融合脑电与人口统计信息，用深度学习提升精神疾病诊断准确率
Multimodal Data-Driven Classification of Mental Disorders: A Comprehensive Approach to Diagnosing Depression, Anxiety, and Schizophrenia
- 结合脑电图与年龄、性别等数据，构建多模态分类模型
- 相干性特征显著提升分类准确率与鲁棒性
- 适合精神健康研究者与临床辅助诊断系统开发者
本研究探索将脑电图（EEG）数据与年龄、性别、教育程度及智商（IQ）等社会人口学特征融合，用于诊断精神分裂症、抑郁症和焦虑症的潜力。基于Apache Spark与卷积神经网络（CNN），构建适用于大数据环境的数据驱动分类流程，有效分析大规模数据集。通过分析功率谱密度（PSD）和相干性等脑电参数，评估精神障碍相关的脑活动与连接模式。对比分析表明，相干性特征对分类性能有显著提升。研究强调了整合多源数据的综合方法在开发高效诊断工具中的重要性，展示了利用大数据、先进深度学习方法和多模态数据提升精神健康诊断精度、可用性与理解力的前景。
原文摘要 · Abstract (English)
This study investigates the potential of multimodal data integration, which combines electroencephalogram (EEG) data with sociodemographic characteristics like age, sex, education, and intelligence quotient (IQ), to diagnose mental diseases like schizophrenia, depression, and anxiety. Using Apache Spark and convolutional neural networks (CNNs), a data-driven classification pipeline has been developed for big data environment to effectively analyze massive datasets. In order to evaluate brain activity and connection patterns associated with mental disorders, EEG parameters such as power spectral density (PSD) and coherence are examined. The importance of coherence features is highlighted by comparative analysis, which shows significant improvement in classification accuracy and robustness. This study emphasizes the significance of holistic approaches for efficient diagnostic tools by integrating a variety of data sources. The findings open the door for creative, data-driven approaches to treating psychiatric diseases by demonstrating the potential of utilizing big data, sophisticated deep learning methods, and multimodal datasets to enhance the precision, usability, and comprehension of mental health diagnostics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。