AUTOMED: Automated Medical Risk Predictive Modeling on Electronic Health Records
AUTOMED: Automated Medical Risk Predictive Modeling on Electronic Health Records
复制标题
DOI：
10.1109/bibm55620.2022.9995209
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Suhan Cui;Jiaqi Wang;Xinning Gui;Ting Wang;Fenglong Ma
中科院分区：
文献类型：
--
作者：
Suhan Cui;Jiaqi Wang;Xinning Gui;Ting Wang;Fenglong Ma
电子健康记录（EHR）已被广泛应用于医疗领域的各种任务，如风险预测建模，其目的是通过分析患者的历史EHR来预测进一步的健康状况。现有的工作主要集中在使用先进的深度学习技术对EHR数据的顺序和时间特征进行建模。然而，这些模型的网络结构都是基于专家的先验知识手动设计的，这在很大程度上阻碍了非专家探索这项任务。为了解决这个问题，在本文中，我们提出了一种新的自动化风险预测模型AUTOMED自动搜索最佳的模型架构建模复杂的EHR数据和提高风险预测任务的性能。特别是，我们遵循神经架构搜索的思想，设计了一个包含三个独立的可搜索模块的搜索空间。其中两个分别用于分析EHR数据的时序和时序特征。第三种是自动将两种功能融合在一起。除了这三个模块，AUTOMED还包含嵌入模块和预测模块。所有这三个可搜索的模块在搜索阶段联合优化，以获得最佳的模型架构。以这种方式，模型设计可以自动实现，几乎没有人为干预。在三个真实世界数据集上的实验结果表明，AUTOMED在PR-AUC，F1和Cohen's Kappa方面优于最先进的基线。此外，消融研究表明，AUTOMED可以获得合理的模型架构，并为未来的风险预测模型设计提供有用的见解。
Electronic health records (EHR) have been widely applied to various tasks in the medical domain such as risk predictive modeling, which aims to predict further health conditions by analyzing patients’ historical EHR. Existing work mainly focuses on modeling the sequential and temporal characteristics of EHR data with advanced deep learning techniques. However, the network architectures of these models are all manually designed based on experts’ prior knowledge, which largely impedes non-experts from exploring this task. To address this issue, in this paper, we propose a novel automated risk prediction model named AUTOMED to automatically search the optimal model architecture for modeling the complex EHR data and improving the performance of the risk prediction task. In particular, we follow the idea of neural architecture search to design a search space that contains three separate searchable modules. Two of them are used for analyzing sequential and temporal features of EHR data, respectively. The third is to automatically fuse both features together. Besides these three modules, AUTOMED contains an embedding module and a prediction module. All the three searchable modules are jointly optimized in the search stage to derive the optimal model architecture. In such a way, the model design can be automatically achieved with few human interventions. Experimental results on three real-world datasets show that AUTOMED outperforms state-of-the-art baselines in terms of PR-AUC, F1, and Cohen’s Kappa. Moreover, the ablation study shows that AUTOMED can obtain reasonable model architectures and offer useful insights to the future risk prediction model design.