数字健康活动早期预测的患者世界模型：能力与局限
A Patient World Model for Early Forecasting of Digital Health Campaign Outcomes: Capabilities and Limits
- IQVIA（艾昆纬）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对数字健康活动结果早期预测，提出紧凑患者世界模型，利用潜在状态与暴露条件动态联合建模转化风险，在真实数据上显著降低预测误差，并揭示因果解释的局限。
AI中文摘要：
数字直接面向消费者（DTC）健康活动通常在事后进行衡量。飞行中预测通常依赖于针对每个截止点和预测水平分别训练的独立分类器。我们将此任务视为一个动态系统问题，并构建了一个紧凑的患者世界模型。该架构为每位患者维护一个潜在状态，学习暴露条件下的状态动态，并与每周转化风险联合建模，然后向前滚动生成未来的转化曲线。我们在一个包含147,173名患者和520万人周风险的美国活动数据集上对其进行了评估。在基于记录的未来暴露进行条件化的回顾性评估中，该模型预测截至第52周的新品牌处方剩余量，从第4周截止点起相对误差为2.9%，从第8至26周截止点起相对误差为0.8%至2.6%。最强的非循环基线模型——在相同生存滚动和信息的条件下使用合并风险梯度提升模型——的相对误差为13.6%至33.1%。按预测水平分类的分类器表现明显更差。Fisher信息分析表明，在转化罕见时，应加强密集的下一次暴露监督。移除这一辅助目标会使处方量误差增加约2至14倍，而在更常见的专科就诊结果上则没有一致的不利影响。我们还评估了情景模拟。将所有未来暴露关闭后，预测转化率从0.31升至0.89，这一模式与观察性暴露数据中的选择效应一致。这一结果凸显了将暴露条件化滚动解释为因果关系的局限性。
英文摘要：
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.
