Mapping cognitive brain functions at scale

Balasubramani, Pragathi Priyadharsini; Ojeda, Alejandro González; Grennan, Gillian; Maric, Vojislav; Le, Hortense; Alim, Fahad; Zafar-Khan, Mariam; Diaz-Delgado, Juan; Silveira, Sarita; Ramanathan, Dhakshin; Mishra, Jyoti

doi:10.1016/j.neuroimage.2020.117641

Cited by 28 publications

(43 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the SBL algorithm has been benchmarked to produce evidence-optimized inverse source models at 0.95 AUC relative to the ground truth, verified using both data and simulations [44,45]. We have also shown that cortical source mapping with this method has high test-retest reliability [29].…”

Section: Neural Processing Methodsmentioning

confidence: 78%

“…All data collected for this study have been previously reported [29], and we used this existing dataset for our symptom prediction analyses.…”

Section: Methodsmentioning

confidence: 99%

Section: Overview Of the Datasetmentioning

confidence: 99%

“…The study, Balasubramani et al, (2021), used EEG data of 97 healthy adult subjects [29] that completed five cognitive tasks using the BrainE platform. The details of subject characteristics and methods used for data collection and cognitive task-related EEG processing are presented below and are also previously reported [29]. For building the model features, for each subject and each task, we used the task-averaged EEG data around the global peak amplitudes of the evoked signals as identified in three frequency bands-theta (θ, 100-300 msecs), alpha (α, 100-300 msecs), and beta (β, 400-600 msecs)-for 68 cortical regions of interest (ROIs) that were reconstructed as per the Desikan-Killiany atlas [33].…”

Section: Overview Of the Datasetmentioning

confidence: 99%

“…For this study, we leverage a scalable cognitive brain-mapping platform that we recently developed called the Brain Engagement Platform (BrainE [29]). A total of 97 healthy adults participated in the study, performing the five fundamental cognitive tasks of selective attention, response inhibition, working memory, interference processing, and emotion interference processing, with simultaneous EEG recorded on all tasks.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Utility of Cognitive Neural Features for Predicting Mental Health Behaviors

Kato

Balasubramani

Ramanathan

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Neural Processing Methodsmentioning

confidence: 78%

“…All data collected for this study have been previously reported [29], and we used this existing dataset for our symptom prediction analyses.…”

Section: Methodsmentioning

confidence: 99%