面向分词电子健康记录的联邦生成事件模型
Federated generative event models for tokenized electronic health records
- University of Chicago（芝加哥大学）
- Northwestern University Feinberg School of Medicine（西北大学费恩伯格医学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究评估了面向分词电子健康记录的联邦生成事件模型（GEMs），其跨站点性能优于LightGBM，联邦学习（FedAvg、FedAvgM）表现接近集中式训练，为解决电子健康记录模型的数据孤岛问题提供了可行方案。
AI中文摘要：
电子健康记录基础模型受限于机构数据孤岛问题，且在跨站点迁移时性能会大幅下降。我们针对来自三个独立卫生系统的122251次重症监护住院病例，对分词生成事件模型（Generative Event Models, GEMs）进行了联邦训练评估，这些病例已被统一为Common Longitudinal ICU Data Format（通用纵向ICU数据格式）。我们采用站点内、跨站点、集中式及联邦式训练配置，对模型在12项24小时后临床预测任务上的表现进行了评估。GEMs在站点内及跨站点的平均ROC-AUC值最高，且比传统监督模型更具可迁移性：其平均跨站点惩罚为ROC-AUC 0.025、PR-AUC 0.027，而LightGBM的对应值分别为0.079和0.089。联邦学习（FedAvg与FedAvgM）的表现接近集中式GEM训练的性能，多数增益可在5-10轮通信内获得。不过，多站点集中式训练与完全本地训练相比仅能带来小幅提升。当本地训练数据有限时，多站点模型最为有用，其优势会随机构数据的积累而缩小。这些发现表明，联邦GEM训练在技术上可行且能保留大部分集中式性能，但主要的开放性挑战是学习可迁移表征，以将多个卫生系统的更大规模但异质的数据转化为对目标站点的可靠收益。
英文摘要：
Electronic health record foundation models are limited by institutionally siloed data and substantial performance degradation under cross-site transfer. We evaluated federated training of tokenized generative event models (GEMs) across 122,251 intensive care hospitalizations from three independent health systems harmonized to the Common Longitudinal ICU Data Format. Models were assessed on 12 post-24-hour clinical prediction tasks using within-site, cross-site, centralized, and federated training configurations. GEMs achieved the highest mean within-site and cross-site ROC-AUC and were substantially more transportable than conventional supervised models: their average cross-site penalties were 0.025 ROC-AUC and 0.027 PR-AUC, compared with 0.079 and 0.089 for LightGBM. Federated Learning (FedAvg and FedAvgM) approached the performance of centralized GEM training, with most gains obtained within 5-10 communication rounds. However, centralized multi-site training provided only modest improvements over complete local training. Multi-site models were most useful when local training data were limited, with their advantage narrowing as institutional data accumulated. These findings show that federated GEM training is technically feasible and preserves most centralized performance, but that the main open challenge is learning transportable representations to translate larger, but heterogeneous data from multiple health systems into a reliable target-site benefit.
