Xia Meng, Wilson Jonathan, Goldstein Benjamin, Henao Ricardo
Department of Electrical and Computer Engineering, Duke University, Durham, US.
Department of Biostatistics and Bioinformatics, Duke University, Durham, US.
Proc Mach Learn Res. 2024 Jul;235:54156-54177.
The use of machine learning models to predict clinical outcomes from (longitudinal) electronic health record (EHR) data is becoming increasingly popular due to advances in deep architectures, representation learning, and the growing availability of large EHR datasets. Existing models generally assume access to the same data sources during both training and inference stages. However, this assumption is often challenged by the fact that real-world clinical datasets originate from various data sources (with distinct sets of covariates), which though can be available for training (in a research or retrospective setting), are more realistically only partially available (a subset of such sets) for inference when deployed. So motivated, we introduce Contrastive Learning for clinical Outcome Prediction with Partial data Sources (CLOPPS), that trains encoders to capture information across different data sources and then leverages them to build classifiers restricting access to a single data source. This approach can be used with existing cross-sectional or longitudinal outcome classification models. We present experiments on two real-world datasets demonstrating that CLOPPS consistently outperforms strong baselines in several practical scenarios.
由于深度架构、表示学习的进展以及大型电子健康记录（EHR）数据集的日益普及，使用机器学习模型从（纵向）EHR数据预测临床结果正变得越来越流行。现有模型通常假设在训练和推理阶段都能访问相同的数据源。然而，这一假设常常受到现实世界临床数据集源自各种数据源（具有不同的协变量集）这一事实的挑战，这些数据源虽然在训练时（在研究或回顾性设置中）可用，但在实际部署进行推理时，更现实的情况是只能部分可用（这些数据集的一个子集）。受此启发，我们引入了用于部分数据源临床结果预测的对比学习（CLOPPS），它训练编码器以跨不同数据源捕获信息，然后利用这些信息构建限制访问单个数据源的分类器。这种方法可以与现有的横断面或纵向结果分类模型一起使用。我们在两个真实世界数据集上进行了实验，结果表明CLOPPS在几种实际场景中始终优于强大的基线模型。
