AI 中文总结
提出ReCoGen两阶段框架，将多模态条件表征与生成分离，在三个生理基准的16项任务中超越6种生成器，可合成缺失生理信号以实现低侵入性临床监测。
AI 中文摘要
连续生理时间序列是现代临床监测的基础，但许多最具信息量的信号具有侵入性、成本高昂，或特定患者无法获取。条件生成技术可作为解决方案：可从同步记录的信号和常规临床变量中合成缺失的信号。然而，现有生成器围绕单一条件模态构建，在处理实际场景中异质、不规则缺失的时变信号与静态协变量混合数据时性能下降。我们提出ReCoGen（Represent Conditions, then Generate，即先表征条件再生成），这是一个将多模态条件表征与目标生成分离的两阶段框架。第一阶段为每个模态训练一个掩码自编码器，将每个时变条件提炼为紧凑且耐受缺失的令牌序列；第二阶段训练一个流匹配生成器，将这些令牌与静态条件融合以合成目标信号。在三个生理基准测试中，包括AI-READI数据集的连续血糖监测、MIMIC-III和MIMIC-IV数据集的动脉血压生成，ReCoGen在全部16个（数据集、任务、指标）设置中均取得最佳下游效用，超越6种代表性条件生成器；在其中13个设置中，其效用也达到或超过真实信号的效用，我们将该参考视为近似锚点而非上限。消融实验表明，性能提升源于条件路径：对冻结的各模态编码器的可学习交叉注意力，以及静态条件的双令牌加AdaLN路由。ReCoGen因此将常规采集的信号转化为侵入性或不可获取信号的有效替代，推动侵入性更低、成本更低的连续临床监测。
英文摘要
Continuous physiological time series underpin modern clinical monitoring, yet many of the most informative signals are invasive, expensive, or simply unavailable for a given patient. Conditional generation offers a remedy: an absent signal can be synthesized from co-recorded signals and routine clinical variables. Existing generators, however, are built around a single conditioning modality and degrade when forced to handle the heterogeneous, irregularly missing mix of time-variant signals and static covariates seen in practice. We propose ReCoGen (Represent Conditions, then Generate), a two-stage framework that decouples multimodal condition representation from target generation. Stage I trains one masked autoencoder per modality, distilling each time-variant condition into a compact and missingness-tolerant token sequence. Stage II trains a flow-matching generator that fuses these tokens with static conditions to synthesize the target signal. Across three physiological benchmarks, including continuous glucose monitoring on AI-READI and arterial blood pressure generation on MIMIC-III and MIMIC-IV, ReCoGen attains the best downstream utility on all sixteen (dataset, task, metric) settings, surpassing six representative conditional generators; on thirteen of them its utility also reaches or exceeds the utility measured on the real signal, a reference we read as an approximate anchor rather than a ceiling. Ablations trace the gains to the conditioning path: learnable cross-attention over the frozen per-modality encoders, and a dual token-plus-AdaLN route for the static conditions. ReCoGen thus turns routinely collected signals into informative surrogates for invasive or unavailable ones, a step toward less invasive, lower-cost continuous clinical monitoring.
Comments17 pages, 5 figures
