用字节对编码直接生成心电图文本，训练快、数据少、结果可解释。
ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language Modeling
- 将心电图信号转为可读的令牌，实现端到端语言模型训练。
- 训练速度提升3倍，仅需传统方法48%的数据量。
- 生成结果可回溯原始信号，适合医疗生成与可解释性研究。
大语言模型（LLM）在多个领域展现出卓越的通用性，包括心电图（ECG）应用。现有方法多采用两阶段流程：先用自监督学习（SSL）预训练专用的ECG编码器，再用编码特征微调语言模型进行自然语言生成（NLG）。但此类方法存在训练效率低和编码特征难以解释的问题。为此，我们提出ECG-Byte，一种适配于心电图的字节对编码（BPE）分词管道，用于心电图的自回归语言建模。ECG-Byte将心电图信号压缩并编码为令牌，使心电图与文本令牌能直接联合输入语言模型，实现端到端训练。该方法提升了可解释性，因编码后的令牌可映射回原始信号。基于ECG-Byte，我们在保持竞争力的NLG性能的同时，训练速度提升3倍，所需数据仅为传统方法的48%。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated exceptional versatility across domains, including applications to electrocardiograms (ECGs). A growing body of work focuses on generating text from multi-channeled ECG signals and corresponding textual prompts. Existing approaches often involve a two-stage process: pretraining an ECG-specific encoder with a self-supervised learning (SSL) objective, followed by finetuning an LLM for natural language generation (NLG) using encoder-derived features. However, these methods face two key limitations: inefficiency due to multi-stage training and challenges in interpreting encoder-generated features. To overcome these issues, we propose ECG-Byte, an adapted byte pair encoding (BPE) tokenizer pipeline for autoregressive language modeling of ECGs. ECG-Byte compresses and encodes ECG signals into tokens, enabling direct end-to-end LLM training by combining ECG and text tokens. This approach enhances interpretability, as ECG tokens can be directly mapped back to the original signals. Leveraging ECG-Byte, we achieve competitive NLG performance while training 3 times faster and using just 48\% of the data required by traditional two-stage methods.
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。