Foundation models are transforming artificial intelligence (AI) in healthcare by providing modular components adaptable for various downstream tasks, making AI development more scalable and cost-effective. Foundation models for structured electronic health records (EHR), trained on coded medical records from millions of patients, demonstrated benefits including increased performance with fewer training labels, and improved robustness to distribution shifts. However, questions remain on the feasibility of sharing these models across hospitals and their performance in local tasks. This multi-center study examined the adaptability of a publicly accessible structured EHR foundation model (FM_SM), trained on 2.57 M patient records from Stanford Medicine. Experiments used EHR data from The Hospital for Sick Children (SickKids) and Medical Information Mart for Intensive Care (MIMIC-IV). We assessed both adaptability via continued pretraining on local data, and task adaptability compared to baselines of locally training models from scratch, including a local foundation model. Evaluations on 8 clinical prediction tasks showed that adapting the off-the-shelf FM_SM matched the performance of gradient boosting machines (GBM) locally trained on all data while providing a 13% improvement in settings with few task-specific training labels. Continued pretraining on local data showed FM_SM required fewer than 1% of training examples to match the fully trained GBM’s performance, and was 60 to 90% more sample-efficient than training local foundation models from scratch. Our findings demonstrate that adapting EHR foundation models across hospitals provides improved prediction performance at less cost, underscoring the utility of base foundation models as modular components to streamline the development of healthcare AI.

基础模型通过提供适用于各种下游任务的模块化组件，正在改变医疗保健领域的人工智能 (AI)，使 AI 开发更具可扩展性和成本效益。结构化电子健康记录 (EHR) 的基础模型经过数百万患者的编码医疗记录的训练，证明了其好处，包括通过更少的训练标签提高性能，以及提高对分布变化的鲁棒性。然而，在医院之间共享这些模型的可行性及其在本地任务中的表现仍然存在疑问。这项多中心研究检验了可公开访问的结构化 EHR 基础模型 (FM _SM ) 的适应性，该模型基于斯坦福大学医学院的 257 万条患者记录进行了训练。实验使用来自病童医院 (SickKids) 和重症监护医疗信息集市 (MIMIC-IV) 的 EHR 数据。我们通过对本地数据的持续预训练来评估适应性，并与从头开始的本地训练模型的基线（包括本地基础模型）相比来评估任务适应性。对 8 项临床预测任务的评估表明，采用现成的 FM _SM与在所有数据上进行本地训练的梯度增强机 (GBM) 的性能相匹配，同时在几乎没有特定于任务的训练标签的设置中提供了 13% 的改进。对本地数据的持续预训练表明，FM _SM需要不到 1% 的训练样本来匹配经过充分训练的 GBM 的性能，并且样本效率比从头开始训练本地基础模型高 60% 到 90%。 我们的研究结果表明，跨医院调整 EHR 基础模型可以以更低的成本提高预测性能，强调了基础基础模型作为模块化组件的实用性，可以简化医疗保健人工智能的开发。