19 July 2018 in European Journal of Neuroscience
11 October 2019 in Movement Disorders
14 September 2016 in European Journal of Applied Physiology
25 September 2023 in Frontiers in Psychiatry
Introduction: Patients 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.Methods: We 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.Results: The 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.Discussion: These results highlight the potential utility of interpretable machine learning algorithms as an aid in diagnosis of schizophrenia and other psychiatric disorders presenting oscillatory abnormalities.
10 December 2024 in Heliyon
KAKilian Abellaneda-Pérez
+10
In early-stage Alzheimer's disease (AD) amyloid-β (Aβ) deposition can induce neuronal hyperactivity, thereby potentially triggering activity-dependent neuronal secretion of phosphorylated tau (p-tau), ensuing tau aggregation and spread. Therefore, cortical excitability is a candidate biomarker for early AD detection. Moreover, lowering neuronal excitability could potentially complement strategies to reduce Aβ and tau buildup. There is, however, a lack of understanding of the relationship between cortical excitability and p-tau increase in vivo. Therefore, in a sample of 658 healthy middle-aged (between the ages of 40 and 65) participants of the Barcelona Brain Health Initiative cohort study, we examined the relation of blood-based tau, phosphorylated at amino acid 181 (p-tau181), reflecting neuronal p-tau secretion; neurofilament light chain (NfL), as a passively released control for p-tau181; and electroencephalography (EEG) markers of cortical excitability. A subsample of 47 participants also completed a controlled brain perturbation approach via transcranial magnetic stimulation (TMS) with concurrent EEG. Results show that both spontaneous (i.e., resting-state) and perturbation-based TMS-EEG markers, are associated with blood p-tau181, particularly in older individuals. The perturbation-based marker was a significantly more sensitive predictor of p-tau181 concentration than the spontaneous resting state EEG-based marker. The relationships observed are not present for the NfL control. These results show that relationships between p-tau181 and cortical excitability are present in healthy middle-aged subjects and that p-tau181 increases may reflect activity-dependent secretion.
1 August 2019 in Neuroscience Letters