Utility of Cognitive Neural Features for Predicting Mental Health Behaviors

Abstract

Cognitive dysfunction underlies common mental health behavioral symptoms including depression, anxiety, inattention, and hyperactivity. In this study of 97 healthy adults, we aimed to classify healthy vs. mild-to-moderate self-reported symptoms of each disorder using cognitive neural markers measured with an electroencephalography (EEG). We analyzed source-reconstructed EEG data for event-related spectral perturbations in the theta, alpha, and beta frequency bands in five tasks, a selective attention and response inhibition task, a visuospatial working memory task, a Flanker interference processing task, and an emotion interference task. From the cortical source activation features, we derived augmented features involving co-activations between any two sources. Logistic regression on the augmented feature set, but not the original feature set, predicted the presence of psychiatric symptoms, particularly for anxiety and inattention with >80% sensitivity and specificity. We also computed current flow closeness and betweenness centralities to identify the “hub” source signal predictors. We found that the Flanker interference processing task was the most useful for assessing the connectivity hubs in general, followed by the inhibitory control go-nogo paradigm. Overall, these interpretable machine learning analyses suggest that EEG biomarkers collected on a rapid suite of cognitive assessments may have utility in classifying diverse self-reported mental health symptoms.

Mindfulness Coaching with Digital Lifestyle Monitoring Enhances Selective Attention in Medical Scientists

“…We have validated the reliability of this BrainE© platform and shown its utility in measuring cognitive changes across the lifespan [28][29][30][31][32] . We also demonstrated its relevance to predict mental health [33][34][35][36] . Here we deploy the BrainE© platform to measure post vs. pre-intervention changes in the well-being intervention group and compare outcomes with repeat assessments in a control group to control for practice effects.…”

Posterior default mode network activity underlies distracted interoceptive attention and provides an objective basis for low mindfulness & depression

“…We then investigated whether consistency of interoceptive attention is a meaningful marker of cognition by investigating whether it can predict performance on exteroceptive cognitive tasks that participants performed in the same session. All participants completed a standard set of cognitive tasks for inhibitory control (Go/NoGo task), interference processing (Flanker task), working memory (visuo-spatial delayed match to probe task), and an emotion bias task during the same experimental session as the interoceptive task; these tasks have been previously described in recent publications 36,39,44,54,55,57,60,61,77,78 . We calculated performance e ciency as a composite metric on each task as the product of the signal detection sensitivity metric, d-prime, and processing speed.…”

“…Neural Analyses. We applied a uniform processing pipeline to EEG data acquired on the interoceptive attention task as well as resting state data, as published in several of our studies 36,44,[54][55][56][57][58][59][60][61] . This included: 1) data pre-processing, 2) computing the EEG power spectrum, and 3) cortical source localization of the EEG data to estimate source-level neural activity and connectivity.…”

Climate Trauma from Wildfire Exposure Impacts Cognitive Decision-Making

“…Neural data analyses were conducted using a uniform two-step processing pipeline published in several of our studies 7,21,38,[41][42][43][44][45][46][47][48] . Step 1) EEG channel data processing was conducted using the EEGLAB toolbox v2020 in MATLAB v2022b.…”