患者世界模型：第4周即可预测全年健康广告转化量
A Patient World Model for Early Forecasting of Digital Health Campaign Outcomes: Capabilities and Limits
广告效果不用等投放结束，这篇论文第4周就能把全年处方量预测误差压到2.9%，梯度提升基线是13%起步。
这篇 arXiv 论文把数字直销（DTC）健康广告的效果预测当作动态系统问题，为每位患者维护一个潜状态，联合学习曝光条件下的状态转移与每周转化风险。在包含 147,173 名患者、520 万风险人周的美国广告数据集上，模型从第 4 周截点预测到第 52 周的新品牌处方量，相对误差仅 2.9%，第 8–26 周截点为 0.8–2.6%。同等信息下的 pooled-hazard 梯度提升基线相对误差为 13.6–33.1%，逐时点分类器表现更差。消融实验显示，去掉受 Fisher 信息分析启发的下一次曝光密集监督目标后，处方量误差扩大约 2–14 倍。情景模拟中关闭全部未来曝光，预测转化率反而从 0.31 升到 0.89，作者据此指出曝光条件化的预测不能当作因果解释。
A Patient World Model for Early Forecasting of Digital Health Campaign Outcomes: Capabilities and Limits
Digital direct-to-consumer (DTC) health campaigns are usually measured after the fact. In-flight forecasting commonly relies on a separate classifier for every cutoff and horizon. We treat this task as a dynamic-system problem and build a compact patient world model. The architecture maintains a latent state per patient, learns exposure-conditioned state dynamics jointly with a weekly conversion hazard, and rolls forward into future conversion curves. We evaluate it on a US campaign dataset with 147{,}173 patients and 5.2 million at-risk person-weeks. In a retrospective evaluation conditioned on recorded future exposures, the model forecasts the remaining new-to-brand prescription volume through week 52 with a relative error of 2.9\% from a week-4 cutoff and 0.8--2.6\% from cutoffs at weeks 8--26. The strongest non-recurrent baseline, a pooled-hazard gradient boosting model given the same survival rollout and information, has relative errors of 13.6--33.1\%. Per-horizon classifiers perform substantially worse. A Fisher-information analysis motivates dense next-exposure supervision when conversions are rare. Removing this auxiliary objective increases prescription-volume error by approximately $2$--$14\times$, while providing no consistent disadvantage on the more common specialist-visit outcome. We also evaluate scenario simulation. Switching all future exposure off raises predicted conversion from 0.31 to 0.89, a pattern consistent with selection effects in observational exposure data. This result highlights the limits of interpreting exposure-conditioned rollouts causally.
