Depression is a mental illness that may be harmful to an individual's health. The detection of mental health disorders in the early stages and a precise diagnosis are critical to avoid social, physiological, or psychological side effects. This work analyzes physiological signals to observe if different depressive states have a noticeable impact on the blood volume pulse (BVP) and the heart rate variability (HRV) response. Although typically, HRV features are calculated from biosignals obtained with contact-based sensors such as wearables, we propose instead a novel scheme that directly extracts them from facial videos, just based on visual information, removing the need for any contact-based device. Our solution is based on a pipeline that is able to extract complete remote photoplethysmography signals (rPPG) in a fully unsupervised manner. We use these rPPG signals to calculate over 60 statistical, geometrical, and physiological features that are further used to train several machine learning regressors to recognize different levels of depression. Experiments on two benchmark datasets indicate that this approach offers comparable results to other audiovisual modalities based on voice or facial expression, potentially complementing them. In addition, the results achieved for the proposed method show promising and solid performance that outperforms hand-engineered methods and is comparable to deep learning-based approaches.
The use of cameras and computational algorithms for noninvasive, low-cost and scalable measurement of physiological (e.g., cardiac and pulmonary) vital signs is very attractive. However, diverse data representing a range of environments, body motions, illumination conditions and physiological states is laborious, time consuming and expensive to obtain. Synthetic data have proven a valuable tool in several areas of machine learning, yet are not widely available for camera measurement of physiological states. Synthetic data offer "perfect" labels (e.g., without noise and with precise synchronization), labels that may not be possible to obtain otherwise (e.g., precise pixel level segmentation maps) and provide a high degree of control over variation and diversity in the dataset. We present SCAMPS, a dataset of synthetics containing 2,800 videos (1.68M frames) with aligned cardiac and respiratory signals and facial action intensities. The RGB frames are provided alongside segmentation maps. We provide precise descriptive statistics about the underlying waveforms, including inter-beat interval, heart rate variability, and pulse arrival time. Finally, we present baseline results training on these synthetic data and testing on real-world datasets to illustrate generalizability.
Many types of ventricular and atrial cardiac arrhythmias have been discovered in clinical practice in the past 100 years, and these arrhythmias are a major contributor to sudden cardiac death. Ventricular tachycardia, ventricular fibrillation, and paroxysmal atrial fibrillation are the most commonly-occurring and dangerous arrhythmias, therefore early detection is crucial to prevent any further complications and reduce fatalities. Implantable devices such as pacemakers are commonly used in patients at high risk of sudden cardiac death. While great advances have been made in medical technology, there remain significant challenges in effective management of common arrhythmias. This thesis proposes novel arrhythmia detection and prediction methods to differentiate cardiac arrhythmias from non-life-threatening cardiac events, to increase the likelihood of detecting events that may lead to mortality, as well as reduce the incidence of unnecessary therapeutic intervention. The methods are based on detailed analysis of Heart Rate Variability (HRV) information. The results of the work show good performance of the proposed methods and support the potential for their deployment in resource-constrained devices for ventricular and atrial arrhythmia prediction, such as implantable pacemakers and defibrillators.
Heart rate variability (HRV) is a practical and noninvasive measure of autonomic nervous system activity, which plays an essential role in cardiovascular health. However, using HRV to assess physiology status is challenging. Even in clinical settings, HRV is sensitive to acute stressors such as physical activity, mental stress, hydration, alcohol, and sleep. Wearable devices provide convenient HRV measurements, but the irregularity of measurements and uncaptured stressors can bias conventional analytical methods. To better interpret HRV measurements for downstream healthcare applications, we learn a personalized diurnal rhythm as an accurate physiological indicator for each individual. We develop Physiological Multitask-Learning (PhysioMTL) by harnessing Optimal Transport theory within a Multitask-learning (MTL) framework. The proposed method learns an individual-specific predictive model from heterogeneous observations, and enables estimation of an optimal transport map that yields a push forward operation onto the demographic features for each task. Our model outperforms competing MTL methodologies on unobserved predictive tasks for synthetic and two real-world datasets. Specifically, our method provides remarkable prediction results on unseen held-out subjects given only $20\%$ of the subjects in real-world observational studies. Furthermore, our model enables a counterfactual engine that generates the effect of acute stressors and chronic conditions on HRV rhythms.
Identifying stress levels can provide valuable data for mental health analytics as well as labels for annotation systems. Although much research has been conducted into stress detection models using heart rate variability at a higher cost of data collection, there is a lack of research on the potential of using low-resolution Electrodermal Activity (EDA) signals from consumer-grade wearable devices to identify stress patterns. In this paper, we concentrate on performing statistical analyses on the stress detection capability of two popular approaches of training stress detection models with stress-related biometric signals: user-dependent and user-independent models. Our research manages to show that user-dependent models are statistically more accurate for stress detection. In terms of effectiveness assessment, the balanced accuracy (BA) metric is employed to evaluate the capability of distinguishing stress and non-stress conditions of the models trained on either low-resolution or high-resolution Electrodermal Activity (EDA) signals. The results from the experiment show that training the model with (comparatively low-cost) low-resolution EDA signal does not affect the stress detection accuracy of the model significantly compared to using a high-resolution EDA signal. Our research results demonstrate the potential of attaching the user-dependent stress detection model trained on personal low-resolution EDA signal recorded to collect data in daily life to provide users with personal stress level insight and analysis.
Complex systems, such as pathophysiological processes, commonly exhibit chaotic, nonlinear, and intermittent phenomena. Koopman operator theory and Hankel alternative view of Koopman (HAVOK) model have been widely used to decompose the chaos of the complex system dynamics into an intermittent forced linear system. Although the statistics of the intermittent forcing have been proposed to characterize intermittencies in the HAVOK model, they were not adequate to attribute for the mode switching of nonlinear dynamics and the fat-tailed non-Gaussian distribution originated from high-frequency bursts and rarely-observed intermittent forcing. The paper proposed a new intermittency dynamics analysis approach to characterize the intermittent phases, chaotic bursts, and local spectral-temporal properties of various intermittent dynamics modes using spectral decomposition and wavelet analysis. To validate our methods, the intermittency behavior of apneic events in obstructive sleep apnea disorder was selected as the case, in which heart rate variability (HRV) features were extracted. Next, we constructed the Hankel matrix from the HRV features and obtained the last eigen time-delay coordinate by singular value decomposition of the Hankel matrix, which was modeled as an intermittent forcing input. The statistics of the forcing in OSA demonstrated the fat-tailed distribution of the intermittent forcing, which correspond to the intermittency of the underlying OSA pathophysiological process. The pooled means and standard deviations of the burst duration and the inter-burst duration across OSA patients were also calculated to be minutes and minutes. Scalogram amplitude and spectral decomposition of the wavelet transform exhibited various predominant frequencies and dynamics modes associated with apneic events.
Adverse posttraumatic neuropsychiatric sequelae (APNS) are common among veterans and millions of Americans after traumatic exposures, resulting in substantial burdens for trauma survivors and society. Despite numerous studies conducted on APNS over the past decades, there has been limited progress in understanding the underlying neurobiological mechanisms due to several unique challenges. One of these challenges is the reliance on subjective self-report measures to assess APNS, which can easily result in measurement errors and biases (e.g., recall bias). To mitigate this issue, in this paper, we investigate the potential of leveraging the objective longitudinal mobile device data to identify homogeneous APNS states and study the dynamic transitions and potential risk factors of APNS after trauma exposure. To handle specific challenges posed by longitudinal mobile device data, we developed exploratory hidden Markov factor models and designed a Stabilized Expectation-Maximization algorithm for parameter estimation. Simulation studies were conducted to evaluate the performance of parameter estimation and model selection. Finally, to demonstrate the practical utility of the method, we applied it to mobile device data collected from the Advancing Understanding of RecOvery afteR traumA (AURORA) study.
This paper presents a comprehensive review of methods covering significant subjective and objective human stress detection techniques available in the literature. The methods for measuring human stress responses could include subjective questionnaires (developed by psychologists) and objective markers observed using data from wearable and non-wearable sensors. In particular, wearable sensor-based methods commonly use data from electroencephalography, electrocardiogram, galvanic skin response, electromyography, electrodermal activity, heart rate, heart rate variability, and photoplethysmography both individually and in multimodal fusion strategies. Whereas, methods based on non-wearable sensors include strategies such as analyzing pupil dilation and speech, smartphone data, eye movement, body posture, and thermal imaging. Whenever a stressful situation is encountered by an individual, physiological, physical, or behavioral change is induced which help in coping with the challenge at hand. A wide range of studies has attempted to establish a relationship between these stressful situations and the response of human beings by using different kinds of psychological, physiological, physical, and behavioral measures. Inspired by the lack of availability of a definitive verdict about the relationship of human stress with these different kinds of markers, a detailed survey about human stress detection methods is conducted in this paper. In particular, we explore how stress detection methods can benefit from artificial intelligence utilizing relevant data from various sources. This review will prove to be a reference document that would provide guidelines for future research enabling effective detection of human stress conditions.
A practical way of detecting sleep stages has become more necessary as we begin to learn about the vast effects that sleep has on people's lives. The current methods of sleep stage detection are expensive, invasive to a person's sleep, and not practical in a modern home setting. While the method of detecting sleep stages via the monitoring of brain activity, muscle activity, and eye movement, through electroencephalogram in a lab setting, provide the gold standard for detection, this paper aims to investigate a new method that will allow a person to gain similar insight and results with no obtrusion to their normal sleeping habits. Ballistocardiography (BCG) is a non-invasive sensing technology that collects information by measuring the ballistic forces generated by the heart. Using features extracted from BCG such as time of usage, heart rate, respiration rate, relative stroke volume, and heart rate variability, we propose to implement a sleep stage detection algorithm and compare it against sleep stages extracted from a Fitbit Sense Smart Watch. The accessibility, ease of use, and relatively-low cost of the BCG offers many applications and advantages for using this device. By standardizing this device, people will be able to benefit from the BCG in analyzing their own sleep patterns and draw conclusions on their sleep efficiency. This work demonstrates the feasibility of using BCG for an accurate and non-invasive sleep monitoring method that can be set up in the comfort of a one's personal sleep environment.
Given the significant amount of time people spend in vehicles, health issues under driving condition have become a major concern. Such issues may vary from fatigue, asthma, stroke, to even heart attack, yet they can be adequately indicated by vital signs and abnormal activities. Therefore, in-vehicle vital sign monitoring can help us predict and hence prevent these issues. Whereas existing sensor-based (including camera) methods could be used to detect these indicators, privacy concern and system complexity both call for a convenient yet effective and robust alternative. This paper aims to develop V2iFi, an intelligent system performing monitoring tasks using a COTS impulse radio mounted on the windshield. V2iFi is capable of reliably detecting driver's vital signs under driving condition and with the presence of passengers, thus allowing for potentially inferring corresponding health issues. Compared with prior work based on Wi-Fi CSI, V2iFi is able to distinguish reflected signals from multiple users, and hence provide finer-grained measurements under more realistic settings. We evaluate V2iFi both in lab environments and during real-life road tests; the results demonstrate that respiratory rate, heart rate, and heart rate variability can all be estimated accurately. Based on these estimation results, we further discuss how machine learning models can be applied on top of V2iFi so as to improve both physiological and psychological wellbeing in driving environments.
Background and Objective: The connection between depression and autonomous nervous system (ANS) is well documented in scientific literature. Heart rate variability (HRV) is a rich source of information for studying the dynamics of this relation. Disturbed heart dynamics in depression seriously increases mortality risk. Technical sciences help improve early detection and monitoring and offer more accurate management of treatment. Based on advances in computational power, information theory, complex systems dynamics, and nonlinear analysis applied to physiological complexity, we can now turn to novel biomarkers extracted from electrophysiological signals. This work is a cross-sectional analysis with methodological commentary of application of nonlinear measures of HRV related to depression. Methods: We systematically searched online for papers exploring the connection of depression and HRV, using both conventional and nonlinear analysis. We scrutinized chosen publications and methodologically analyzed and compared them. Results: Sixty-seven publications on the connection of HRV measures and depression meeting our inclusion criteria are selected. The effectiveness of the applied methods of electrocardiogram (ECG) analysis are compared and discussed in the light of detection and prevention of depression-related cardiac diseases. Conclusions: It is clear that aberrated ANS dynamics can be detected via ECG analysis, where nonlinear measures show to be more sensitive and accurate than standard time and spectral ones. With the portable ECG devices and cloud-based telehealth applications, monitoring of outpatients could be done anytime anywhere. We appeal for early screening for cardiovascular abnormalities in depressive patients to prevent possible deleterious events.
Objective: We propose a non-contact approach for atrial fibrillation (AF) detection from face videos. Methods: Face videos, electrocardiography (ECG), and contact photoplethysmography (PPG) from 100 healthy subjects and 100 AF patients are recorded. Data recordings from healthy subjects are all labeled as healthy. Two cardiologists evaluated ECG recordings of patients and labeled each recording as AF, sinus rhythm (SR), or atrial flutter (AFL). We use the 3D convolutional neural network for remote PPG monitoring and propose a novel loss function (Wasserstein distance) to use the timing of systolic peaks from contact PPG as the label for our model training. Then a set of heart rate variability (HRV) features are calculated from the inter-beat intervals, and a support vector machine (SVM) classifier is trained with HRV features. Results: Our proposed method can accurately extract systolic peaks from face videos for AF detection. The proposed method is trained with subject-independent 10-fold cross-validation with 30s video clips and tested on two tasks. 1) Classification of healthy versus AF: the accuracy, sensitivity, and specificity are 96.00%, 95.36%, and 96.12%. 2) Classification of SR versus AF: the accuracy, sensitivity, and specificity are 95.23%, 98.53%, and 91.12%. In addition, we also demonstrate the feasibility of non-contact AFL detection. Conclusion: We achieve good performance of non-contact AF detection by learning systolic peaks. Significance: non-contact AF detection can be used for self-screening of AF symptoms for suspectable populations at home or self-monitoring of AF recurrence after treatment for chronic patients.
While machine learning techniques are being applied to various fields for their exceptional ability to find complex relations in large datasets, the strengthening of regulations on data ownership and privacy is causing increasing difficulty in its application to medical data. In light of this, Federated Learning has recently been proposed as a solution to train on private data without breach of confidentiality. This conservation of privacy is particularly appealing in the field of healthcare, where patient data is highly confidential. However, many studies have shown that its assumption of Independent and Identically Distributed data is unrealistic for medical data. In this paper, we propose Personalized Federated Cluster Models, a hierarchical clustering-based FL process, to predict Major Depressive Disorder severity from Heart Rate Variability. By allowing clients to receive more personalized model, we address problems caused by non-IID data, showing an accuracy increase in severity prediction. This increase in performance may be sufficient to use Personalized Federated Cluster Models in many existing Federated Learning scenarios.
Since stress contributes to a broad range of mental and physical health problems, the objective assessment of stress is essential for behavioral and physiological studies. Although several studies have evaluated stress levels in controlled settings, objective stress assessment in everyday settings is still largely under-explored due to challenges arising from confounding contextual factors and limited adherence for self-reports. In this paper, we explore the objective prediction of stress levels in everyday settings based on heart rate (HR) and heart rate variability (HRV) captured via low-cost and easy-to-wear photoplethysmography (PPG) sensors that are widely available on newer smart wearable devices. We present a layered system architecture for personalized stress monitoring that supports a tunable collection of data samples for labeling, and present a method for selecting informative samples from the stream of real-time data for labeling. We captured the stress levels of fourteen volunteers through self-reported questionnaires over periods of between 1-3 months, and explored binary stress detection based on HR and HRV using Machine Learning Methods. We observe promising preliminary results given that the dataset is collected in the challenging environments of everyday settings. The binary stress detector is fairly accurate and can detect stressful vs non-stressful samples with a macro-F1 score of up to \%76. Our study lays the groundwork for more sophisticated labeling strategies that generate context-aware, personalized models that will empower health professionals to provide personalized interventions.
Inter-beat interval (IBI) measurement enables estimation of heart-rate variability (HRV) which, in turns, can provide early indication of potential cardiovascular diseases. However, extracting IBIs from noisy signals is challenging since the morphology of the signal is distorted in the presence of the noise. Electrocardiogram (ECG) of a person in heavy motion is highly corrupted with noise, known as motion-artifact, and IBI extracted from it is inaccurate. As a part of remote health monitoring and wearable system development, denoising ECG signals and estimating IBIs correctly from them have become an emerging topic among signal-processing researchers. Apart from conventional methods, deep-learning techniques have been successfully used in signal denoising recently, and diagnosis process has become easier, leading to accuracy levels that were previously unachievable. We propose a deep-learning approach leveraging tiramisu autoencoder model to suppress motion-artifact noise and make the R-peaks of the ECG signal prominent even in the presence of high-intensity motion. After denoising, IBIs are estimated more accurately expediting diagnosis tasks. Results illustrate that our method enables IBI estimation from noisy ECG signals with SNR up to -30dB with average root mean square error (RMSE) of 13 milliseconds for estimated IBIs. At this noise level, our error percentage remains below 8% and outperforms other state of the art techniques.
A photoplethysmography (PPG) is an uncomplicated and inexpensive optical technique widely used in the healthcare domain to extract valuable health-related information, e.g., heart rate variability, blood pressure, and respiration rate. PPG signals can easily be collected continuously and remotely using portable wearable devices. However, these measuring devices are vulnerable to motion artifacts caused by daily life activities. The most common ways to eliminate motion artifacts use extra accelerometer sensors, which suffer from two limitations: i) high power consumption and ii) the need to integrate an accelerometer sensor in a wearable device (which is not required in certain wearables). This paper proposes a low-power non-accelerometer-based PPG motion artifacts removal method outperforming the accuracy of the existing methods. We use Cycle Generative Adversarial Network to reconstruct clean PPG signals from noisy PPG signals. Our novel machine-learning-based technique achieves 9.5 times improvement in motion artifact removal compared to the state-of-the-art without using extra sensors such as an accelerometer.
In order to develop machine learning and deep learning models that take into account the guidelines and principles of trustworthy AI, a novel information theoretic trustworthy AI framework is introduced. A unified approach to "privacy-preserving interpretable and transferable learning" is considered for studying and optimizing the tradeoffs between privacy, interpretability, and transferability aspects. A variational membership-mapping Bayesian model is used for the analytical approximations of the defined information theoretic measures for privacy-leakage, interpretability, and transferability. The approach consists of approximating the information theoretic measures via maximizing a lower-bound using variational optimization. The study presents a unified information theoretic approach to study different aspects of trustworthy AI in a rigorous analytical manner. The approach is demonstrated through numerous experiments on benchmark datasets and a real-world biomedical application concerned with the detection of mental stress on individuals using heart rate variability analysis.
The autonomic nervous system (ANS) regulatory capacity begins before birth as the sympathetic and parasympathetic activity contributes significantly to the fetus' development. Several studies have shown how vagus nerve is involved in many vital processes during fetal, perinatal and postnatal life: from the regulation of inflammation through the anti-inflammatory cholinergic pathway, which may affect the functioning of each organ, to the production of hormones involved in bioenergetic metabolism. In addition, the vagus nerve has been recognized as the primary afferent pathway capable of transmitting information to the brain from every organ of the body. Therefore, this hypothesis paper aims to review the development of ANS during fetal and perinatal life, focusing particularly on the vagus nerve, to identify possible "critical windows" that could impact its maturation. These "critical windows" could help clinicians know when to monitor fetuses to effectively assess the developmental status of both ANS and specifically the vagus nerve. In addition, this paper will focus on which factors (i.e. fetal characteristics and behaviors, maternal lifestyle and pathologies, placental health and dysfunction, labor, incubator conditions, and drug exposure) may have an impact on the development of the vagus during the above-mentioned "critical window" and how. This analysis could help clinicians and stakeholders define precise guidelines for improving the management of fetuses and newborns, particularly to reduce the potential adverse environmental impacts on ANS development that may lead to persistent long-term consequences. Since the development of ANS and the vagus influence have been shown to be reflected in cardiac variability, this paper will rely in particular on studies using fetal heart rate variability (fHRV) to monitor the continued growth and health of both animal and human fetuses.
We show that a mobile phone can serve as an accurate monitor for several physiological variables, based on its ability to record and analyze the varying color signals of a fingertip placed in contact with its optical sensor. We confirm the accuracy of measurements of breathing rate, cardiac R-R intervals, and blood oxygen saturation, by comparisons to standard methods for making such measurements (respiration belts, ECGs, and pulse-oximeters, respectively). Measurement of respiratory rate uses a previously reported algorithm developed for use with a pulse-oximeter, based on amplitude and frequency modulation sequences within the light signal. We note that this technology can also be used with recently developed algorithms for detection of atrial fibrillation or blood loss. Index Terms: non-invasive monitoring, telemonitoring, heart rate variability (HRV), breathing rate, oxygen saturation
Heart rate variability (HRV) has been studied for over 50 years, yet an integrative concept is missing on what HRV's mathematical properties represent physiologically. Here I introduce the notion of HRV code as an attempt to address this challenge systematically. I review the existing evidence from physiological studies in various species to support this concept and propose experiments to help validate and expand this notion further.