholds calculated with Youden's J statistic, predictive accuracy was 80.1% for depression (sensitivity of 71.2% and specificity of 85.6%) and 89.1% for (hypo)mania (sensitivity of 80.0% and specificity of 90.1%).

CONCLUSION

We achieved sound performance in detecting mood symptomatology in BD patients using methods designed for broad application. Findings expand upon evidence that Fitbit data can produce accurate mood symptomatology predictions. Additionally, to the best of our knowledge, this represents the first application of BiMM forest for mood symptomatology prediction. Overall, results move the field a step toward personalized algorithms suitable for the full population of patients, rather than only those with high compliance, access to specialized devices, or willingness to share invasive data.

Uncovering Emotions: A Pilot Study on Classifying Moods in the Valence-Arousal Space using In-the-Wild Passive Data

Mood classification from passive data promises to provide an unobtrusive way to track a person's emotions over time. In this exploratory study, we collected phone sensor data and physiological signals from 8 individuals, including 5 healthy participants and 3 depressed patients, for a maximum of 35 days. Participants were asked to answer a digital questionnaire three times daily, resulting in a total of 334 self-reported mood state samples. Gradient-boosting classification was applied to the collected passive data to categorize 4 mood states in the Valence-Energetic Arousal space. The cross-validation results showed better classification performance compared to a baseline model, which always predicts the majority class. The classifier using passive data had an area under the precision-recall curve of 0.39 (SD = 0.1) while the baseline had 0.26 (SD = 0.03), suggesting the presence of information in the collected features that support the classification process. The model identified the entropy of the heart rate and the average physical activity in the preceding 8 hours, along with the max normal-to-normal (NN) sinus beat interval and the NN low frequency-high frequency ratio during the questionnaire completion, as the most important features in its analysis. Additionally, the time range of data collection was considered a contextual factor.

Systematic review and meta-analysis of performance of wearable artificial intelligence in detecting and predicting depression

Given the limitations of traditional approaches, wearable artificial intelligence (AI) is one of the technologies that have been exploited to detect or predict depression. The current review aimed at examining the performance of wearable AI in detecting and predicting depression. The search sources in this systematic review were 8 electronic databases. Study selection, data extraction, and risk of bias assessment were carried out by two reviewers independently. The extracted results were synthesized narratively and statistically. Of the 1314 citations retrieved from the databases, 54 studies were included in this review. The pooled mean of the highest accuracy, sensitivity, specificity, and root mean square error (RMSE) was 0.89, 0.87, 0.93, and 4.55, respectively. The pooled mean of lowest accuracy, sensitivity, specificity, and RMSE was 0.70, 0.61, 0.73, and 3.76, respectively. Subgroup analyses revealed that there is a statistically significant difference in the highest accuracy, lowest accuracy, highest sensitivity, highest specificity, and lowest specificity between algorithms, and there is a statistically significant difference in the lowest sensitivity and lowest specificity between wearable devices. Wearable AI is a promising tool for depression detection and prediction although it is in its infancy and not ready for use in clinical practice. Until further research improve its performance, wearable AI should be used in conjunction with other methods for diagnosing and predicting depression. Further studies are needed to examine the performance of wearable AI based on a combination of wearable device data and neuroimaging data and to distinguish patients with depression from those with other diseases.

Wearable Artificial Intelligence for Anxiety and Depression: Scoping Review

BACKGROUND

Anxiety and depression are the most common mental disorders worldwide. Owing to the lack of psychiatrists around the world, the incorporation of artificial intelligence (AI) into wearable devices (wearable AI) has been exploited to provide mental health services.

OBJECTIVE

This review aimed to explore the features of wearable AI used for anxiety and depression to identify application areas and open research issues.

METHODS

We searched 8 electronic databases (MEDLINE, PsycINFO, Embase, CINAHL, IEEE Xplore, ACM Digital Library, Scopus, and Google Scholar) and included studies that met the inclusion criteria. Then, we checked the studies that cited the included studies and screened studies that were cited by the included studies. The study selection and data extraction were carried out by 2 reviewers independently. The extracted data were aggregated and summarized using narrative synthesis.

RESULTS

Of the 1203 studies identified, 69 (5.74%) were included in this review. Approximately, two-thirds of the studies used wearable AI for depression, whereas the remaining studies used it for anxiety. The most frequent application of wearable AI was in diagnosing anxiety and depression; however, none of the studies used it for treatment purposes. Most studies targeted individuals aged between 18 and 65 years. The most common wearable device used in the studies was Actiwatch AW4 (Cambridge Neurotechnology Ltd). Wrist-worn devices were the most common type of wearable device in the studies. The most commonly used category of data for model development was physical activity data, followed by sleep data and heart rate data. The most frequently used data set from open sources was Depresjon. The most commonly used algorithm was random forest, followed by support vector machine.

CONCLUSIONS

Wearable AI can offer great promise in providing mental health services related to anxiety and depression. Wearable AI can be used by individuals for the prescreening assessment of anxiety and depression. Further reviews are needed to statistically synthesize the studies' results related to the performance and effectiveness of wearable AI. Given its potential, technology companies should invest more in wearable AI for the treatment of anxiety and depression.

A Bibliometric Analysis of Wearable Device Research Trends 2001-2022-A Study on the Reversal of Number of Publications and Research Trends in China and the USA

In recent years, Wearable Devices have been used in a wide variety of applications and fields, but because they span so many different disciplines, it is difficult to ascertain the intellectual structure of this entire research domain. No review encompasses the whole research domain related to Wearable Devices. In this study, we collected articles on wearable devices from 2001 to 2022 and quantitatively organized them by bibliometric analysis to clarify the intellectual structure of this research domain as a whole. The cluster analysis, co-occurrence analysis, and network centrality analysis were conducted on articles collected from the Web of Science. As a result, we identified one cluster that represents applied research and two clusters that represent basic research in this research domain. Furthermore, focusing on the top two countries contributing to this research domain, China and the USA., it was confirmed that China is extremely inclined toward basic research and the USA. toward applied research, indicating that applied and basic research are in balance. The basic intellectual structure of this cross-sectional research domain was identified. The results summarize the current state of research related to Wearable Devices and provide insight into trends.

Application of artificial intelligence in wearable devices: Opportunities and challenges

BACKGROUND AND OBJECTIVES

Wearable technologies have added completely new and fast emerging tools to the popular field of personal gadgets. Aside from being fashionable and equipped with advanced hardware technologies such as communication modules and networking, wearable devices have the potential to fuel artificial intelligence (AI) methods with a wide range of valuable data.

METHODS

Various AI techniques such as supervised, unsupervised, semi-supervised and reinforcement learning (RL) have already been used to carry out various tasks. This paper reviews the recent applications of wearables that have leveraged AI to achieve their objectives.

RESULTS

Particular example applications of supervised and unsupervised learning for medical diagnosis are reviewed. Moreover, examples combining the internet of things, wearables, and RL are reviewed. Application examples of wearables will be also presented for specific domains such as medical, industrial, and sport. Medical applications include fitness, movement disorder, mental health, etc. Industrial applications include employee performance improvement with the aid of wearables. Sport applications are all about providing better user experience during workout sessions or professional gameplays.

CONCLUSION

The most important challenges regarding design and development of wearable devices and the computation burden of using AI methods are presented. Finally, future challenges and opportunities for wearable devices are presented.

Portable technologies for digital phenotyping of bipolar disorder: A systematic review

BACKGROUND

Bias-prone psychiatric interviews remain the mainstay of bipolar disorder (BD) assessment. The development of digital phenotyping promises to improve BD management. We present a systematic review of the evidence about the use of portable digital devices for the identification of BD, BD types and BD mood states and for symptom assessment.

METHODS

We searched Web of Knowledge^SM, Scopus ®, IEEE Xplore, and ACM Digital Library databases (until 5/1/2021) for articles evaluating the use of portable/wearable digital devices, such as smartphone apps, wearable sensors, audio and/or visual recordings, and multimodal tools. The protocol is registered in PROSPERO (CRD42020200086).

RESULTS

We included 62 studies (2325 BD; 724 healthy controls, HC): 27 using smartphone apps, either for recording self-assessments (n = 10) or for passively gathering metadata (n = 7) or both (n = 10); 15 using wearable sensors for physiological parameters; 17 analysing audio and/or video recordings; 3 using multiple technologies. Two thirds of the included studies applied artificial intelligence (AI)-based approaches. They achieved fair to excellent classification performances.

LIMITATIONS

The included studies had small sample sizes and marked heterogeneity. Evidence of overfitting emerged, limiting generalizability. The absence of clear guidelines about reporting classification performances, with no shared standard metrics, makes results hardly interpretable and comparable.

CONCLUSIONS

New technologies offer a noteworthy opportunity to BD digital phenotyping with objectivity and high granularity. AI-based models could deliver important support in clinical decision-making. Further research and cooperation between different stakeholders are needed for addressing methodological, ethical and socio-economic considerations.

Effects of mood and aging on keystroke dynamics metadata and their diurnal patterns in a large open-science sample: A BiAffect iOS study

OBJECTIVE

Ubiquitous technologies can be leveraged to construct ecologically relevant metrics that complement traditional psychological assessments. This study aims to determine the feasibility of smartphone-derived real-world keyboard metadata to serve as digital biomarkers of mood.

MATERIALS AND METHODS

BiAffect, a real-world observation study based on a freely available iPhone app, allowed the unobtrusive collection of typing metadata through a custom virtual keyboard that replaces the default keyboard. User demographics and self-reports for depression severity (Patient Health Questionnaire-8) were also collected. Using >14 million keypresses from 250 users who reported demographic information and a subset of 147 users who additionally completed at least 1 Patient Health Questionnaire, we employed hierarchical growth curve mixed-effects models to capture the effects of mood, demographics, and time of day on keyboard metadata.

RESULTS

We analyzed 86 541 typing sessions associated with a total of 543 Patient Health Questionnaires. Results showed that more severe depression relates to more variable typing speed (P < .001), shorter session duration (P < .001), and lower accuracy (P < .05). Additionally, typing speed and variability exhibit a diurnal pattern, being fastest and least variable at midday. Older users exhibit slower and more variable typing, as well as more pronounced slowing in the evening. The effects of aging and time of day did not impact the relationship of mood to typing variables and were recapitulated in the 250-user group.

CONCLUSIONS

Keystroke dynamics, unobtrusively collected in the real world, are significantly associated with mood despite diurnal patterns and effects of age, and thus could serve as a foundation for constructing digital biomarkers.

Inflexible autonomic responses to sadness predict habitual and real-world rumination: A multi-level, multi-wave study

Inflexibility of the autonomic nervous system is relevant to depression vulnerability, but the downstream behavioral consequences of autonomic inflexibility are not well understood. Rumination, a perseverative thinking style that characterizes depression, is one candidate phenotype relevant to autonomic inflexibility. Undergraduates (N = 134) completed a sadness induction while respiratory sinus arrhythmia was measured, and completed four waves of follow-up over twelve weeks during which rumination, stressful events, and symptoms of depression were measured. Individuals with less autonomic flexibility had higher levels of trait rumination, and were more likely to ruminate in daily life, regardless of stress exposure, whereas individuals with more autonomic flexibility ruminated more only in the context of stress. These findings provide the first evidence that autonomic inflexibility may confer vulnerability to context-insensitive rumination. This work suggests a potential behavioral mechanism by which autonomic inflexibility leads to problems with self-regulation and depression, suggesting multiple avenues for intervention to target these markers of vulnerability.

Evaluating depression with multimodal wristband-type wearable device: screening and assessing patient severity utilizing machine-learning

OBJECTIVE

We aimed to develop a machine learning algorithm to screen for depression and assess severity based on data from wearable devices.

METHODS

We used a wearable device that calculates steps, energy expenditure, body movement, sleep time, heart rate, skin temperature, and ultraviolet light exposure. Depressed patients and healthy volunteers wore the device continuously for the study period. The modalities were compared hourly between patients and healthy volunteers. XGBoost was used to build machine learning models and 10-fold cross-validation was applied for the validation.

RESULTS

Forty-five depressed patients and 41 healthy controls participated, creating a combined 5,250 days' worth of data. Heart rate, steps, and sleep were significantly different between patients and healthy volunteers in some comparisons. Similar differences were also observed longitudinally when patients' symptoms improved. Based on seven days' data, the model identified symptomatic patients with 0.76 accuracy and predicted Hamilton Depression Rating Scale-17 scores with a 0.61 correlation coefficient. Skin temperature, sleep time-related features, and the correlation of those modalities were the most significant features in machine learning.

LIMITATIONS

The small number of subjects who participated in this study may have weakened the statistical significance of the study. There are differences in the demographic data among groups although we performed a correction for multiple comparisons. Validation in independent datasets was not performed, although 10-fold cross validation with the internal data was conducted.

CONCLUSION

The results indicated that utilizing wearable devices and machine learning may be useful in identifying depression as well as assessing severity.

Self-health monitoring and wearable neurotechnologies

Brain-computer interfaces and wearable neurotechnologies are now used to measure real-time neural and physiologic signals from the human body and hold immense potential for advancements in medical diagnostics, prevention, and intervention. Given the future role that wearable neurotechnologies will likely serve in the health sector, a critical state-of-the-art assessment is necessary to gain a better understanding of their current strengths and limitations. In this chapter we present wearable electroencephalography systems that reflect groundbreaking innovations and improvements in real-time data collection and health monitoring. We focus on specifications reflecting technical advantages and disadvantages, discuss their use in fundamental and clinical research, their current applications, limitations, and future directions. While many methodological and ethical challenges remain, these systems host the potential to facilitate large-scale data collection far beyond the reach of traditional research laboratory settings.

Using ambulatory assessment to measure dynamic risk processes in affective disorders

BACKGROUND

Rapid advances in the capability and affordability of digital technology have begun to allow for the intensive monitoring of psychological and physiological processes associated with affective disorders in daily life. This technology may enable researchers to overcome some limitations of traditional methods for studying risk in affective disorders, which often (implicitly) assume that risk factors are distal and static - that they do not change over time. In contrast, ambulatory assessment (AA) is particularly suited to measure dynamic "real-world" processes and to detect fluctuations in proximal risk for outcomes of interest.

METHOD

We highlight key questions about proximal and distal risk for affective disorders that AA methods (with multilevel modeling, or fully-idiographic methods) allow researchers to evaluate.

RESULTS

Key questions include between-subject questions to understand who is at risk (e.g., are people with more affective instability at greater risk than others?) and within-subject questions to understand when risk is most acute among those who are at risk (e.g., does suicidal ideation increase when people show more sympathetic activation than usual?). We discuss practical study design and analytic strategy considerations for evaluating questions of risk in context, and the benefits and limitations of self-reported vs. passively-collected AA.

LIMITATIONS

Measurements may only be as accurate as the observation period is representative of individuals' usual life contexts. Active measurement techniques are limited by the ability and willingness to self-report.

CONCLUSIONS

We conclude by discussing how monitoring proximal risk with AA may be leveraged for translation into personalized, real-time interventions to reduce risk.

Brain Dynamics Induced by Pleasant/Unpleasant Tactile Stimuli Conveyed by Different Fabrics

In this study, we investigated brain dynamics from electroencephalographic (EEG) signals during affective tactile stimulation conveyed by the dynamical contact with different fabrics. Thirty-three healthy subjects (16 females) were enrolled to interact with a haptic device able to mimic caress-like stimuli conveyed by strips of different fabrics moved back and forth at different velocities. Specifically, two velocity levels (i.e., 9.4 and 65 mm/sec) and two kinds of fabric (i.e., burlap and silk) were selected to deliver pleasant and unpleasant affective elicitations, according to subjects' self-assessment. EEG power spectra and functional connectivity were then calculated and analyzed. Experimental results, reported in terms of p-value topographic maps, demonstrated that caresses administered through unpleasant fabrics increased brain activity in the θ (4-8 Hz), α (8-14 Hz), and β (14-30 Hz) bands, whereas the use of pleasant fabrics enhanced functional connections in specific areas (e.g., frontal, occipital, and temporal cortices) depending on the oscillations frequency and caressing velocity. Furthermore, we adopted K-NN algorithms to automatically recognize the pleasantness of the haptic stimulation at a single-subject level using EEG power spectra, achieving a recognition accuracy up to 74.24%. Finally, we showed how brain oscillation power in the α and β bands over contralateral frontal- and central-cortex were the most informative features characterizing the pleasantness of a tactile stimulus on the forearm.

Quantitative Analysis of the Effect of an Ectopic Beat on the Heart Rate Variability in the Resting Condition

The purpose of this study is to quantitatively analyze the effect of an ectopic beat on heart rate variability (HRV) in the time domain, frequency domain, and in a non-linear analysis. A quantitative analysis was carried out by generating artificial ectopic beats that probabilistically contained a missed beat or a false-detected beat, and the statistical significance was evaluated though a comparison with an ectopic-free HRV by increasing the ratio of the ectopic beat in 0.1% increments from 0 to 50%. The effect of the interpolation on the ectopic HRV was also investigated by applying nearest-neighbor interpolation, linear interpolation, and cubic spline interpolation. The results confirmed a statistically significant difference (P < 0.05) even in the less-than-1% ectopic HRV in every domain. When interpolation was applied, there were differences according to the interpolation method used, but statistical significance was secured for an ectopic beat ratio from 1 to 2% to several tens of a percent. In the effect, linear interpolation, and spline interpolation were confirmed to have a higher effect on the high-frequency related HRV variables, and nearest-neighbor interpolation had a higher effect on low-frequency related variables.

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.

Spectro-Temporal Electrocardiogram Analysis for Noise-Robust Heart Rate and Heart Rate Variability Measurement

The last few years has seen a proliferation of wearable electrocardiogram (ECG) devices in the market with applications in fitness tracking, patient monitoring, athletic performance assessment, stress and fatigue detection, and biometrics, to name a few. The majority of these applications rely on the computation of the heart rate (HR) and the so-called heart rate variability (HRV) index via time-, frequency-, or non-linear-domain approaches. Wearable/portable devices, however, are highly susceptible to artifacts, particularly those resultant from movement. These artifacts can hamper HR/HRV measurement, thus pose a serious threat to cardiac monitoring applications. While current solutions rely on ECG enhancement as a pre-processing step prior to HR/HRV calculation, existing artifact removal algorithms still perform poorly under extremely noisy scenarios. To overcome this limitation, we take an alternate approach and propose the use of a spectro-temporal ECG signal representation that we show separates cardiac components from artifacts. More specifically, by quantifying the rate-of-change of ECG spectral components over time, we show that heart rate estimates can be reliably obtained even in extremely noisy signals, thus bypassing the need for ECG enhancement. With such HR measurements in hands, we then propose a new noise-robust HRV index termed MD-HRV (modulation-domain HRV) computed as the standard deviation of the obtained HR values. Experiments with synthetic ECG signals corrupted at various different signal-to-noise levels, as well as recorded noisy signals show the proposed measure outperforming several HRV benchmark parameters computed post wavelet-based enhancement. These findings suggest that the proposed HR measures and derived MD-HRV metric are well-suited for ambulant cardiac monitoring applications, particularly those involving intense movement (e.g., elite athletic training).

Heart rate variability in bipolar disorder and borderline personality disorder: a clinical review

Heart rate variability (HRV) in psychiatric disorders has become an increasing area of interest in recent years following technological advances that enable non-invasive monitoring of autonomic nervous system regulation. However, the clinical interpretation of HRV features remain widely debated or unknown. Standardisation within studies of HRV in psychiatric disorders is poor, making it difficult to reproduce or build on previous work. Recently, a Guidelines for Reporting Articles on Psychiatry and Heart rate variability checklist has been proposed to address this issue. Here we assess studies of HRV in bipolar disorder and borderline personality disorder against this checklist and discuss the implication for ongoing research in this area.

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, LPP_symb, 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 LPP_symb for emotion recognition.

Quantitative heartbeat coupling measures in human-horse interaction

We present a study focused on a quantitative estimation of a human-horse dynamic interaction. A set of measures based on magnitude and phase coupling between heartbeat dynamics of both humans and horses in three different conditions is reported: no interaction, visual/olfactory interaction and grooming. Specifically, Magnitude Squared Coherence (MSC), Mean Phase Coherence (MPC) and Dynamic Time Warping (DTW) have been used as estimators of the amount of coupling between human and horse through the analysis of their heart rate variability (HRV) time series in a group of eleven human subjects, and one horse. The rationale behind this study is that the interaction of two complex biological systems go towards a coupling process whose dynamical evolution is modulated by the kind and time duration of the interaction itself. We achieved a congruent and consistent statistical significant difference for all of the three indices. Moreover, a Nearest Mean Classifier was able to recognize the three classes of interaction with an accuracy greater than 70%. Although preliminary, these encouraging results allow a discrimination of three distinct phases in a real human-animal interaction opening to the characterization of the empirically proven relationship between human and horse.

Perseverate or decenter? Differential effects of metacognition on the relationship between parasympathetic inflexibility and symptoms of depression in a multi-wave study

Depression often is characterized by inflexible autonomic and metacognitive processes that interfere with effective self-regulation. However, few studies have integrated these factors to improve the prediction of which individuals are at greatest risk for depression. Among 134 undergraduates, we evaluated whether parasympathetic inflexibility (a lack of reduction in respiratory sinus arrhythmia) in response to a sadness induction involving loss would prospectively predict symptoms of depression across four waves of follow-up over twelve weeks. Furthermore, we evaluated whether metacognitive components of perseverative cognition (PC) and decentering (identified by a principal component analysis) would moderate this relationship in opposite directions. Multilevel modeling demonstrated that the relationship between parasympathetic inflexibility and prospective symptoms of depression was exacerbated by PC, but attenuated by decentering. Furthermore, individuals with parasympathetic inflexibility, PC, and low decentering were at greatest risk for symptoms of depression across follow-up. These results support the utility of integrating autonomic and metacognitive risk factors to identify individuals at risk for depression.

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.

Longitudinal monitoring of heartbeat dynamics predicts mood changes in bipolar patients: A pilot study

OBJECTIVES

Recent research indicates that Heart Rate Variability (HRV) is affected in Bipolar Disorders (BD) patients. To determine whether such alterations are a mere expression of the current mood state or rather contain longitudinal information on BD course, we examined the potential influence of states adjacent in time upon HRV features measured in a target mood state.

METHODS

Longitudinal evaluation of HRV was obtained in eight BD patients by using a wearable monitoring system developed within the PSYCHE project. We extracted time-domain, frequency-domain and non-linear HRV-features and trained a Support Vector Machine (SVM) to classify HRV-features according to mood state. To evaluate the influence of adjacent mood states, we trained SVM with different HRV-feature sets: 1) belonging to each mood state considered alone; 2) belonging to each mood state and normalized using information from the preceding mood state; 3) belonging to each mood state and normalized using information from the preceding and subsequent mood states; 4) belonging to each mood state and normalized using information from two randomly chosen states.

RESULTS

SVM classification accuracy within a target state was significantly greater when HRV-features from the previous and subsequent mood states were considered.

CONCLUSIONS

Although preliminary and in need of replications our results suggest for the first time that psychophysiological states in BD contain information related to the subsequent ones. Such characteristic may be used to improve clinical management and to develop algorithms to predict clinical course and mood switches in individual patients.

State-related differences in heart rate variability in bipolar disorder

Heart rate variability (HRV) is a validated measure of sympato-vagal balance in the autonomic nervous system. HRV appears decreased in patients with bipolar disorder (BD) compared with healthy individuals, but the extent of state-related alterations has been sparingly investigated. The present study examined differences in HRV between affective states in BD. A heart rate and movement sensor weighing 8 g collected average acceleration, heart rate and the two slowest and fastest heart beats (of the most recent 16 beats) every 30 s over a period of at least three consecutive weekdays and nights in a prospective longitudinal design from a total of 31 different affective states in 16 outpatients with BD. A proxy measure of HRV was calculated as the difference between the second-shortest and the second-longest inter-beat-interval collected during each of the epochs. Analyses were based on over 100.000 HRV data-points. In unadjusted analyses and in analyses adjusted for age, gender and heart rate, during a manic state HRV was increased by 18% compared with a depressed state (eB = 1.18, 95% CI: 1.16-1.20, p < 0.001) and increased by 17% compared with a euthymic state (eB = 1.17, 95% CI: 1.15-1.19, p < 0.001), whereas there was no difference between a depressive state and a euthymic state (eB = 0.98, 95% CI: 0.96-1.00, p = 0.12). Further inclusion of BMI as a covariate did not alter any of the associations. HRV appears to be altered in a state-dependent manner in bipolar disorder and could represent a candidate state marker. Further studies with larger sample sizes are warranted.

Heart rate variability in bipolar disorder: A systematic review and meta-analysis

BACKGROUND

Heart rate variability (HRV) has been suggested reduced in bipolar disorder (BD) compared with healthy individuals (HC). This meta-analysis investigated: HRV differences in BD compared with HC, major depressive disorder or schizophrenia; HRV differences between affective states; HRV changes from mania/depression to euthymia; and HRV changes following interventions.

METHODS

A systematic review and meta-analysis reported according to the PRISMA guidelines was conducted. MEDLINE, Embase, PsycINFO, The Cochrane Library and Scopus were searched. A total of 15 articles comprising 2534 individuals were included.

RESULTS

HRV was reduced in BD compared to HC (g=-1.77, 95% CI: -2.46; -1.09, P<0.001, 10 comparisons, n=1581). More recent publication year, larger study and higher study quality were associated with a smaller difference in HRV. Large between-study heterogeneity, low study quality, and lack of consideration of confounding factors in individual studies were observed.

CONCLUSIONS

This first meta-analysis of HRV in BD suggests that HRV is reduced in BD compared to HC. Heterogeneity and methodological issues limit the evidence. Future studies employing strict methodology are warranted.

Detecting Bipolar Depression From Geographic Location Data

Objective

This paper aims to identify periods of depression using geolocation movements recorded from mobile phones in a prospective community study of individuals with bipolar disorder (BD).

Methods

Anonymized geographic location recordings from 22 BD participants and 14 healthy controls (HC) were collected over 3 months. Participants reported their depressive symptomatology using a weekly questionnaire (QIDS-SR₁₆). Recorded location data were preprocessed by detecting and removing imprecise data points and features were extracted to assess the level and regularity of geographic movements of the participant. A subset of features were selected using a wrapper feature selection method and presented to 1) a linear regression model and a quadratic generalized linear model with a logistic link function for questionnaire score estimation; and 2) a quadratic discriminant analysis classifier for depression detection in BD participants based on their questionnaire responses.

Results

HC participants did not report depressive symptoms and their features showed similar distributions to nondepressed BD participants. Questionnaire score estimation using geolocation-derived features from BD participants demonstrated an optimal mean absolute error rate of 3.73, while depression detection demonstrated an optimal (median ± IQR) F₁ score of 0.857 ± 0.022 using five features (classification accuracy: 0.849 ± 0.016; sensitivity: 0.839 ± 0.014; specificity: 0.872 ± 0.047).

Conclusion

These results demonstrate a strong link between geographic movements and depression in bipolar disorder.

Significance

To our knowledge, this is the first community study of passively recorded objective markers of depression in bipolar disorder of this scale. The techniques could help individuals monitor their depression and enable healthcare providers to detect those in need of care or treatment.

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.

Uncovering brain-heart information through advanced signal and image processing

Through their dynamical interplay, the brain and the heart ensure fundamental homeostasis and mediate a number of physiological functions as well as their disease-related aberrations. Although a vast number of ad hoc analytical and computational tools have been recently applied to the non-invasive characterization of brain and heart dynamic functioning, little attention has been devoted to combining information to unveil the interactions between these two physiological systems. This theme issue collects contributions from leading experts dealing with the development of advanced analytical and computational tools in the field of biomedical signal and image processing. It includes perspectives on recent advances in 7 T magnetic resonance imaging as well as electroencephalogram, electrocardiogram and cerebrovascular flow processing, with the specific aim of elucidating methods to uncover novel biological and physiological correlates of brain-heart physiology and physiopathology.

Relationship between cardiac vagal activity and mood congruent memory bias in major depression

BACKGROUND

Previous studies suggest that autonomic reactivity during encoding of emotional information could modulate the neural processes mediating mood-congruent memory. In this study, we use a point-process model to determine dynamic autonomic tone in response to negative emotions and its influence on long-term memory of major depressed subjects.

METHODS

Forty-eight patients with major depression and 48 healthy controls were randomly assigned to either neutral or emotionally arousing audiovisual stimuli. An adaptive point-process algorithm was applied to compute instantaneous estimates of the spectral components of heart rate variability [Low frequency (LF), 0.04-0.15 Hz; High frequency (HF), 0.15-0.4 Hz]. Three days later subjects were submitted to a recall test.

RESULTS

A significant increase in HF power was observed in depressed subjects in response to the emotionally arousing stimulus (p=0.03). The results of a multivariate analysis revealed that the HF power during the emotional segment of the stimulus was independently associated with the score of the recall test in depressed subjects, after adjusting for age, gender and educational level (Coef. 0.003, 95%CI, 0.0009-0.005, p=0.008).

LIMITATIONS

These results could only be interpreted as responses to elicitation of specific negative emotions, the relationship between HF changes and encoding/recall of positive stimuli should be further examined.

CONCLUSIONS

Alterations on parasympathetic response to emotion are involved in the mood-congruent cognitive bias observed in major depression. These findings are clinically relevant because it could constitute the mechanism by which depressed patients maintain maladaptive patterns of negative information processing that trigger and sustain depressed mood.

Gender-specific velocity recognition of caress-like stimuli through nonlinear analysis of Heart Rate Variability

This study reports on the development of a gender-specific classification system able to discern between two levels of velocity of a caress-like stimulus, through information gathered from Autonomic Nervous System (ANS) linear and nonlinear dynamics. Specifically, caress-like stimuli were administered to 32 healthy volunteers (16 males) while monitoring electrocardiogram signal to extract Heart Rate Variability (HRV) series. Caressing stimuli were administered to the forearm at a fixed force level (6 N) and two levels of velocity, 9.4 mm/s and 37 mm/s. Standard HRV measures, defined in the time and frequency domain, as well as HRV nonlinear measures were extracted during the pre- and post-stimulus sessions, and given as an input to a Support Vector Machine (SVM) classifier implementing a leave-one-subject-out procedure. Results show an accuracy of velocity recognition of 70% for the men, and 84.38% for the women, when both standard and nonlinear HRV measures were taken into account. Conversely, non-significant results were achieved considering standard measures only, or a gender-aspecific classification. We can conclude that caress-like stimuli elicitation significantly affect HRV nonlinear dynamics with a highly specific gender dependency.

Arousal recognition system based on heartbeat dynamics during auditory elicitation

This study reports on the recognition of different arousal levels, elicited by affective sounds, performed using estimates of autonomic nervous system dynamics. Specifically, as a part of the circumplex model of affect, arousal levels were recognized by properly combining information gathered from standard and nonlinear analysis of heartbeat dynamics, which was derived from the electrocardiogram (ECG). Affective sounds were gathered from the International Affective Digitized Sound System and grouped into four different levels of arousal. A group of 27 healthy volunteers underwent such elicitation while ECG signals were continuously recorded. Results showed that a quadratic discriminant classifier, as applied implementing a leave-one-subject-out procedure, achieved a recognition accuracy of 84.26%. Moreover, this study confirms the crucial role of heartbeat nonlinear dynamics for emotion recognition, hereby estimated through lagged Poincare plots.

Electroencephalographic spectral correlates of caress-like affective haptic stimuli

This paper describes how brain dynamics, as estimated through spectral analysis of electroencephalographic (EEG) oscillatory rhythms, is modified by quantifiable, affective haptic stimuli. Specifically, 32 healthy subjects (16 females) interacted with a haptic device able to convey caress-like stimuli while varying force and velocity of the device itself. More specifically, 2 values of force (i.e., "strength of the caress") and 3 velocity levels (i.e. "velocity of the caress") were combined to control the device during the experiment. Subjects were also asked to self-assess the haptic stimuli in terms of arousal (activation/ deactivation) and valence (pleasure/displeasure) scores. Results, shown in terms of p-values topographic maps, revealed a suppression of the oscillations over the controlateral somatosensory cortex, during caresses performed with the lowest force (2N) and the highest velocity (65 mm/s). This occurred in all of the frequency bands considered, α, β, and γ. Lower velocities (9.4 mm/s and 37 mm/s) did not significantly modify EEG reactivity in such bands. Concerning caresses administered at high force (6N), there was a significant decrease of EEG oscillatory activity focused on mid-frontal electrodes, in all of the considered frequency bands, when the velocity of the caresses was the lowest one. Significant sparse decrease of EEG power spectra, in all of the considered frequency bands, occurred at higher strength and velocity of the caress.

Examining Accumulated Emotional Traits in Suicide Blogs With an Emotion Topic Model

Suicide has been a major cause of death throughout the world. Recent studies have proved a reliable connection between the emotional traits and suicide. However, detection and prevention of suicide are mostly carried out in the clinical centers, which limit the effective treatments to a restricted group of people. To assist detecting suicide risks among the public, we propose a novel method by exploring the accumulated emotional information from people's daily writings (i.e., Blogs), and examining these emotional traits that are predictive of suicidal behaviors. A complex emotion topic model is employed to detect the underlying emotions and emotion-related topics in the Blog streams, based on eight basic emotion categories and five levels of emotion intensities. Since suicide is caused through an accumulative process, we propose three accumulative emotional traits, i.e., accumulation, covariance, and transition of the consecutive Blog emotions, and employ a generalized linear regression algorithm to examine the relationship between emotional traits and suicide risk. Our experiment results suggest that the emotion transition trait turns to be more discriminative of the suicide risk, and that the combination of three traits in linear regression would generate even more discriminative predictions. A classification of the suicide and nonsuicide Blog articles in our additional experiment verifies this result. Finally, we conduct a case study of the most commonly mentioned emotion-related topics in the suicidal Blogs, to further understand the association between emotions and thoughts for these authors.

Estimation of instantaneous complex dynamics through Lyapunov exponents: a study on heartbeat dynamics

Measures of nonlinearity and complexity, and in particular the study of Lyapunov exponents, have been increasingly used to characterize dynamical properties of a wide range of biological nonlinear systems, including cardiovascular control. In this work, we present a novel methodology able to effectively estimate the Lyapunov spectrum of a series of stochastic events in an instantaneous fashion. The paradigm relies on a novel point-process high-order nonlinear model of the event series dynamics. The long-term information is taken into account by expanding the linear, quadratic, and cubic Wiener-Volterra kernels with the orthonormal Laguerre basis functions. Applications to synthetic data such as the Hénon map and Rössler attractor, as well as two experimental heartbeat interval datasets (i.e., healthy subjects undergoing postural changes and patients with severe cardiac heart failure), focus on estimation and tracking of the Instantaneous Dominant Lyapunov Exponent (IDLE). The novel cardiovascular assessment demonstrates that our method is able to effectively and instantaneously track the nonlinear autonomic control dynamics, allowing for complexity variability estimations.