Brain lesions caused by cerebral ischemia lead to network disturbances in both hemispheres, causing a subsequent reorganization of functional connectivity both locally and remotely with respect to the injury. Quantitative electroencephalography (qEEG) methods have long been used for exploring brain electrical activity and functional connectivity modifications after stroke. However, results obtained so far are not univocal. Here, we used basic and advanced EEG methods to characterize how brain activity and functional connectivity change after stroke. Thirty-three unilateral post stroke patients in the sub-acute phase and ten neurologically intact age-matched right-handed subjects were enrolled. Patients were subdivided into two groups based on lesion location: cortico-subcortical (CS, n = 18) and subcortical (S, n = 15), respectively. Stroke patients were evaluated in the period ranging from 45 days since the acute event (T0) up to 3 months after stroke (T1) with both neurophysiological (resting state EEG) and clinical assessment (Barthel Index, BI) measures, while healthy subjects were evaluated once. Brain power at T0 was similar between the two groups of patients in all frequency bands considered (δ, θ, α, and β). However, evolution of θ-band power over time was different, with a normalization only in the CS group. Instead, average connectivity and specific network measures (Integration, Segregation, and Small-worldness) in the β-band at T0 were significantly different between the two groups. The connectivity and network measures at T0 also appear to have a predictive role in functional recovery (BI T1-T0), again group-dependent. The results obtained in this study showed that connectivity measures and correlations between EEG features and recovery depend on lesion location. These data, if confirmed in further studies, on the one hand could explain the heterogeneity of results so far observed in previous studies, on the other hand they could be used by researchers as biomarkers predicting spontaneous recovery, to select homogenous groups of patients for the inclusion in clinical trials.
Objective. This study aims to design and implement the first Deep Learning (DL) model to classify subjects in the prodromic states of Alzheimer’s Disease (AD) based on resting-state electroencephalographic signals. Approach. EEG recordings of 17 Healthy Controls (HC), 56 Subjective Cognitive Decline (SCD) and 45 Mild Cognitive Impairment (MCI) subjects were acquired at resting state. After preprocessing, we selected sections corresponding to eyes-closed condition. Five different datasets were created by extracting Delta, Theta, Alpha, Beta and Delta-to-Theta frequency bands using bandpass filters. To classify SCD vs MCI and HC vs SCD vs MCI, we propose a framework based on the Transformer architecture, which uses Multi-Head Attention to focus on the most relevant parts of the input signals. We trained and validated the model on each dataset with a leave-one-subject-out cross-validation approach, splitting the signals into 10-second epochs. Subjects were assigned to the same class as the majority of their epochs. Classification performances of the Transformer were assessed for both epochs and subjects and compared with other DL models. Main results. Results showed that the Delta dataset allowed our model to achieve the best performances for the discrimination of SCD and MCI, reaching an AUC of 0.807, while the highest results for the HC vs SCD vs MCI classification were obtained on Alpha and Theta with a micro-AUC higher than 0.74. Significance. We demonstrated that DL approaches can support the adoption of non-invasive and economic techniques as EEG to stratify patients in the clinical population at risk for AD. This result was achieved since the attention mechanism was able to learn temporal dependencies of the signal, focusing on the most discriminative patterns, achieving state-of-the-art results by using a deep model of reduced complexity. Our results were consistent with clinical evidence that changes in brain activity are progressive when considering early stages of AD.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.