We introduce Prior-Fitted Functional Flows, a generative foundation model for pharmacokinetics that enables zero-shot population synthesis and individual forecasting without manual parameter tuning. We learn functional vector fields, explicitly conditioned on the sparse, irregular data of an entire study population. This enables the generation of coherent virtual cohorts as well as forecasting of partially observed patient trajectories with calibrated uncertainty. We construct a new open-access literature corpus to inform our priors, and demonstrate state-of-the-art predictive accuracy on extensive real-world datasets.

翻译：我们提出了Prior-Fitted Functional Flow，一种用于药代动力学的生成式基础模型，能够实现零样本群体合成和个体预测，无需手动参数调整。我们学习面向功能的向量场，该场显式地以整个研究群体的稀疏且不规则数据为条件。这使我们能够生成连贯的虚拟队列，以及以校准后的不确定性预测部分观测到的患者轨迹。我们构建了一个新的开放获取文献语料库来为我们的先验知识提供信息，并在大量真实世界数据集上展示了最先进的预测准确性。