No abstract

Electroencephalography (EEG) has emerged as a powerful tool for quantitatively studying the brain that enables natural and mobile experiments. Recent advances in EEG have allowed for the use of dry electrodes that do not require a conductive medium between the recording electrode and the scalp. The overall goal of this research was to gain an understanding of the overall usability and signal quality of dry EEG headsets compared to traditional gel-based systems in an unconstrained environment. EEG was used to collect Mobile Brain-body Imaging (MoBI) data from 432 people as they experienced an art exhibit in a public museum. The subjects were instrumented with either one of four dry electrode EEG systems or a conventional gel electrode EEG system. Each of the systems was evaluated based on the signal quality and usability in a real-world setting. First, we describe the various artifacts that were characteristic of each of the systems. Second, we report on each system's usability and their limitations in a mobile setting. Third, to evaluate signal quality for task discrimination and characterization, we employed a data driven clustering approach on the data from 134 of the 432 subjects (those with reliable location tracking information and usable EEG data) to evaluate the power spectral density (PSD) content of the EEG recordings. The experiment consisted of a baseline condition in which the subjects sat quietly facing a white wall for 1 min. Subsequently, the participants were encouraged to explore the exhibit for as long as they wished (piece-viewing). No constraints were placed upon the individual in relation to action, time, or navigation of the exhibit. In this freely-behaving approach, the EEG systems varied in their capacity to record characteristic modulations in the EEG data, with the gel-based system more clearly capturing stereotypical alpha and beta-band modulations.

The brain response to conceptual art was studied with mobile electroencephalography (EEG) to examine the neural basis of aesthetic experiences. In contrast to most studies of perceptual phenomena, participants were moving and thinking freely as they viewed the exhibit The Boundary of Life is Quietly Crossed by Dario Robleto at the Menil Collection-Houston. The brain activity of over 400 subjects was recorded using dry-electrode and one reference gel-based EEG systems over a period of 3 months. Here, we report initial findings based on the reference system. EEG segments corresponding to each art piece were grouped into one of three classes (complex, moderate, and baseline) based on analysis of a digital image of each piece. Time, frequency, and wavelet features extracted from EEG were used to classify patterns associated with viewing art, and ranked based on their relevance for classification. The maximum classification accuracy was 55% (chance = 33%) with delta and gamma features the most relevant for classification. Functional analysis revealed a significant increase in connection strength in localized brain networks while subjects viewed the most aesthetically pleasing art compared to viewing a blank wall. The direction of signal flow showed early recruitment of broad posterior areas followed by focal anterior activation. Significant differences in the strength of connections were also observed across age and gender. This work provides evidence that EEG, deployed on freely behaving subjects, can detect selective signal flow in neural networks, identify significant differences between subject groups, and report with greater-than-chance accuracy the complexity of a subject's visual percept of aesthetically pleasing art. Our approach, which allows acquisition of neural activity “in action and context,” could lead to understanding of how the brain integrates sensory input and its ongoing internal state to produce the phenomenon which we term aesthetic experience.

Objective:To determine whether machine learning (ML) algorithms can improve the prediction of delayed cerebral ischemia (DCI) and functional-outcomes after subarachnoid hemorrhage (SAH).Methods:ML models and standard models (SM) were trained to predict DCI and functional-outcomes with data collected within 3 days of admission. Functional-outcomes at discharge and at 3-months were quantified using the modified Rankin scale (mRS) for neurological disability (dichotomized as ‘good’ (mRS≤3) vs ‘bad’ (mRS≥4) outcomes). Concurrently, clinicians prospectively prognosticated 3-month outcomes of patients. The performance of ML, SM and clinicians are retrospectively compared.Results:DCI status, discharge, and 3-month outcomes were available for 399, 393 and 240 subjects respectively. Prospective clinician (an attending, a fellow and a nurse) prognostication of 3-month outcomes was available for 90 subjects. ML models yielded predictions with the following AUC (area under the receiver operating curve) scores: 0.75 ± 0.07 (95% CI: 0.64 to 0.84) for DCI, 0.85 ± 0.05 (95% CI: 0.75 to 0.92) for discharge outcome, and 0.89 ± 0.03 (95% CI: 0.81 to 0.94) for 3-month outcome. ML outperformed SMs, improving AUC by 0.20 (95% CI: -0.02–0.4) for DCI, by 0·07 ± 0.03 (95% CI: -0.0018–0.14) for discharge outcomes, by 0.14 (95% CI: 0.03 –0.24) for 3-month outcomes and matched physician’s performance in predicting 3-month outcomes.Conclusion:ML models significantly outperform SMs in predicting DCI and functional-outcomes and has the potential to improve SAH management.