arXiv：cs.LG· Xingrui Gu, Hanxue Gu, Yuxiang Zhang, Yang Yang·· 4 小时前AI 评分32
P³ 框架：医学世界模型中的个性化到底算什么？
Patient, Place, Prior (P$^3$): What Counts as Personalization in Medical World Models?
AI 导读
研究提出 Patient, Place, Prior（P³）审计框架，检验预测是否真正受益于患者纵向影像史、患者匹配的外部空间支持，以及能否超越群体平均预测。配套的 Cancer JEPA 一步预测新辅助治疗中乳腺 DCE-MRI 的冻结表征，以患者条件低复杂度降秩回归为基线，叠加病灶约束的神经校正并用遮挡式潜空间目标训练。
正文
Abstract: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.
| Comments: | 12 pages, 1 figure, 2 tables |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.09194 [cs.LG] |
| (or arXiv:2610.09194v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09194 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hanxue Gu [view email]
[v1]
Tue, 6 Oct 2026 22:45:39 UTC (331 KB)
来源：arXiv：cs.LG · arxiv.org