Dense attention network identifies EEG abnormalities during working memory performance of patients with schizophrenia

Abstract

IntroductionPatients with schizophrenia typically exhibit deficits in working memory (WM) associated with abnormalities in brain activity. Alterations in the encoding, maintenance and retrieval phases of sequential WM tasks are well established. However, due to the heterogeneity of symptoms and complexity of its neurophysiological underpinnings, differential diagnosis remains a challenge. We conducted an electroencephalographic (EEG) study during a visual WM task in fifteen schizophrenia patients and fifteen healthy controls. We hypothesized that EEG abnormalities during the task could be identified, and patients successfully classified by an interpretable machine learning algorithm.MethodsWe tested a custom dense attention network (DAN) machine learning model to discriminate patients from control subjects and compared its performance with simpler and more commonly used machine learning models. Additionally, we analyzed behavioral performance, event-related EEG potentials, and time-frequency representations of the evoked responses to further characterize abnormalities in patients during WM.ResultsThe DAN model was significantly accurate in discriminating patients from healthy controls, ACC = 0.69, SD = 0.05. There were no significant differences between groups, conditions, or their interaction in behavioral performance or event-related potentials. However, patients showed significantly lower alpha suppression in the task preparation, memory encoding, maintenance, and retrieval phases F(1,28) = 5.93, p = 0.022, η2 = 0.149. Further analysis revealed that the two highest peaks in the attention value vector of the DAN model overlapped in time with the preparation and memory retrieval phases, as well as with two of the four significant time-frequency ROIs.DiscussionThese results highlight the potential utility of interpretable machine learning algorithms as an aid in diagnosis of schizophrenia and other psychiatric disorders presenting oscillatory abnormalities.

Differences in Electroencephalography Power Levels between Poor and Good Performance in Attentional Tasks

“…Another study suggested that α wave as α lateralization plays a causal role in attention tasks [ 23 , 24 ]. Conversely, patients with schizophrenia, who typically exhibit deficits in working memory, showed significantly lower α suppression in the task preparation, memory encoding, maintenance, and retrieval phases, indicating strong α power [ 25 ], whereas stronger connections in δ, β, and γ bands were found in the depressive emotion group [ 10 ]. These results may imply that attentional network might be modulated due to mental conditions.…”