发表机构
Automation Core Inc.（自动化核心公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出将手术数字孪生中人群不良事件监测作为独立信念层，采用联邦贝叶斯协议（Gamma-Poisson后验与Rényi差分隐私），在FDA MAUDE数据上优于集中式方法，并保留制造商特定风险特征。
AI 中文摘要
学习型手术模拟器和世界模型可以推演合理的程序性未来，但它们缺乏对介入设备实际伤害患者频率的有根据估计。我们提出将人群规模的不良事件监测视为手术数字孪生的一个独立信念层，并评估一种在正式隐私保证下学习该层的联邦贝叶斯协议。每个站点持有每类Gamma-Poisson后验分布，涵盖不良事件率，且仅交换满足Rényi差分隐私的自然参数更新。我们在完整的FDA MAUDE队列（产品代码NRY）上对血栓回收导管进行基准测试：共8,617份报告，其中6,491份通过透明关键词规则被分类为五类血栓切除并发症，并分配到K=8个制造商站点。在匹配的隐私预算（ε≈2.09, δ=10⁻⁵）下，共轭协议在保留测试事件上达到-5.78的Poisson得分，而带差分隐私的FedAvg为-26.58。非私有联邦模型也优于集中式池化（+3.19对+2.93），这证明制造商特定的并发症特征是真实存在的，且联邦学习保留了这些特征。由于MAUDE缺乏手术分母，输出为相对率排序而非绝对风险，我们报告了所有隐私-效用操作点。
英文摘要
Learned surgical simulators and world models can roll out plausible procedural futures, but they carry no grounded estimate of how often interventional devices actually harm patients. We propose treating population-scale adverse-event surveillance as a distinct belief layer of the surgical digital twin, and we evaluate a federated Bayesian protocol for learning it under formal privacy guarantees. Each site holds per-class Gamma-Poisson posteriors over adverse-event rates and exchanges only Rényi-differentially-private natural-parameter updates. We benchmark on the complete FDA MAUDE cohort for thrombus-retrieval catheters (product code NRY): 8,617 reports, of which 6,491 are classified by transparent keyword rules into five thrombectomy complication classes and partitioned across $K=8$ manufacturer sites. At a matched privacy budget of $(\\varepsilon \\approx 2.09, \δ= 10^{-5})$, the conjugate protocol attains a held-out Poisson score of -5.78 per test event versus -26.58 for FedAvg with differential privacy. The non-private federated model also outperforms centralized pooling (+3.19 vs +2.93), evidence that manufacturer-specific complication profiles are real and that federation preserves them. Because MAUDE lacks procedure denominators, outputs are relative rate orderings rather than absolute risks, and we report all privacy-utility operating points.
CommentsPresented at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026) Workshop on Surgical Digital Twins (SurgTwin). 3 pages, 1 figure
