信号、图像或符号：通过统一框架探索心电图-语言模型的最佳输入表示
Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework
AI总结：
本研究首次系统比较了心电图-语言模型（ELM）的三种输入表示（信号、图像、符号），发现符号表示在6个数据集和5个指标上表现最优，为ELM开发提供输入选择指导。
摘要：
近期研究进展日益将大型语言模型（LLMs）应用于心电图（ECG）解读，催生了心电图-语言模型（ELMs）。在给定心电图和文本查询的条件下，ELM自回归地生成自由形式的文本响应。与传统基于分类的系统不同，ELMs通过发布诊断、分析波形形态、识别致病因素并提出针对患者的具体行动计划，来模拟心脏电生理学专家。为实现这一潜力，研究人员正在构建将心电图与文本对话配对的指令微调数据集，并在此类资源上训练ELMs。然而，在进一步扩展ELMs之前，有一个基本问题尚待探索：哪种心电图输入表示最为有效？在近期工作中，出现了三种候选表示——原始时间序列信号、渲染图像和离散化符号序列。我们首次在6个公共数据集和5个评估指标上对这些模态进行了全面基准测试。我们发现，符号表示相对于信号和图像输入，在统计显著胜出次数上最多。我们进一步消融了LLM骨干网络、心电图持续时间和令牌预算，并评估了对信号扰动的鲁棒性。我们希望我们的发现能为开发下一代ELMs时选择输入表示提供明确指导。
英文摘要：
Recent advances have increasingly applied large language models (LLMs) to electrocardiogram (ECG) interpretation, giving rise to Electrocardiogram-Language Models (ELMs). Conditioned on an ECG and a textual query, an ELM autoregressively generates a free-form textual response. Unlike traditional classification-based systems, ELMs emulate expert cardiac electrophysiologists by issuing diagnoses, analyzing waveform morphology, identifying contributing factors, and proposing patient-specific action plans. To realize this potential, researchers are curating instruction-tuning datasets that pair ECGs with textual dialogues and are training ELMs on these resources. Yet before scaling ELMs further, there is a fundamental question yet to be explored: What is the most effective ECG input representation? In recent works, three candidate representations have emerged-raw time-series signals, rendered images, and discretized symbolic sequences. We present the first comprehensive benchmark of these modalities across 6 public datasets and 5 evaluation metrics. We find symbolic representations achieve the greatest number of statistically significant wins over both signal and image inputs. We further ablate the LLM backbone, ECG duration, and token budget, and we evaluate robustness to signal perturbations. We hope that our findings offer clear guidance for selecting input representations when developing the next generation of ELMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
