研究人员开发了EEG-SpikeAgent，一个利用大型语言模型（LLM）代理自动生成信号处理特征以检测脑电图（EEG）数据中癫痫样放电的新框架。该代理系统迭代地提出、执行和优化EEG特征模块，旨在提高传统深度学习模型的解释性。在VEPISET数据集上进行测试时，EEG-SpikeAgent实现了0.935的高ROC曲线下面积，展示了其在可审计和可检查的EEG特征工程方面的潜力。 AI
影响 自动化复杂的医学信号分析特征工程，可能提高诊断准确性和可解释性。
排序理由 该集群描述了一篇研究论文，详细介绍了使用LLM代理进行自动脑电图尖波检测的新方法。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.04558v1 Announce Type: cross Abstract: Automated detection of interictal epileptiform discharges in scalp electroencephalography (EEG) is clinically important, but recent high-performing deep-learning models often trade interpretability for accuracy. We introduce EEG-S…
Automated detection of interictal epileptiform discharges in scalp electroencephalography (EEG) is clinically important, but recent high-performing deep-learning models often trade interpretability for accuracy. We introduce EEG-SpikeAgent, a closed-loop program-synthesis framewo…
Automated detection of interictal epileptiform discharges in scalp electroencephalography (EEG) is clinically important, but recent high-performing deep-learning models often trade interpretability for accuracy. We introduce EEG-SpikeAgent, a closed-loop program-synthesis framewo…