Clinical AI systems frequently suffer performance decay post-deployment due to temporal data shifts, such as evolving populations, diagnostic coding updates (e.g., ICD-9 to ICD-10), and systemic shocks like the COVID-19 pandemic. Addressing this ``aging'' effect via frequent retraining is often impractical due to computational costs and privacy constraints. To overcome these hurdles, we introduce Adversarial Drift-Aware Predictive Transfer (ADAPT), a novel framework designed to confer durability against temporal drift with minimal retraining. ADAPT innovatively constructs an uncertainty set of plausible future models by combining historical source models and limited current data. By optimizing worst-case performance over this set, it balances current accuracy with robustness against degradation due to future drifts. Crucially, ADAPT requires only summary-level model estimators from historical periods, preserving data privacy and ensuring operational simplicity. Validated on longitudinal suicide risk prediction using electronic health records from Mass General Brigham (2005--2021) and Duke University Health Systems, ADAPT demonstrated superior stability across coding transitions and pandemic-induced shifts. By minimizing annual performance decay without labeling or retraining future data, ADAPT offers a scalable pathway for sustaining reliable AI in high-stakes healthcare environments.

翻译：临床人工智能系统常因时间性数据漂移（如人群演变、诊断编码更新（例如从ICD-9到ICD-10）以及COVID-19大流行等系统性冲击）而在部署后出现性能衰退。由于计算成本与隐私限制，通过频繁再训练来应对这种“老化”效应往往不切实际。为克服这些障碍，我们提出了对抗性漂移感知预测迁移（ADAPT）——一种旨在以最小化再训练实现时间漂移耐久性的新型框架。ADAPT通过结合历史源模型与有限的当前数据，创新性地构建了未来可能模型的集合。通过优化该集合上的最差性能，它在当前准确性与抵御未来漂移导致的性能退化之间取得平衡。关键的是，ADAPT仅需历史周期的汇总级模型估计量，从而保护数据隐私并确保操作简便性。基于麻省总医院布里格姆（2005–2021年）及杜克大学医疗系统的电子健康记录进行纵向自杀风险预测验证，ADAPT在编码转换与疫情引发的数据漂移中均表现出卓越的稳定性。通过无需标注或再训练未来数据即可最小化年度性能衰减，ADAPT为在高风险医疗环境中维持可靠人工智能提供了可扩展的路径。