Predicting Age From Brain EEG Signals-A Machine Learning Approach

From genetics to systems biology of stress-related mental disorders

Many individuals will be exposed to some form of traumatic stress in their lifetime which, in turn, increases the likelihood of developing stress-related disorders such as post-traumatic stress disorder (PTSD), major depressive disorder (MDD) and anxiety disorders (ANX). The development of these disorders is also influenced by genetics and have heritability estimates ranging between ∼30 and 70%. In this review, we provide an overview of the findings of genome-wide association studies for PTSD, depression and ANX, and we observe a clear genetic overlap between these three diagnostic categories. We go on to highlight the results from transcriptomic and epigenomic studies, and, given the multifactorial nature of stress-related disorders, we provide an overview of the gene-environment studies that have been conducted to date. Finally, we discuss systems biology approaches that are now seeing wider utility in determining a more holistic view of these complex disorders.

Deep learning analysis and age prediction from shoeprints

Human gaits are the patterns of limb movements which involve both the upper and lower body parts. These patterns in terms of step rate, gait speed, stance widening, stride, and bipedal forces are influenced by different factors including environmental (such as social, cultural, and behavioral traits) and physical changes (such as age and health status). These factors are reflected on the imprinted shoeprints generated with body forces, which in turn can be used to predict age, a problem not systematically addressed using any computational approach. We collected 100,000 shoeprints of subjects ranging from 7 to 80 years old and used the data to develop a deep learning end-to-end model ShoeNet to analyze age-related patterns and predict age. The model integrates various convolutional neural network models together using a skip mechanism to extract age-related features, especially in pressure and abrasion regions from pair-wise shoeprints. The results show that 40.23% of the subjects had prediction errors within 5-years of age and the prediction accuracy for gender/sex classification reached 86.07%. Interestingly, the age-related features mostly reside in the asymmetric differences between left and right shoeprints. The analysis also reveals interesting age-related and gender-related patterns in the pressure distributions on shoeprints; in particular, the pressure forces spread from the middle of the toe toward outside regions over age with gender-specific variations of forces on heel regions. Such statistics provide insight into new methods for forensic investigations, medical studies of gait pattern disorders, biometrics, and sport studies.

Prediction of dispositional dialectical thinking from resting-state electroencephalography

This study aims to explore the possibility of predicting the dispositional level of dialectical thinking using resting-state electroencephalography signals. Thirty-four participants completed a self-reported measure of dialectical thinking, and their resting-state electroencephalography was recorded. After wave filtration and eye movement removal, time-frequency electroencephalography signals were converted into four frequency domains: delta (1-4 Hz), theta (4-7 Hz), alpha (7-13 Hz), and beta (13-30 Hz). Functional principal component analysis with B-spline approximation was then applied for feature reduction. Five machine learning methods (support vector regression, least absolute shrinkage and selection operator, K-nearest neighbors, random forest, and gradient boosting decision tree) were applied to the reduced features for prediction. The model ensemble technique was used to create the best performing final model. The results showed that the alpha wave of the electroencephalography signal in the early period (12-15 s) contributed most to the prediction of dialectical thinking. With data-driven electrode selection (FC1, FCz, Fz, FC3, Cz, AFz), the prediction model achieved an average coefficient of determination of 0.45 on 200 random test sets. Furthermore, a significant positive correlation was found between the alpha value of standardized low-resolution electromagnetic tomography activity in the right dorsal anterior cingulate cortex and dialectical self-scale score. The prefrontal and midline alpha oscillations of resting electroencephalography are good predictors of the dispositional level of dialectical thinking, possibly reflecting these brain structures' involvement in dialectical thinking.

Common Data Elements, Scalable Data Management Infrastructure, and Analytics Workflows for Large-Scale Neuroimaging Studies

Neuroscience studies require considerable bioinformatic support and expertise. Numerous high-dimensional and multimodal datasets must be preprocessed and integrated to create robust and reproducible analysis pipelines. We describe a common data elements and scalable data management infrastructure that allows multiple analytics workflows to facilitate preprocessing, analysis and sharing of large-scale multi-level data. The process uses the Brain Imaging Data Structure (BIDS) format and supports MRI, fMRI, EEG, clinical, and laboratory data. The infrastructure provides support for other datasets such as Fitbit and flexibility for developers to customize the integration of new types of data. Exemplar results from 200+ participants and 11 different pipelines demonstrate the utility of the infrastructure.

Long-term stability of computational parameters during approach-avoidance conflict in a transdiagnostic psychiatric patient sample

Maladaptive behavior during approach-avoidance conflict (AAC) is common to multiple psychiatric disorders. Using computational modeling, we previously reported that individuals with depression, anxiety, and substance use disorders (DEP/ANX; SUDs) exhibited differences in decision uncertainty and sensitivity to negative outcomes versus reward (emotional conflict) relative to healthy controls (HCs). However, it remains unknown whether these computational parameters and group differences are stable over time. We analyzed 1-year follow-up data from a subset of the same participants (N = 325) to assess parameter stability and relationships to other clinical and task measures. We assessed group differences in the entire sample as well as a subset matched for age and IQ across HCs (N = 48), SUDs (N = 29), and DEP/ANX (N = 121). We also assessed 2-3 week reliability in a separate sample of 30 HCs. Emotional conflict and decision uncertainty parameters showed moderate 1-year intra-class correlations (.52 and .46, respectively) and moderate to excellent correlations over the shorter period (.84 and .54, respectively). Similar to previous baseline findings, parameters correlated with multiple response time measures (ps < .001) and self-reported anxiety (r = .30, p < .001) and decision difficulty (r = .44, p < .001). Linear mixed effects analyses revealed that patients remained higher in decision uncertainty (SUDs, p = .009) and lower in emotional conflict (SUDs, p = .004, DEP/ANX, p = .02) relative to HCs. This computational modelling approach may therefore offer relatively stable markers of transdiagnostic psychopathology.

Cognitive Effects of Montelukast: A Pharmaco-EEG Study

Montelukast is a well-established antiasthmatic drug with little side effects. It is a leukotriene receptor antagonist and recent research suggests cognitive benefits from its anti-inflammatory actions on the central nervous system. However, changes in brain activity were not directly shown so far in humans. This study aims to document changes in brain activity that are associated with cognitive improvement during treatment with Montelukast. We recorded EEG and conducted neuropsychological tests in 12 asthma-patients aged 38-73 years before and after 8 weeks of treatment with Montelukast. We found no significant changes on neuropsychological scales for memory, attention, and mood. In the EEG, we found decreased entropy at follow up during rest (p < 0.005). During episodic memory acquisition we found decreased entropy (p < 0.01) and acceleration of the background rhythm (p < 0.05). During visual attention performance, we detected an increase in gamma power (p < 0.005) and slowing of the background rhythm (p < 0.05). The study is limited by its small sample size, young age and absence of baseline cognitive impairment of the participants. Unspecific changes in brain activity were not accompanied by cognitive improvement. Future studies should examine elderly patients with cognitive impairment in a double-blind study with longer-term treatment by Montelukast.

The aging brain: sleep, the circadian clock and exercise

Aging is a multifactorial process likely stemming from damage accumulation and/or a decline in maintenance and repair mechanisms in the organisms that eventually determine their lifespan. In our review, we focus on the morphological and functional alterations that the aging brain undergoes affecting sleep and the circadian clock in both human and rodent models. Although both species share mammalian features, differences have been identified on several experimental levels, which we outline in this review. Additionally, we delineate some challenges on the preferred analysis and we suggest that a uniform route is followed so that findings can be smoothly compared. We conclude by discussing potential interventions and highlight the influence of physical exercise as a beneficial lifestyle intervention, and its effect on healthy aging and longevity. We emphasize that even moderate age-matched exercise is able to ameliorate several aging characteristics as far as sleep and circadian rhythms are concerned, independent of the species studied.

Extracting Robust Biomarkers From Multichannel EEG Time Series Using Nonlinear Dimensionality Reduction Applied to Ordinal Pattern Statistics and Spectral Quantities

In this study, ordinal pattern analysis and classical frequency-based EEG analysis methods are used to differentiate between EEGs of different age groups as well as individuals. As characteristic features, functional connectivity as well as single-channel measures in both the time and frequency domain are considered. We compare the separation power of each feature set after nonlinear dimensionality reduction using t-distributed stochastic neighbor embedding and demonstrate that ordinal pattern-based measures yield results comparable to frequency-based measures applied to preprocessed data, and outperform them if applied to raw data. Our analysis yields no significant differences in performance between single-channel features and functional connectivity features regarding the question of age group separation.

Estimating brain age from structural MRI and MEG data: Insights from dimensionality reduction techniques

Brain age prediction studies aim at reliably estimating the difference between the chronological age of an individual and their predicted age based on neuroimaging data, which has been proposed as an informative measure of disease and cognitive decline. As most previous studies relied exclusively on magnetic resonance imaging (MRI) data, we hereby investigate whether combining structural MRI with functional magnetoencephalography (MEG) information improves age prediction using a large cohort of healthy subjects (N = 613, age 18-88 years) from the Cam-CAN repository. To this end, we examined the performance of dimensionality reduction and multivariate associative techniques, namely Principal Component Analysis (PCA) and Canonical Correlation Analysis (CCA), to tackle the high dimensionality of neuroimaging data. Using MEG features (mean absolute error (MAE) of 9.60 years) yielded worse performance when compared to using MRI features (MAE of 5.33 years), but a stacking model combining both feature sets improved age prediction performance (MAE of 4.88 years). Furthermore, we found that PCA resulted in inferior performance, whereas CCA in conjunction with Gaussian process regression models yielded the best prediction performance. Notably, CCA allowed us to visualize the features that significantly contributed to brain age prediction. We found that MRI features from subcortical structures were more reliable age predictors than cortical features, and that spectral MEG measures were more reliable than connectivity metrics. Our results provide an insight into the underlying processes that are reflective of brain aging, yielding promise for the identification of reliable biomarkers of neurodegenerative diseases that emerge later during the lifespan.

A Review on Machine Learning for EEG Signal Processing in Bioengineering

Electroencephalography (EEG) has been a staple method for identifying certain health conditions in patients since its discovery. Due to the many different types of classifiers available to use, the analysis methods are also equally numerous. In this review, we will be examining specifically machine learning methods that have been developed for EEG analysis with bioengineering applications. We reviewed literature from 1988 to 2018 to capture previous and current classification methods for EEG in multiple applications. From this information, we are able to determine the overall effectiveness of each machine learning method as well as the key characteristics. We have found that all the primary methods used in machine learning have been applied in some form in EEG classification. This ranges from Naive-Bayes to Decision Tree/Random Forest, to Support Vector Machine (SVM). Supervised learning methods are on average of higher accuracy than their unsupervised counterparts. This includes SVM and KNN. While each of the methods individually is limited in their accuracy in their respective applications, there is hope that the combination of methods when implemented properly has a higher overall classification accuracy. This paper provides a comprehensive overview of Machine Learning applications used in EEG analysis. It also gives an overview of each of the methods and general applications that each is best suited to.

Greater decision uncertainty characterizes a transdiagnostic patient sample during approach-avoidance conflict: a computational modelling approach

BACKGROUND

Imbalances in approach-avoidance conflict (AAC) decision-making (e.g., sacrificing rewards to avoid negative outcomes) are considered central to multiple psychiatric disorders. We used computational modelling to examine 2 factors that are often not distinguished in descriptive analyses of AAC: decision uncertainty and sensitivity to negative outcomes versus rewards (emotional conflict).

METHODS

A previously validated AAC task was completed by 478 participants, including healthy controls (n = 59), people with substance use disorders (n = 159) and people with depression and/or anxiety disorders who did not have substance use disorders (n = 260). Using an active inference model, we estimated individual-level values for a model parameter that reflected decision uncertainty and another that reflected emotional conflict. We also repeated analyses in a subsample (59 healthy controls, 161 people with depression and/or anxiety disorders, 56 people with substance use disorders) that was propensity-matched for age and general intelligence.

RESULTS

The model showed high accuracy (72%). As further validation, parameters correlated with reaction times and self-reported task motivations in expected directions. The emotional conflict parameter further correlated with self-reported anxiety during the task (r = 0.32, p < 0.001), and the decision uncertainty parameter correlated with self-reported difficulty making decisions (r = 0.45, p < 0.001). Compared to healthy controls, people with depression and/or anxiety disorders and people with substance use disorders showed higher decision uncertainty in the propensity-matched sample (t = 2.16, p = 0.03, and t = 2.88, p = 0.005, respectively), with analogous results in the full sample; people with substance use disorders also showed lower emotional conflict in the full sample (t = 3.17, p = 0.002).

LIMITATIONS

This study was limited by heterogeneity of the clinical sample and an inability to examine learning.

CONCLUSION

These results suggest that reduced confidence in how to act, rather than increased emotional conflict, may explain maladaptive approach-avoidance behaviours in people with psychiatric disorders.

Greater decision uncertainty characterizes a transdiagnostic patient sample during approach-avoidance conflict: a computational modelling approach

BACKGROUND

Imbalances in approach-avoidance conflict (AAC) decision-making (e.g., sacrificing rewards to avoid negative outcomes) are considered central to multiple psychiatric disorders. We used computational modelling to examine 2 factors that are often not distinguished in descriptive analyses of AAC: decision uncertainty and sensitivity to negative outcomes versus rewards (emotional conflict).

METHODS

A previously validated AAC task was completed by 478 participants, including healthy controls (n = 59), people with substance use disorders (n = 159) and people with depression and/or anxiety disorders who did not have substance use disorders (n = 260). Using an active inference model, we estimated individual-level values for a model parameter that reflected decision uncertainty and another that reflected emotional conflict. We also repeated analyses in a subsample (59 healthy controls, 161 people with depression and/or anxiety disorders, 56 people with substance use disorders) that was propensity-matched for age and general intelligence.

RESULTS

The model showed high accuracy (72%). As further validation, parameters correlated with reaction times and self-reported task motivations in expected directions. The emotional conflict parameter further correlated with self-reported anxiety during the task (r = 0.32, p < 0.001), and the decision uncertainty parameter correlated with self-reported difficulty making decisions (r = 0.45, p < 0.001). Compared to healthy controls, people with depression and/or anxiety disorders and people with substance use disorders showed higher decision uncertainty in the propensity-matched sample (t = 2.16, p = 0.03, and t = 2.88, p = 0.005, respectively), with analogous results in the full sample; people with substance use disorders also showed lower emotional conflict in the full sample (t = 3.17, p = 0.002).

LIMITATIONS

This study was limited by heterogeneity of the clinical sample and an inability to examine learning.

CONCLUSION

These results suggest that reduced confidence in how to act, rather than increased emotional conflict, may explain maladaptive approach-avoidance behaviours in people with psychiatric disorders.

Night-to-night variability of sleep electroencephalography-based brain age measurements

OBJECTIVE

Brain Age Index (BAI), calculated from sleep electroencephalography (EEG), has been proposed as a biomarker of brain health. This study quantifies night-to-night variability of BAI and establishes probability thresholds for inferring underlying brain pathology based on a patient's BAI.

METHODS

86 patients with multiple nights of consecutive EEG recordings were selected from Epilepsy Monitoring Unit patients whose EEGs reported as within normal limits. While EEGs with epileptiform activity were excluded, the majority of patients included in the study had a diagnosis of chronic epilepsy. BAI was calculated for each 12-hour segment of patient data using a previously established algorithm, and the night-to-night variability in BAI was measured.

RESULTS

The within-patient night-to-night standard deviation in BAI was 7.5 years. Estimates of BAI derived by averaging over 2, 3, and 4 nights had standard deviations of 4.7, 3.7, and 3.0 years, respectively.

CONCLUSIONS

Averaging BAI over n nights reduces night-to-night variability of BAI by a factor of n, rendering BAI a more suitable biomarker of brain health at the individual level. A brain age risk lookup table of results provides thresholds above which a patient has a high probability of excess BAI.

SIGNIFICANCE

With increasing ease of EEG acquisition, including wearable technology, BAI has the potential to track brain health and detect deviations from normal physiologic function. The measure of night-to-night variability and how this is reduced by averaging across multiple nights provides a basis for using BAI in patients' homes to identify patients who should undergo further investigation or monitoring.

Applications of Convolutional Neural Networks in neurodegeneration and physiological aging

The process of aging is linked with significant changes in a human's physiological organization and structure. This is more evident in the case of the brain whose functions generally vary between young and old individuals. Detecting such patterns can be of significant importance especially during the Mild Cognitive Impairment (MCI) stage which is a transition state before the clinical onset of dementia. Intervening in that stage may delay or eventually prevent dementia onset. In this paper we propose a new methodology based in electroencephalographic (EEG) recordings, aiming to classify individuals into healthy, pathological (patients diagnosed with MCI or Mild Dementia) and young, old groups (healthy individuals over and under 50 years of age) through functional connectivity and macro-architecture features. These features are calculated on the estimated brain region activations through the inverse problem solution, enabling us to transform the sensor level EEG recordings through an appropriate transformation matrix. Afterwards, Synchronization Likelihood and Relative Wavelet Entropy values were calculated along with the graph metrics corresponding to the functional connectivity values, as well as the relative energy contributions of five EEG bands (delta, theta, alpha, beta and gamma). These features were organized in Red, Green, Blue (RGB) image-like data structures. Therefore, it was possible to classify each individual into one of the two groups per experiment employing Convolutional Neural Networks. From the maximum classification accuracy achieved on the test set, 90.48% for the pathological aging group and 91.19% for the physiological aging, it is evident that the proposed approach is capable of providing adequate health and age group classification.

Patch-wise brain age longitudinal reliability

We recently introduced a patch‐wise technique to estimate brain age from anatomical T1‐weighted magnetic resonance imaging (T1w MRI) data. Here, we sought to assess its longitudinal reliability by leveraging a unique dataset of 99 longitudinal MRI scans from a single, cognitively healthy volunteer acquired over a period of 17 years (aged 29–46 years) at multiple sites. We built a robust patch‐wise brain age estimation framework on the basis of 100 cognitively healthy individuals from the MindBoggle dataset (aged 19–61 years) using the Desikan‐Killiany‐Tourville atlas, then applied the model to the volunteer dataset. The results show a high prediction accuracy on the independent test set (R² = .94, mean absolute error of 0.63 years) and no statistically significant difference between manufacturers, suggesting that the patch‐wise technique has high reliability and can be used for longitudinal multi‐centric studies.

An Investigation of Insider Threat Mitigation Based on EEG Signal Classification

This study proposes a scheme to identify insider threats in nuclear facilities through the detection of malicious intentions of potential insiders using subject-wise classification. Based on electroencephalography (EEG) signals, a classification model was developed to identify whether a subject has a malicious intention under scenarios of being forced to become an insider threat. The model also distinguishes insider threat scenarios from everyday conflict scenarios. To support model development, 21-channel EEG signals were measured on 25 healthy subjects, and sets of features were extracted from the time, time–frequency, frequency and nonlinear domains. To select the best use of the available features, automatic selection was performed by random-forest-based algorithms. The k-nearest neighbor, support vector machine with radial kernel, naïve Bayes, and multilayer perceptron algorithms were applied for the classification. By using EEG signals obtained while contemplating becoming an insider threat, the subject-wise model identified malicious intentions with 78.57% accuracy. The model also distinguished insider threat scenarios from everyday conflict scenarios with 93.47% accuracy. These findings could be utilized to support the development of insider threat mitigation systems along with existing trustworthiness assessments in the nuclear industry.

Reward processing electrophysiology in schizophrenia: Effects of age and illness phase

BACKGROUND

Reward processing abnormalities may underlie characteristic pleasure and motivational impairments in schizophrenia. Some neural measures of reward processing show age-related modulation, highlighting the importance of considering age effects on reward sensitivity. We compared event-related potentials (ERPs) reflecting reward anticipation (stimulus-preceding negativity, SPN) and evaluation (reward positivity, RewP; late positive potential, LPP) across individuals with schizophrenia (SZ) and healthy controls (HC), with an emphasis on examining the effects of chronological age, brain age (i.e., predicted age based on neurobiological measures), and illness phase.

METHODS

Subjects underwent EEG while completing a slot-machine task for which rewards were not dependent on performance accuracy, speed, or response preparation. Slot-machine task EEG responses were compared between 54 SZ and 54 HC individuals, ages 19 to 65. Reward-related ERPs were analyzed with respect to chronological age, categorically-defined illness phase (early; ESZ versus chronic schizophrenia; CSZ), and were used to model brain age relative to chronological age.

RESULTS

Illness phase-focused analyses indicated there were no group differences in average SPN or RewP amplitudes. However, a group × reward outcome interaction revealed that ESZ differed from HC in later outcome processing, reflected by greater LPP responses following loss versus reward (a reversal of the HC pattern). While brain age estimates did not differ among groups, depressive symptoms in SZ were associated with older brain age estimates while controlling for negative symptoms.

CONCLUSIONS

ESZ and CSZ did not differ from HC in reward anticipation or early outcome processing during a cognitively undemanding reward task, highlighting areas of preserved functioning. However, ESZ showed altered later reward outcome evaluation, pointing to selective reward deficits during the early illness phase of schizophrenia. Further, an association between ERP-derived brain age and depressive symptoms in SZ extends prior findings linking depression with reward-related ERP blunting. Taken together, both illness phase and age may impact reward processing among SZ, and brain aging may offer a promising, novel marker of reward dysfunction that warrants further study.

Association of Sleep Electroencephalography-Based Brain Age Index With Dementia

IMPORTANCE

Dementia is an increasing cause of disability and loss of independence in the elderly population yet remains largely underdiagnosed. A biomarker for dementia that can identify individuals with or at risk for developing dementia may help close this diagnostic gap.

OBJECTIVE

To investigate the association between a sleep electroencephalography-based brain age index (BAI), the difference between chronological age and brain age estimated using the sleep electroencephalogram, and dementia.

DESIGN, SETTING, AND PARTICIPANTS

In this retrospective cross-sectional study of 9834 polysomnograms, BAI was computed among individuals with previously determined dementia, mild cognitive impairment (MCI), or cognitive symptoms but no diagnosis of MCI or dementia, and among healthy individuals without dementia from August 22, 2008, to June 4, 2018. Data were analyzed from November 15, 2018, to June 24, 2020.

EXPOSURE

Dementia, MCI, and dementia-related symptoms, such as cognitive change and memory impairment.

MAIN OUTCOMES AND MEASURES

The outcome measures were the trend in BAI when moving from groups ranging from healthy, to symptomatic, to MCI, to dementia and pairwise comparisons of BAI among these groups.

FINDINGS

A total of 5144 sleep studies were included in BAI examinations. Patients in these studies had a median (interquartile range) age of 54 (43-65) years, and 3026 (59%) were men. The patients included 88 with dementia, 44 with MCI, 1075 who were symptomatic, and 2336 without dementia. There was a monotonic increase in mean (SE) BAI from the nondementia group to the dementia group (nondementia: 0.20 [0.42]; symptomatic: 0.58 [0.41]; MCI: 1.65 [1.20]; dementia: 4.18 [1.02]; P < .001).

CONCLUSIONS AND RELEVANCE

These findings suggest that a sleep-state electroencephalography-based BAI shows promise as a biomarker associated with progressive brain processes that ultimately result in dementia.

Estimating brain age based on a uniform healthy population with deep learning and structural magnetic resonance imaging

Numerous studies have established that estimated brain age constitutes a valuable biomarker that is predictive of cognitive decline and various neurological diseases. In this work, we curate a large-scale brain MRI data set of healthy individuals, on which we train a uniform deep learning model for brain age estimation. We demonstrate an age estimation accuracy on a hold-out test set (mean absolute error = 4.06 years, r = 0.970) and an independent life span evaluation data set (mean absolute error = 4.21 years, r = 0.960). We further demonstrate the utility of the estimated age in a life span aging analysis of cognitive functions. In summary, we achieve age estimation performance comparable to previous studies, but with a more heterogenous data set confirming the efficacy of this deep learning framework. We also evaluated training with varying age distributions. The analysis of regional contributions to our brain age predictions through multiple analyses, and confirmation of the association of divergence between the estimated and chronological brain age with neuropsychological measures, may be useful in the development and evaluation of similar imaging biomarkers.

Excess brain age in the sleep electroencephalogram predicts reduced life expectancy

The brain age index (BAI) measures the difference between an individual's apparent "brain age" (BA; estimated by comparing EEG features during sleep from an individual with age norms), and their chronological age (CA); that is BAI = BA-CA. Here, we evaluate whether BAI predicts life expectancy. Brain age was quantified using a previously published machine learning algorithm for a cohort of participants ≥40 years old who underwent an overnight sleep electroencephalogram (EEG) as part of the Sleep Heart Health Study (n = 4877). Excess brain age (BAI >0) was associated with reduced life expectancy (adjusted hazard ratio: 1.12, [1.03, 1.21], p = 0.002). Life expectancy decreased by -0.81 [-1.44, -0.24] years per standard-deviation increase in BAI. Our findings show that BAI, a sleep EEG-based biomarker of the deviation of sleep microstructure from patterns normal for age, is an independent predictor of life expectancy.

Detecting self-paced walking intention based on fNIRS technology for the development of BCI

Since more and more elderly people suffer from lower extremity movement problems, it is of great social significance to assist persons with motor dysfunction to walk independently again and reduce the burden on caregivers. The self-paced walking intention, which could increase the ability of self-control on the start and stop of motion, was studied by applying brain-computer interface (BCI) technology, a novel research field. The cerebral hemoglobin signal, which was obtained from 30 subjects by applying functional near-infrared spectroscopy (fNIRS) technology, was processed to detect self-paced walking intention in this paper. Teager-Kaiser energy was extracted at each sampling point for five sub-bands (0.0095~0.021 Hz, 0.021~0.052 Hz, 0.052~0.145 Hz, 0.145~0.6 Hz, and 0.6~2.0 Hz). Gradient boosting decision tree (GBDT) was then utilized to establish the detecting model in real-time. The proposed method had a good performance to detect the walking intention and passed the pseudo-online test with a true positive rate of 100% (80/80), a false positive rate of 2.91% (4822/165171), and a detection latency of 0.39 ± 1.06 s. GBDT method had an area under the curve value of 0.944 and was 0.125 (p < 0.001) higher than linear discriminant analysis (LDA). The results reflected that it is feasible to decode self-paced walking intention by applying fNIRS technology. This study lays a foundation for applying fNIRS-based BCI technology to control walking assistive devices practically. Graphical abstract Graphical representation of the detecting process for pseudo-online test. The lower figure is a partial enlargement of the upper figure. In the lower figure, the blue line represents the probability of walking predicted by GBDT without smoothing and the orange-red line represents the smoothed probability. The dark-red ellipse shows the effect of the smoothing-threshold method.

A Between-Subject fNIRS-BCI Study on Detecting Self-Regulated Intention During Walking

OBJECTIVE

Most BCI (brain-computer interface) studies have focused on detecting motion intention from a resting state. However, the dynamic regulation of two motion states, which usually happens in real life, is rarely studied. Besides, popular within-subject methods also require an extensive and time-consuming learning stage when testing on a new subject. This paper proposed a method to discriminate dynamic gait- adjustment intention with strong adaptability for different subjects.

METHODS

Cerebral hemoglobin signals obtained from 30 subjects were studied to decode gait-adjustment intention. Cerebral hemoglobin information was recorded by using fNIRS (functional near infrared spectroscopy) technology. Mathematical morphology filtering was applied to remove zero drift and EWM (Entropy Weight Method) was used to calculate the average hemoglobin values over Regions of Interest (ROIs). The gradient boosting decision tree (GBDT) was utilized to detect the onset of self-regulated intention. A 2-layer-GA-SVM (Genetic Algorithm-Support Vector Machine) model based on stacking algorithm was further proposed to identify the four types of self-regulated intention (speed increase, speed reduction, step increase, and step reduction).

RESULTS

It was found that GBDT had a good performance to detect the onset intention with an average AUC (Area Under Curve) of 0.894. The 2-layer-GA-SVM model boosted the average ACC (accuracy) of four types of intention from 70.6% to 84.4% ( p = 0.005 ) from the single GA-SVM model. Furthermore, the proposed method passed pseudo-online test with the average results as following: AUC = 0.883, TPR (True Positive Rate) = 97.5%, FPR (False Positive Rate) = 0.11%, and LAY (Detection Latency) = -0.52 ± 2.57 seconds for the recognition of gait-adjustment intention; ACC = 80% for the recognition of adjusted gait.

CONCLUSION

The results indicate that it is feasible to decode dynamic gait-adjustment intentions from a motion state for different subjects based on fNIRS technology. It has a potential to realize the practical application of fNIRS-based brain-computer interface technology in controlling walking-assistive devices.

Combination of an Automated 3D Field Phenotyping Workflow and Predictive Modelling for High-Throughput and Non-Invasive Phenotyping of Grape Bunches

In grapevine breeding, loose grape bunch architecture is one of the most important selection traits, contributing to an increased resilience towards Botrytis bunch rot. Grape bunch architecture is mainly influenced by the berry number, berry size, the total berry volume, and bunch width and length. For an objective, precise, and high-throughput assessment of these architectural traits, the 3D imaging sensor Artec® Spider was applied to gather dense point clouds of the visible side of grape bunches directly in the field. Data acquisition in the field is much faster and non-destructive in comparison to lab applications but results in incomplete point clouds and, thus, mostly incomplete phenotypic values. Therefore, lab scans of whole bunches (360°) were used as ground truth. We observed strong correlations between field and lab data but also shifts in mean and max values, especially for the berry number and total berry volume. For this reason, the present study is focused on the training and validation of different predictive regression models using 3D data from approximately 2000 different grape bunches in order to predict incomplete bunch traits from field data. Modeling concepts included simple linear regression and machine learning-based approaches. The support vector machine was the best and most robust regression model, predicting the phenotypic traits with an R2 of 0.70–0.91. As a breeding orientated proof-of-concept, we additionally performed a Quantitative Trait Loci (QTL)-analysis with both the field modeled and lab data. All types of data resulted in joint QTL regions, indicating that this innovative, fast, and non-destructive phenotyping method is also applicable for molecular marker development and grapevine breeding research.

Bias-adjustment in neuroimaging-based brain age frameworks: A robust scheme

The level of prediction error in the brain age estimation frameworks is associated with the authenticity of statistical inference on the basis of regression models. In this paper, we present an efficacious and plain bias-adjustment scheme using chronological age as a covariate through the training set for downgrading the prediction bias in a Brain-age estimation framework. We applied proposed bias-adjustment scheme coupled by a machine learning-based brain age framework on a large set of metabolic brain features acquired from 675 cognitively unimpaired adults through fluorodeoxyglucose positron emission tomography data as the training set to build a robust Brain-age estimation framework. Then, we tested the reliability of proposed bias-adjustment scheme on 75 cognitively unimpaired adults, 561 mild cognitive impairment patients as well as 362 Alzheimer's disease patients as independent test sets. Using the proposed method, we gained a strong R2 of 0.81 between the chronological age and brain estimated age, as well as an excellent mean absolute error of 2.66 years on 75 cognitively unimpaired adults as an independent set; whereas an R2 of 0.24 and a mean absolute error of 4.71 years was achieved without bias-adjustment. The simulation results demonstrated that the proposed bias-adjustment scheme has a strong capability to diminish prediction error in brain age estimation frameworks for clinical settings.

Selection of the Best Electroencephalogram Channel to Predict the Depth of Anesthesia

Precise cerebral dynamics of action of the anesthetics are a challenge for neuroscientists. This explains why there is no gold standard for monitoring the Depth of Anesthesia (DoA) and why experimental studies may use several electroencephalogram (EEG) channels, ranging from 2 to 128 EEG-channels. Our study aimed at finding the scalp area providing valuable information about brain activity under general anesthesia (GA) to select the more optimal EEG channel to characterized the DoA. We included 30 patients undergoing elective, minor surgery under GA and used a 32-channel EEG to record their electrical brain activity. In addition, we recorded their physiological parameters and the BIS monitor. Each individual EEG channel data were processed to test their ability to differentiate awake from asleep states. Due to strict quality criteria adopted for the EEG data and the difficulties of the real-life setting of the study, only 8 patients recordings were taken into consideration in the final analysis. Using 2 classification algorithms, we identified the optimal channels to discriminate between asleep and awake states: the frontal and temporal F8 and T7 were retrieved as being the two bests channels to monitor DoA. Then, using only data from the F8 channel, we tried to minimize the number of features required to discriminate between the awake and asleep state. The best algorithm turned out to be the Gaussian Naïve Bayes (GNB) requiring only 5 features (Area Under the ROC Curve - AUC- of 0.93 ± 0.04). This finding may pave the way to improve the assessment of DoA by combining one EEG channel recordings with a multimodal physiological monitoring of the brain state under GA. Further work is needed to see if these results may be valid to asses the depth of sedation in ICU.

Deep Learning and Multiplex Networks for Accurate Modeling of Brain Age

Recent works have extensively investigated the possibility to predict brain aging from T1-weighted MRI brain scans. The main purposes of these studies are the investigation of subject-specific aging mechanisms and the development of accurate models for age prediction. Deviations between predicted and chronological age are known to occur in several neurodegenerative diseases; as a consequence, reaching higher levels of age prediction accuracy is of paramount importance to develop diagnostic tools. In this work, we propose a novel complex network model for brain based on segmenting T1-weighted MRI scans in rectangular boxes, called patches, and measuring pairwise similarities using Pearson's correlation to define a subject-specific network. We fed a deep neural network with nodal metrics, evaluating both the intensity and the uniformity of connections, to predict subjects' ages. Our model reaches high accuracies which compare favorably with state-of-the-art approaches. We observe that the complex relationships involved in this brain description cannot be accurately modeled with standard machine learning approaches, such as Ridge and Lasso regression, Random Forest, and Support Vector Machines, instead a deep neural network has to be used.

Investigating systematic bias in brain age estimation with application to post-traumatic stress disorders

Brain age prediction using machine-learning techniques has recently attracted growing attention, as it has the potential to serve as a biomarker for characterizing the typical brain development and neuropsychiatric disorders. Yet one long-standing problem is that the predicted brain age is overestimated in younger subjects and underestimated in older. There is a plethora of claims as to the bias origins, both methodologically and in data itself. With a large neuroanatomical dataset (N = 2,026; 6-89 years of age) from multiple shared datasets, we show this bias is neither data-dependent nor specific to particular method including deep neural network. We present an alternative account that offers a statistical explanation for the bias and describe a simple, yet efficient, method using general linear model to adjust the bias. We demonstrate the effectiveness of bias adjustment with a large multi-modal neuroimaging data (N = 804; 8-21 years of age) for both healthy controls and post-traumatic stress disorders patients obtained from the Philadelphia Neurodevelopmental Cohort.