Key result
EEG-based CNN-Transformer fusion model achieves 97% accuracy in detecting schizophrenia relapse versus leading baselines.
Why the study?
Proactively detecting schizophrenia relapse remains challenging because existing predictive models often fail to capture complex neurophysiological and behavioral dynamics and rely on shallow or unimodal data sources with limited early sensitivity.
Does a CNN-Transformer fusion model improve the proactive detection of schizophrenia relapse from EEG signals compared to leading baselines?
Does a CNN-Transformer fusion model improve the proactive detection of schizophrenia relapse from EEG signals compared to leading baselines?
A novel CNN-Transformer fusion model using EEG and clinical features achieved 97% accuracy in predicting schizophrenia relapse, outperforming existing baseline models.
This is the authors' abstract. We don't add key points for this paper.
Proactively detecting schizophrenia relapse remains a critical challenge in psychiatric care, where traditional predictive models often fail to capture the complex neurophysiological and behavioral dynamics preceding recurrence. Existing methods typically rely on shallow architectures or unimodal data sources, resulting in limited sensitivity-particularly in the early stages of relapse. In this study, we propose a CNN-Transformer fusion model that leverages the complementary strengths of Convolutional Neural Networks (CNNs) and Transformer-based architectures to process electroencephalogram (EEG) signals enriched with clinical and sentiment-derived features. This hybrid framework enables joint spatial-temporal modeling of relapse indicators, allowing for a more nuanced and patient-specific analysis. Unlike previous approaches, our model incorporates a multi-resource data fusion pipeline, improving robustness, interpretability, and clinical relevance. Experimental evaluations demonstrate a superior prediction accuracy of 97%, with notable improvements in recall and F1-score compared to leading baselines. Moreover, the model significantly reduces false negatives, a crucial factor for timely therapeutic intervention. By addressing the limitations of unimodal and superficial prediction strategies, this framework lays the groundwork for scalable, real-world applications in continuous mental health monitoring and personalized relapse prevention.
Answers are grounded in this paper and cite their sources.
May support EEG-based relapse monitoring in schizophrenia; leaves open prospective validation before clinical adoption.
No takes yet. Share an insight, caveat, or question.
Yasin et al. (2025) studied Schizophrenia relapse. CNN-Transformer fusion model vs. leading baselines was evaluated on Prediction accuracy. A CNN-Transformer fusion model using EEG signals achieved a superior prediction accuracy of 97% for detecting schizophrenia relapse compared to leading baselines.
Synapse has enriched 10 related papers. Consider them for comparative context: