发表机构
Institute for Advanced Studies in Basic Sciences（基础科学高等研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出基于EEG频谱图的Transformer框架，通过短时傅里叶变换和受试者级划分，实现精神分裂症自动检测，CST-SZ模型AUC-ROC达92.88%。
AI 中文摘要
精神分裂症是一种严重的精神疾病，影响全球数百万人，其诊断仍主要依赖临床评估。脑电图（EEG）提供了一种非侵入性的方法来研究大脑活动，并已显示出支持自动化精神分裂症检测的潜力。然而，现有的基于EEG的分类研究常受限于小数据集、不一致的预处理策略以及可能无法充分防止受试者相关数据泄漏的评估协议。在本研究中，我们提出了一种基于EEG的精神分裂症分类框架，该框架使用短时傅里叶变换将预处理后的EEG记录转换为时频表示。生成的频谱图图像分别使用传统机器学习算法（包括支持向量机、随机森林和XGBoost）以及深度学习模型（包括卷积架构和CNN-Transformer混合模型）进行分类。为确保评估的可靠性，所有数据划分均在受试者层面进行。实验结果表明，所提出的方法取得了有竞争力的分类性能，其中CNN-Transformer（CT-SZ）模型在独立测试集上的AUC-ROC达到88.41%，而CNN+挤压激励+Transformer（CST-SZ）模型的AUC-ROC达到92.88%。
英文摘要
Schizophrenia is a serious psychiatric disorder that affects millions of people worldwide, and its diagnosis remains primarily dependent on clinical assessment. Electroencephalography (EEG) provides a non-invasive approach to investigate brain activity and has shown potential to support automated Schizophrenia detection. However, existing EEG-based classification studies often suffer from limitations including small datasets, inconsistent preprocessing strategies, and evaluation protocols that may not adequately prevent subject-related data leakage. In this study, we propose an EEG-based Schizophrenia classification framework that transforms preprocessed EEG recordings into time-frequency representations using the Short-Time Fourier Transform. The generated spectrogram images are classified using both conventional Machine Learning algorithms, including Support Vector Machines, Random Forests, and XGBoost, and Deep Learning models, including convolutional architectures and CNN-Transformer hybrids. To ensure reliable evaluation, all data partitions are performed at the subject level, and image-level predictions are aggregated into subject-level decisions. On the independent test set of 18 subjects, the CNN-Transformer (CT-SZ) model achieves a subject-level AUC-ROC of 95.00%, while the CNN + Squeeze-and-Excitation + Transformer (CST-SZ) model achieves 92.50%.
Comments6 Pages, 5 figures, Conference
