Electrocardiography (ECG) plays a central role in cardiovascular diagnostics, yet existing automated approaches often struggle to generalize across clinical tasks and offer limited support for open-ended reasoning. We present HeartLLM, a novel framework that integrates time-series (TS) and language modeling by enabling large language models (LLMs) to process 12-lead ECG signals for clinical text generation tasks. Our approach discretizes continuous ECG embeddings into quantized codes using a lead-wise encoder and quantization module. These quantized codes are then mapped to an extended ECG vocabulary to form ECG tokens, enabling the model to process both ECG and natural language inputs within a unified framework. To bridge the modality gap, we pretrain the model on an autoregressive ECG token forecasting task, allowing the LLM to capture temporal dynamics through its inherent language modeling capability. Finally, we perform instruction tuning on both ECG question answering and diagnostic report generation. Without modifying the core model, HeartLLM achieves strong performance across tasks while maintaining generalization to out-of-distribution settings. Extensive experiments demonstrate the effectiveness of each component and highlight the potential of integrating discretized ECG tokens into LLMs for medical reasoning.

翻译：心电图（ECG）在心血管疾病诊断中具有核心地位，然而现有自动化方法通常难以跨临床任务泛化，且对开放式推理的支持有限。本文提出HeartLLM——一种通过使大语言模型（LLM）能够处理12导联ECG信号以完成临床文本生成任务的新型时序（TS）与语言建模融合框架。该方法通过导联编码器与量化模块将连续ECG嵌入离散化为量化编码，随后将这些量化编码映射至扩展的ECG词汇表以形成ECG标记，使模型能够在统一框架内同时处理ECG与自然语言输入。为弥合模态差异，我们通过自回归ECG标记预测任务对模型进行预训练，使LLM能够凭借其固有的语言建模能力捕捉时序动态特征。最后，我们在ECG问答与诊断报告生成任务上进行了指令微调。在不修改核心模型架构的情况下，HeartLLM在各项任务中均取得优异性能，同时保持对分布外场景的泛化能力。大量实验验证了各模块的有效性，并凸显了将离散化ECG标记整合至LLM以进行医疗推理的潜力。