发表机构
TUM University Hospital and Technical University of Munich (TUM); Institute for Diagnostic and Interventional Radiology, TUM University Hospital; Munich Center for Machine Learning (MCML); Institute for Diagnostic and Interventional Neuroradiology, TUM University Hospital; University Medical Center Hamburg-Eppendorf（慕尼黑工业大学医院与慕尼黑工业大学; 慕尼黑工业大学医院诊断与介入放射学研究所; 慕尼黑机器学习中心; 慕尼黑工业大学医院诊断与介入神经放射学研究所; 汉堡埃彭多夫大学医学中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
NOAH是一种时间感知、任务无关的生成式Transformer模型，通过双向时间整合和变分潜在空间，在MIMIC数据上学习完整患者旅程，支持预测、零样本分类和反事实模拟。
AI 中文摘要
医疗保健的数字化在患者一生中产生了海量、纵向且多模态的病历记录，然而，充分利用这些数据来表示和预测患者状态轨迹仍是一个关键挑战。当前的AI模型往往难以捕捉真实世界多模态患者数据中复杂、不规则的时间动态和固有的随机性。现有的用于建模纵向患者记录的AI方法主要具有判别性，局限于少数模态，受限于封闭的分类词汇表，将时间视为单调的归纳偏置，或者在预测未来患者状态方面能力有限。我们提出了NOAH，一种时间感知、任务无关的生成式Transformer模型，用于表示和预测完整的患者多模态旅程。NOAH具有新颖的双向时间整合和变分潜在空间，以捕捉患者状态的连续演变和临床轨迹的随机性。NOAH基于MIMIC数据集系列中来自299,000名患者的431,000次医院就诊的超过5.59亿个临床事件构建，原生处理医学图像、时间序列和数值信号、分类事件以及结构化和非结构化的临床记录。NOAH是该领域首个真正全面的生成式模型，支持具有可选时间控制的自回归预测、零样本分类和反事实干预模拟。它生成信息丰富且具有预测性的患者状态表示，在临床结果探查、15个ICD章节和29种合并症以及事件时间预测方面表现出强大的性能。NOAH无缝处理多种模态和复杂的时间动态，为个性化临床护理和数字医学中的智能预测系统提供了通用、任务无关、可扩展的基础。
英文摘要
The digitization of healthcare has generated vast, longitudinal, and multimodal patient records over a lifetime, yet fully exploiting these data to represent and predict patient state trajectories remains a critical challenge. Current AI models often struggle to capture the complex, irregular temporal dynamics and inherent stochasticity of real-world multimodal patient data. Existing AI approaches for modeling longitudinal patient records are predominantly discriminative, limited to a few modalities, constrained by closed categorical vocabularies, treating time as a monotonic inductive bias, or they are limited in forecasting future patient states. We introduce NOAH, a time-aware, task-agnostic, generative transformer model representing and forecasting the full multimodal patient journey. NOAH features a novel bidirectional time integration and a variational latent space to capture the continuous evolution of patient states and the stochasticity of clinical trajectories. Built from over 559 million clinical events from 431,000 hospital visits of 299,000 patients across the MIMIC dataset family, NOAH natively processes medical images, time-series and numeric signals, categorical events, as well as structured and unstructured clinical records. NOAH is the first truly holistic generative model in its field, enabling autoregressive forecasting with optional time control, zero-shot classification, and counterfactual intervention simulation. It generates highly informative and predictive patient state representations that demonstrate strong performance in probing for clinical outcomes, 15 ICD chapters, and 29 comorbidities, as well as in time-to-event prediction. Seamlessly handling diverse modalities and complex temporal dynamics, NOAH provides a versatile, task-agnostic, scalable foundation for intelligent predictive systems in personalized clinical care and digital medicine.
