发表机构
Shandong University; University of Auckland（山东大学; 奥克兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对不规则临床时间序列问答，提出ClinPRISM框架。该框架含不规则感知多尺度编码器、时间证据蒸馏器和渐进对齐策略，通过构建训练数据，在40亿参数大语言模型主干上实现最优性能，兼具低时间序列令牌数和低推理延迟。
AI 中文摘要
在不规则临床时间序列（ICTS）上进行问答在众多医疗应用中起着关键作用。尽管近期多模态时间序列大语言模型在通用时间序列问答中展现出潜力，但在处理临床观察的稀疏性、异步性和不规则采样模式方面仍存在不足。为填补这一空白，我们提出了ClinPRISM，一种用于ICTS数据问答的经济高效多模态大语言模型推理框架。首先，设计了一个不规则感知多尺度编码器来捕捉不同时间尺度上的稀疏临床证据；接着，提出了一个时间证据蒸馏器来整合跨尺度的表示并压缩成少量与大语言模型兼容的令牌；还引入了一种渐进对齐策略。为便于训练，构建了30000个与多尺度描述配对的临床时间序列以及41000个跨11个任务的指令微调实例。使用40亿参数的大语言模型主干，ClinPRISM在留出的评估基准上实现了最优性能，仅使用16个时间序列令牌，每个问题的平均推理延迟为0.15秒。
英文摘要
Question answering (QA) over irregular clinical time series (ICTS) plays a pivotal role in a wide range of healthcare applications. Although recent multimodal time-series large language models (LLMs) have shown considerable promise in general-purpose time-series QA, they remain poorly equipped to model the sparsity, asynchrony, and irregular sampling patterns of clinical observations. To fill this gap, we propose ClinPRISM, a cost-effective multimodal LLM reasoning framework for question answering over ICTS data. First, we devise an irregularity-aware multi-scale encoder to capture sparse clinical evidence at diverse temporal scales. Then, we propose a temporal evidence distiller to integrate representations across these scales and compress them into a small number of LLM-compatible tokens. Moreover, we introduce a progressive alignment strategy that sequentially aligns the irregular trajectories with the LLM's textual embedding space. To facilitate training, we construct 30,000 clinical time series paired with multi-scale descriptions, together with 41,000 instruction-tuning instances spanning 11 tasks. Using a 4-billion-parameter LLM backbone, ClinPRISM achieves state-of-the-art performance on the held-out evaluation benchmark while using only 16 time-series tokens and achieving an average inference latency of 0.15 seconds per question.
