提出混合架构，让自动脑电报告精确到临床可用水平。
Bridging the Compression-Precision Paradox: A Hybrid Architecture for Clinical EEG Report Generation with Guaranteed Measurement Accuracy
- 先用信号处理提取精确数值，再生成文本，避免压缩损失
- 在两个数据集上减少60%误报，检测速度提升50%，测量误差极小
- 适合临床医生做自动化辅助诊断，尤其关注时间精度的场景
自动脑电监测需达到临床级精度以识别癫痫发作。临床脑电记录长度超过大模型上下文窗口，需压缩400:1以上，导致细微时间精度丢失。0.5赫兹的误差可区分失神癫痫与伦诺克斯-加斯托综合征。大模型缺乏时序理解能力，依赖压缩表示中的统计关联，常产生不准确的测量值。本文将测量提取与文本生成分离：先通过信号处理计算精确临床数值，再经跨模态桥梁实现脑电到语言的翻译，并采用参数高效微调与冻结槽位的约束解码。多速率采样在保持长程上下文的同时保留事件级精度。在TUH和CHB-MIT数据集上的评估显示，系统误报减少60%，检测速度提升50%，测量精度达到临床可接受水平。这是首个在自动生成脑电报告中保障临床测量准确性的系统。
原文摘要 · Abstract (English)
Automated EEG monitoring requires clinician-level precision for seizure detection and reporting. Clinical EEG recordings exceed LLM context windows, requiring extreme compression (400:1+ ratios) that destroys fine-grained temporal precision. A 0.5 Hz error distinguishes absence epilepsy from Lennox-Gastaut syndrome. LLMs lack inherent time-series comprehension and rely on statistical associations from compressed representations. This dual limitation causes systems to hallucinate clinically incorrect measurement values. We separate measurement extraction from text generation. Our hybrid architecture computes exact clinical values via signal processing before compression, employs a cross-modal bridge for EEG-to-language translation, and uses parameter-efficient fine-tuning with constrained decoding around frozen slots. Multirate sampling maintains long-range context while preserving event-level precision. Evaluation on TUH and CHB-MIT datasets achieves 60% fewer false alarms, 50% faster detection, and sub-clinical measurement precision. This is the first system guaranteeing clinical measurement accuracy in automated EEG reports.
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。