Predicting next visit diagnosis using Electronic Health Records (EHR) is an essential task in healthcare, critical for devising proactive future plans for both healthcare providers and patients. Nonetheless, many preceding studies have not sufficiently addressed the heterogeneous and hierarchical characteristics inherent in EHR data, inevitably leading to sub-optimal performance. To this end, we propose NECHO, a novel medical code-centric multimodal contrastive EHR learning framework with hierarchical regularisation. First, we integrate multifaceted information encompassing medical codes, demographics, and clinical notes using a tailored network design and a pair of bimodal contrastive losses, all of which pivot around a medical code representation. We also regularise modality-specific encoders using a parental level information in medical ontology to learn hierarchical structure of EHR data. A series of experiments on MIMIC-III data demonstrates effectiveness of our approach.

翻译：利用电子健康记录（EHR）预测下次就诊诊断是医疗领域的关键任务，对于医疗提供者和患者制定前瞻性计划至关重要。然而，许多现有研究未能充分处理EHR数据中固有的异质性和层次性特征，导致模型性能欠佳。为此，我们提出NECHO——一种新颖的以医疗代码为中心的多模态对比EHR学习框架，并引入分层正则化。首先，我们通过定制化网络设计和一对双模态对比损失，整合医疗代码、人口统计学信息和临床笔记等多维度信息，所有模块均围绕医疗代码表示展开。同时，利用医学本体中的父级层次信息对模态特定编码器进行正则化，以学习EHR数据的分层结构。基于MIMIC-III数据集的一系列实验验证了本方法的有效性。