Early detection of neurodegenerative diseases is critical. Distinguishing early-stage Creutzfeldt–Jakob disease (CJD) from “mimics” like Alzheimer's disease (AD) remains a major challenge; while EEG is valuable in advanced CJD, early-stage abnormalities are often non-specific and overlap with other rapidly progressive dementias. Deep learning offers promising EEG-based diagnostic solutions, but clinical adoption requires transparent decision-making, the interpretability of the features learned by deep learning models is equally important. In this context, careful model design and explainability are essential. In this paper, we propose a novel interpretable framework, EEGDecoder-x, for decoding EEG signals from subjects with Alzheimer's disease, Creutzfeldt–Jakob disease, and healthy controls, while providing insight into the model's learned characteristics. The EEGDecoder-x framework comprises two main components: a hybrid attention network for disease decoding (EEGDecoder-Net) and an explainability module (EEGDecoder-XAI). EEGDecoder-Net combines a convolutional neural network with a dual attention mechanism, followed by a classification layer, enabling efficient spatio-temporal feature extraction. EEGDecoder-XAI provides a comprehensive local and global explanations of the network's learning process for spatio-temporal dimensions. We validate the proposed framework using a Leave-One-Subject-Out evaluation paradigm, achieving 97.22% classification accuracy on a dataset of 36 subjects (12 with AD, 12 with CJD, and 12 healthy controls), and outperforming the baseline models, demonstrating both the effectiveness and interpretability of EEGDecoder-x.
Muhammad Suffian, Nadia Mammone, C. Ieracitano et al.· Frontiers in Neurology· 0 citations
OBJECTIVE
To investigate changes in quality of life (QoL) dimensions and their relationship with seizure outcome, depression, and suicidality after the addition or substitution of an anti-seizure medication (ASM) in adults with drug-resistant focal epilepsy.
METHODS
A total of 665 consecutively enrolled patients were followed prospectively and assessed with Quality of Life in Epilepsy Inventory 31 (QOLIE-31) and the Neurological Disorders Depression Inventory for Epilepsy (NDDI-E). QoL changes over time for the overall population and seizure outcome categories were analyzed with analysis of variance (ANOVA), whereas factors affecting QoL changes were assessed by using a linear regression model.
RESULTS
Seizure freedom was associated with a marked improvement across all QoL domains, ranging from 11 points for Seizure worry to 4 points for Emotional well-being. The presence of depression before starting medication and its persistence during the observation period was associated with a global worsening of QoL across all domains, ranging from 10 points worse for Social functioning, almost 8 points for Energy and fatigue, 6 points for Cognitive functioning, and to nearly 5 points for Seizure worry. The new development of depression during treatment was associated with worsening in specific QoL domains such as Cognitive functioning, Social functioning, and Overall QoL subscales. Persistent positive suicidality screening was associated with progressive worsening in the domain Emotional well-being.
SIGNIFICANCE
Seizure freedom can improve all domains of QoL, but mainly Seizure worry, although this can be negatively affected by depressed mood. Improvement in the domain of Social functioning requires a period of sustained seizure freedom longer than 6 months to improve, and it is negatively influenced by persistent depressed mood. In contrast, changes in Emotional well-being are negatively influenced by suicidality. Clinical and demographic variables, including duration of epilepsy and number of comorbidities or concomitant medical problems, showed no correlation with changes in QoL.
Marco Mula, S. Borghs, Bruno Ferrò et al.· Epilepsia· 0 citations
