发表机构
University of California, Berkeley; University of California, San Francisco; Southern Methodist University（加州大学伯克利分校; 加州大学旧金山分校; 南卫理公会大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出P$^3$审计框架和Cancer JEPA模型，用于评估医学世界模型中的个性化预测，区分输入使用与患者特定预测价值，并验证了患者历史与病灶占用图对预测误差的降低作用。
AI 中文摘要
纵向模型预测患者影像状态的演变，但准确性并不能表明患者的观察轨迹是否驱动了预测。人群平均预测可能有用，但不能确立患者特定的世界模型主张。我们引入患者、地点、先验（P$^3$），这是一种审计，询问预测是否受益于患者的纵向影像历史（患者），是否受益于患者匹配的外部提供的空间支持（地点），以及在匹配的支持和上下文下，是否获得超出人群平均预测的预测价值（先验）。我们还提出了Cancer JEPA，一种单步模型，用于预测新辅助治疗期间未来乳腺动态对比增强MRI检查的冻结表示。它在患者条件的低复杂度降秩回归基线之上，添加了一个病灶约束的神经校正，该校正通过基于遮挡的潜在目标进行训练。这种分解允许对冻结模型进行事后P$^3$审计。在先前用于开发的验证队列中，当神经校正接收患者自身的历史而非其他患者的历史，以及患者匹配的病灶占用图而非替代图时，预测误差较低。然而，将患者历史计算出的校正与人群平均神经校正进行比较的描述性95%区间包含零。因此，P$^3$将输入使用与超出人群水平模式的患者特定预测价值的证据区分开来。
英文摘要
Longitudinal models forecast how a patient's imaging state evolves, but accuracy does not show whether the patient's observed trajectory drives the prediction. A population-average forecast may be useful but cannot establish a patient-specific world-model claim. We introduce Patient, Place, Prior (P$^3$), an audit asking whether a forecast benefits from the patient's longitudinal imaging history (Patient), benefits from patient-matched externally supplied spatial support (Place), and gains predictive value beyond a population-average prediction under matched support and context (Prior). We also propose Cancer JEPA, a one-step model that forecasts frozen representations of future breast dynamic contrast-enhanced MRI examinations during neoadjuvant therapy. It adds a lesion-constrained neural correction, trained with an occlusion-based latent objective, to a patient-conditioned low-complexity reduced-rank regression baseline. This factorization permits a post-hoc P$^3$ audit of the frozen model. In a validation cohort previously used in development, forecast error is lower when the neural correction receives the patient's history rather than another patient's and patient-matched lesion occupancy maps rather than substituted maps. However, the descriptive 95% interval comparing the correction computed from patient history with the population-average neural correction includes zero. P$^3$ thus separates input use from evidence of patient-specific predictive value beyond a population-level pattern.
Comments12 pages, 1 figure, 2 tables
