Using CNN Saliency Maps and EEG Modulation Spectra for Improved and More Interpretable Machine Learning-Based Alzheimer's Disease Diagnosis.

Biomarkers based on resting-state electroencephalography (EEG) signals have emerged as a promising tool in the study of Alzheimer's disease (AD). Recently, a state-of-the-art biomarker was found based on visual inspection of power modulation spectrograms where three "patches" or regions from the modulation spectrogram were proposed and used for AD diagnostics. Here, we propose the use of deep neural networks, in particular convolutional neural networks (CNNs) combined with saliency maps, trained on power modulation spectrogram inputs to find optimal patches in a data-driven manner. Experiments are conducted on EEG data collected from fifty-four participants, including 20 healthy controls, 19 patients with mild AD, and 15 moderate-to-severe AD patients. Five classification tasks are explored, including the three-class problem, early-stage detection (control vs. mild-AD), and severity level detection (mild vs. moderate-to-severe). Experimental results show the proposed biomarkers outperform the state-of-the-art benchmark across all five tasks, as well as finding complementary modulation spectrogram regions not previously seen via visual inspection. Lastly, experiments are conducted on the proposed biomarkers to test their sensitivity to age, as this is a known confound in AD characterization. Across all five tasks, none of the proposed biomarkers showed a significant relationship with age, thus further highlighting their usefulness for automated AD diagnostics.

Multimodal resting-state connectivity predicts affective neurofeedback performance.

Neurofeedback has been suggested as a potential complementary therapy to different psychiatric disorders. Of interest for this approach is the prediction of individual performance and outcomes. In this study, we applied functional connectivity-based modeling using electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) modalities to (i) investigate whether resting-state connectivity predicts performance during an affective neurofeedback task and (ii) evaluate the extent to which predictive connectivity profiles are correlated across EEG and fNIRS techniques. The fNIRS oxyhemoglobin and deoxyhemoglobin concentrations and the EEG beta and gamma bands modulated by the alpha frequency band (beta-m-alpha and gamma-m-alpha, respectively) recorded over the frontal cortex of healthy subjects were used to estimate functional connectivity from each neuroimaging modality. For each connectivity matrix, relevant edges were selected in a leave-one-subject-out procedure, summed into "connectivity summary scores" (CSS), and submitted as inputs to a support vector regressor (SVR). Then, the performance of the left-out-subject was predicted using the trained SVR model. Linear relationships between the CSS across both modalities were evaluated using Pearson's correlation. The predictive model showed a mean absolute error smaller than 20%, and the fNIRS oxyhemoglobin CSS was significantly correlated with the EEG gamma-m-alpha CSS (r = -0.456, p = 0.030). These results support that pre-task electrophysiological and hemodynamic resting-state connectivity are potential predictors of neurofeedback performance and are meaningfully coupled. This investigation motivates the use of joint EEG-fNIRS connectivity as outcome predictors, as well as a tool for functional connectivity coupling investigation.

Modulation Spectral Signal Representation for Quality Measurement and Enhancement of Wearable Device Data: A Technical Note.

Wearable devices are burgeoning, and applications across numerous verticals are emerging, including human performance monitoring, at-home patient monitoring, and health tracking, to name a few. Off-the-shelf wearables have been developed with focus on portability, usability, and low-cost. As such, when deployed in highly ecological settings, wearable data can be corrupted by artifacts and by missing data, thus severely hampering performance. In this technical note, we overview a signal processing representation called the modulation spectrum. The representation quantifies the rate-of-change of different spectral magnitude components and is shown to separate signal from noise, thus allowing for improved quality measurement, quality enhancement, and noise-robust feature extraction, as well as for disease characterization. We provide an overview of numerous applications developed by the authors over the last decade spanning different wearable modalities and list the results obtained from experimental results alongside comparisons with various state-of-the-art benchmark methods. Open-source software is showcased with the hope that new applications can be developed. We conclude with a discussion on possible future research directions, such as context awareness, signal compression, and improved input representations for deep learning algorithms.

Predicting Driver Stress Levels with a Sensor-Equipped Steering Wheel and a Quality-Aware Heart Rate Measurement Algorithm.

Unobtrusive monitoring of driver mental states has been regarded as an important element in improving the safety of existing transportation systems. While many solutions exist relying on camera-based systems for e.g., drowsiness detection, these can be sensitive to varying lighting conditions and to driver facial accessories, such as eye/sunglasses. In this work, we evaluate the use of physiological signals derived from sensors embedded directly into the steering wheel. In particular, we are interested in monitoring driver stress levels. To achieve this goal, we first propose a modulation spectral signal representation to reliably extract electrocardiogram (ECG) signals from the steering wheel sensors, thus allowing for heart rate and heart rate variability features to be computed. When input to a simple logistic regression classifier, we show that up to 72% accuracy can be achieved when discriminating between stressful and non-stressful driving conditions. In particular, the proposed modulation spectral signal representation allows for direct quality assessment of the obtained heart rate information, thus can provide additional intelligence to autonomous driver monitoring systems.

Multimodal Prediction of Alzheimer's Disease Severity Level Based on Resting-State EEG and Structural MRI.

While several biomarkers have been developed for the detection of Alzheimer's disease (AD), not many are available for the prediction of disease severity, particularly for patients in the mild stages of AD. In this paper, we explore the multimodal prediction of Mini-Mental State Examination (MMSE) scores using resting-state electroencephalography (EEG) and structural magnetic resonance imaging (MRI) scans. Analyses were carried out on a dataset comprised of EEG and MRI data collected from 89 patients diagnosed with minimal-mild AD. Three feature selection algorithms were assessed alongside four machine learning algorithms. Results showed that while MRI features alone outperformed EEG features, when both modalities were combined, improved results were achieved. The top-selected EEG features conveyed information about amplitude modulation rate-of-change, whereas top-MRI features comprised information about cortical area and white matter volume. Overall, a root mean square error between predicted MMSE values and true MMSE scores of 1.682 was achieved with a multimodal system and a random forest regression model.

Neurofeedback and the Aging Brain: A Systematic Review of Training Protocols for Dementia and Mild Cognitive Impairment.

Dementia describes a set of symptoms that occur in neurodegenerative disorders and that is characterized by gradual loss of cognitive and behavioral functions. Recently, non-invasive neurofeedback training has been explored as a potential complementary treatment for patients suffering from dementia or mild cognitive impairment. Here we systematically reviewed studies that explored neurofeedback training protocols based on electroencephalography or functional magnetic resonance imaging for these groups of patients. From a total of 1,912 screened studies, 10 were included in our final sample (N = 208 independent participants in experimental and N = 81 in the control groups completing the primary endpoint). We compared the clinical efficacy across studies, and evaluated their experimental designs and reporting quality. In most studies, patients showed improved scores in different cognitive tests. However, data from randomized controlled trials remains scarce, and clinical evidence based on standardized metrics is still inconclusive. In light of recent meta-research developments in the neurofeedback field and beyond, quality and reporting practices of individual studies are reviewed. We conclude with recommendations on best practices for future studies that investigate the effects of neurofeedback training in dementia and cognitive impairment.

Adaptive Filtering for Improved EEG-Based Mental Workload Assessment of Ambulant Users.

Recently, due to the emergence of mobile electroencephalography (EEG) devices, assessment of mental workload in highly ecological settings has gained popularity. In such settings, however, motion and other common artifacts have been shown to severely hamper signal quality and to degrade mental workload assessment performance. Here, we show that classical EEG enhancement algorithms, conventionally developed to remove ocular and muscle artifacts, are not optimal in settings where participant movement (e.g., walking or running) is expected. As such, an adaptive filter is proposed that relies on an accelerometer-based referential signal. We show that when combined with classical algorithms, accurate mental workload assessment is achieved. To test the proposed algorithm, data from 48 participants was collected as they performed the Revised Multi-Attribute Task Battery-II (MATB-II) under a low and a high workload setting, either while walking/jogging on a treadmill, or using a stationary exercise bicycle. Accuracy as high as 95% could be achieved with a random forest based mental workload classifier with ambulant users. Moreover, an increase in gamma activity was found in the parietal cortex, suggesting a connection between sensorimotor integration, attention, and workload in ambulant users.

WAUC: A Multi-Modal Database for Mental Workload Assessment Under Physical Activity.

Assessment of mental workload is crucial for applications that require sustained attention and where conditions such as mental fatigue and drowsiness must be avoided. Previous work that attempted to devise objective methods to model mental workload were mainly based on neurological or physiological data collected when the participants performed tasks that did not involve physical activity. While such models may be useful for scenarios that involve static operators, they may not apply in real-world situations where operators are performing tasks under varying levels of physical activity, such as those faced by first responders, firefighters, and police officers. Here, we describe WAUC, a multimodal database of mental Workload Assessment Under physical aCtivity. The study involved 48 participants who performed the NASA Revised Multi-Attribute Task Battery II under three different activity level conditions. Physical activity was manipulated by changing the speed of a stationary bike or a treadmill. During data collection, six neural and physiological modalities were recorded, namely: electroencephalography, electrocardiography, breathing rate, skin temperature, galvanic skin response, and blood volume pulse, in addition to 3-axis accelerometry. Moreover, participants were asked to answer the NASA Task Load Index questionnaire after each experimental section, as well as rate their physical fatigue level on the Borg fatigue scale. In order to bring our experimental setup closer to real-world situations, all signals were monitored using wearable, off-the-shelf devices. In this paper, we describe the adopted experimental protocol, as well as validate the subjective, neural, and physiological data collected. The WAUC database, including the raw data and features, subjective ratings, and scripts to reproduce the experiments reported herein will be made available at: http://musaelab.ca/resources/.

PASS: A Multimodal Database of Physical Activity and Stress for Mobile Passive Body/ Brain-Computer Interface Research.

With the burgeoning of wearable devices and passive body/brain-computer interfaces (B/BCIs), automated stress monitoring in everyday settings has gained significant attention recently, with applications ranging from serious games to clinical monitoring. With mobile users, however, challenges arise due to other overlapping (and potentially confounding) physiological responses (e.g., due to physical activity) that may mask the effects of stress, as well as movement artifacts that can be introduced in the measured signals. For example, the classical increase in heart rate can no longer be attributed solely to stress and could be caused by the activity itself. This makes the development of mobile passive B/BCIs challenging. In this paper, we introduce PASS, a multimodal database of Physical Activity and StresS collected from 48 participants. Participants performed tasks of varying stress levels at three different activity levels and provided quantitative ratings of their perceived stress and fatigue levels. To manipulate stress, two video games (i.e., a calm exploration game and a survival game) were used. Peripheral physical activity (electrocardiography, electrodermal activity, breathing, skin temperature) as well as cerebral activity (electroencephalography) were measured throughout the experiment. A complete description of the experimental protocol is provided and preliminary analyses are performed to investigate the physiological reactions to stress in the presence of physical activity. The PASS database, including raw data and subjective ratings has been made available to the research community at http://musaelab.ca/pass-database/. It is hoped that this database will help advance mobile passive B/BCIs for use in everyday settings.

Virtual reality and non-invasive brain stimulation for rehabilitation applications: a systematic review.

The present article reports the results of a systematic review on the potential benefits of the combined use of virtual reality (VR) and non-invasive brain stimulation (NIBS) as a novel approach for rehabilitation. VR and NIBS are two rehabilitation techniques that have been consistently explored by health professionals, and in recent years there is strong evidence of the therapeutic benefits of their combined use. In this work, we reviewed research articles that report the combined use of VR and two common NIBS techniques, namely transcranial direct current stimulation (tDCS) and transcranial magnetic stimulation (TMS). Relevant queries to six major bibliographic databases were performed to retrieve original research articles that reported the use of the combination VR-NIBS for rehabilitation applications. A total of 16 articles were identified and reviewed. The reviewed studies have significant differences in the goals, materials, methods, and outcomes. These differences are likely caused by the lack of guidelines and best practices on how to combine VR and NIBS techniques. Five therapeutic applications were identified: stroke, neuropathic pain, cerebral palsy, phobia and post-traumatic stress disorder, and multiple sclerosis rehabilitation. The majority of the reviewed studies reported positive effects of the use of VR-NIBS. However, further research is still needed to validate existing results on larger sample sizes and across different clinical conditions. For these reasons, in this review recommendations for future studies exploring the combined use of VR and NIBS are presented to facilitate the comparison among works.

Optimal filter characterization for photoplethysmography-based pulse rate and pulse power spectrum estimation.

Photoplethysmography (PPG) is a non-invasive, low-cost optical technique used to assess the cardiovascular system. In recent years, PPG-based heart rate measurement has gained significant attention due to its popularity in wearable devices, as well as its practicality relative to electrocardiography (ECG). Studies comparing the dynamics of ECG- and PPG-based heart rate measures have found small differences between these two modalities; differences related to the physiological processes behind each technique. In this work, we analyzed the spectral coherence and the signal-to-noise ratio between isolated PPG pulses and the raw PPG signal in order to: (i) determine the optimal filter to enhance pulse detection from raw PPG for improved heart rate estimation, and (ii) characterize the spectral content of the PPG pulse. The proposed methods were evaluated on 27000 pulses from a PPG database acquired from 42 participants (adults and children). The results showed that the optimal bandpass filter to enhance PPG from the adult group was 0.6-3.3 Hz, while for the children group it was 1.0-2.7 Hz. The spectral analysis on the pulse signal showed that similar bandwidths were found for the adult (0.8-2.4 Hz) and children (0.9-2.7 Hz) groups. We hope that the results presented herein serve as a baseline for pulse detection algorithms and assist with the development of more sophisticated PPG processing algorithms.

EEG spectro-temporal amplitude modulation as a measurement of cortical hemodynamics: an EEG-fNIRS study.

Neurovascular coupling provides valuable descriptive information about neural function and communication. In this work, we propose to objectively characterize EEG sub-band modulation in an attempt to compare with local variations of fNIRS hemoglobin concentration. First, full-band EEG signals are decomposed into five well-known frequency sub-bands: delta, theta, alpha, beta, and gamma. The temporal amplitude envelope of each sub-band is then computed via Hilbert transformation. The proposed EEG 'spectro-temporal amplitude modulation' (EEG-AM) feature measures the rate at which each sub-band is modulated. Similarities between EEG-AM features and fNIRS hemoglobin concentration are computed for four neighboring channels over the occipital area during resting-state. Experiments with a database of 29 participants show statistically significant similarities between the total hemoglobin concentration and the alpha band modulating the alpha, beta, and gamma frequencies. These results support the idea that the EEG-AM can carry hemodynamic properties.Clinical relevance- This shows that the EEG spectro-temporal amplitude modulation present similarities with the hemoglobin concentration in co-placed channels.

Prediction of Stress and Mental Workload during Police Academy Training Using Ultra-Short-Term Heart Rate Variability and Breathing Analysis.

Heart rate variability (HRV) has been studied in the context of human behavior analysis and many features have been extracted from the inter-beat interval (RR) time series and tested as correlates of constructs such as mental workload, stress and anxiety. Such constructs are crucial in assessing quality-of-life of individuals, as well as their overall performance when doing critical tasks. Most studies, however, have been conducted in controlled laboratory environments with artificially-induced psychological responses. While this assures that high quality data are collected, the amount of data is limited and the transferability of the findings to more ecologically-appropriate settings remains unknown. Additionally, it is desirable for such mental state monitoring systems to have high temporal resolution, thus allowing for quick feedback and adaptive decision making. In this article, we explore the use of features computed from time windows much shorter than typically reported in the literature. More specifically, we evaluate the potential of HRV and breathing features computed over so-called ultra-short-term segments (i.e., < 5 minutes) for stress and mental workload prediction. Experiments with 27 police academy trainees show that short time windows as low as 60 seconds can provide useful insights, in particular for mental workload assessment. Moreover, the fusion of HRV and breathing features showed to be an important aspect for reliable behavioural assessment in highly ecological settings.

Alzheimer's Disease Diagnosis and Severity Level Detection Based on Electroencephalography Modulation Spectral "Patch" Features.

Over the last two decades, electroencephalography (EEG) has emerged as a reliable tool for the diagnosis of cortical disorders such as Alzheimer's disease (AD). Typically, resting-state EEG (rsEEG) signals have been used, and traditional frequency bands (delta, theta, alpha, beta and gamma) have been explored. Recent studies, however, have suggested that non-conventional bands may lead to improved diagnostic performance. In this work, we propose a new type of features derived from the 2-dimensional modulation spectral domain representation of the rsEEG signal in order to characterize the neuromodulatory deficit emergent with AD. The proposed features are computed as the power in specific "patches" or regions of interest in the power modulation spectrogram, which are shown to be highly discriminant of AD severity levels. The proposed features were compared with traditional features used in the rsEEG AD monitoring literature. Results showed the proposed features not only achieving improved performance at discriminating between healthy normal elderly controls (Nold) and AD patients with varying severity levels, but also at monitoring severity levels (i.e., mild AD versus moderate AD). Moreover, the proposed features were shown to outperform traditional rsEEG features. Finally, we validated the biological origin of the proposed features by using source localization and comparing the obtained results with ones reported in the AD literature.

A Comparative Study of Stress and Anxiety Estimation in Ecological Settings Using a Smart-shirt and a Smart-bracelet.

In recent years, consumer wearable devices focused on health assessment have gained popularity. Of these devices, a large number target monitoring heart rate; a few among them include additional biometrics such as breathing rate, galvanic skin response, and skin temperature. Heart rate, and more specifically, heart rate variability (HRV) measures have proven useful in monitoring user psychological states, such as mental workload, stress and anxiety. Most studies, however, have been conducted in controlled laboratory environments with artificially-induced psychological responses. While these conditions assure high quality in the collected data, the amount of data are limited and the generalization of the findings to more ecologically-appropriate settings remains unknown. To this end, in this paper we compare the accuracy of two wearable devices, namely a smart-shirt measuring electrocardiograms and a smart-bracelet measuring photoplethysmograms. Several HRV features are extracted and tested as correlates of stress and anxiety. Data were collected from 196 participants during their normal work shifts for a period of 10 weeks. The complementarity of the two devices is also explored and the advantages of each method are discussed.

Systematic Review on Resting-State EEG for Alzheimer's Disease Diagnosis and Progression Assessment.

Alzheimer's disease (AD) is a neurodegenerative disorder that accounts for nearly 70% of the more than 46 million dementia cases estimated worldwide. Although there is no cure for AD, early diagnosis and an accurate characterization of the disease progression can improve the quality of life of AD patients and their caregivers. Currently, AD diagnosis is carried out using standardized mental status examinations, which are commonly assisted by expensive neuroimaging scans and invasive laboratory tests, thus rendering the diagnosis time consuming and costly. Notwithstanding, over the last decade, electroencephalography (EEG) has emerged as a noninvasive alternative technique for the study of AD, competing with more expensive neuroimaging tools, such as MRI and PET. This paper reports on the results of a systematic review on the utilization of resting-state EEG signals for AD diagnosis and progression assessment. Recent journal articles obtained from four major bibliographic databases were analyzed. A total of 112 journal articles published from January 2010 to February 2018 were meticulously reviewed, and relevant aspects of these papers were compared across articles to provide a general overview of the research on this noninvasive AD diagnosis technique. Finally, recommendations for future studies with resting-state EEG were presented to improve and facilitate the knowledge transfer among research groups.

Vitamin D receptor regulates autophagy in the normal mammary gland and in luminal breast cancer cells.

Women in North America have a one in eight lifetime risk of developing breast cancer (BC), and a significant proportion of these individuals will develop recurrent BC and will eventually succumb to the disease. Metastatic, therapy-resistant BC cells are refractory to cell death induced by multiple stresses. Here, we document that the vitamin D receptor (VDR) acts as a master transcriptional regulator of autophagy. Activation of the VDR by vitamin D induces autophagy and an autophagic transcriptional signature in BC cells that correlates with increased survival in patients; strikingly, this signature is present in the normal mammary gland and is progressively lost in patients with metastatic BC. A number of epidemiological studies have shown that sufficient vitamin D serum levels might be protective against BC. We observed that dietary vitamin D supplementation in mice increases basal levels of autophagy in the normal mammary gland, highlighting the potential of vitamin D as a cancer-preventive agent. These findings point to a role of vitamin D and the VDR in modulating autophagy and cell death in both the normal mammary gland and BC cells.

The effects of automated artifact removal algorithms on electroencephalography-based Alzheimer's disease diagnosis.

Over the last decade, electroencephalography (EEG) has emerged as a reliable tool for the diagnosis of cortical disorders such as Alzheimer's disease (AD). EEG signals, however, are susceptible to several artifacts, such as ocular, muscular, movement, and environmental. To overcome this limitation, existing diagnostic systems commonly depend on experienced clinicians to manually select artifact-free epochs from the collected multi-channel EEG data. Manual selection, however, is a tedious and time-consuming process, rendering the diagnostic system "semi-automated." Notwithstanding, a number of EEG artifact removal algorithms have been proposed in the literature. The (dis)advantages of using such algorithms in automated AD diagnostic systems, however, have not been documented; this paper aims to fill this gap. Here, we investigate the effects of three state-of-the-art automated artifact removal (AAR) algorithms (both alone and in combination with each other) on AD diagnostic systems based on four different classes of EEG features, namely, spectral, amplitude modulation rate of change, coherence, and phase. The three AAR algorithms tested are statistical artifact rejection (SAR), blind source separation based on second order blind identification and canonical correlation analysis (BSS-SOBI-CCA), and wavelet enhanced independent component analysis (wICA). Experimental results based on 20-channel resting-awake EEG data collected from 59 participants (20 patients with mild AD, 15 with moderate-to-severe AD, and 24 age-matched healthy controls) showed the wICA algorithm alone outperforming other enhancement algorithm combinations across three tasks: diagnosis (control vs. mild vs. moderate), early detection (control vs. mild), and disease progression (mild vs. moderate), thus opening the doors for fully-automated systems that can assist clinicians with early detection of AD, as well as disease severity progression assessment.