In this study, we introduce ExBEHRT, an extended version of BEHRT (BERT applied to electronic health records), and apply different algorithms to interpret its results. While BEHRT considers only diagnoses and patient age, we extend the feature space to several multimodal records, namely demographics, clinical characteristics, vital signs, smoking status, diagnoses, procedures, medications, and laboratory tests, by applying a novel method to unify the frequencies and temporal dimensions of the different features. We show that additional features significantly improve model performance for various downstream tasks in different diseases. To ensure robustness, we interpret model predictions using an adaptation of expected gradients, which has not been previously applied to transformers with EHR data and provides more granular interpretations than previous approaches such as feature and token importances. Furthermore, by clustering the model representations of oncology patients, we show that the model has an implicit understanding of the disease and is able to classify patients with the same cancer type into different risk groups. Given the additional features and interpretability, ExBEHRT can help make informed decisions about disease trajectories, diagnoses, and risk factors of various diseases.

翻译：在本研究中，我们提出了ExBEHRT——一种BEHRT（将BERT应用于电子健康记录）的扩展版本，并应用多种算法解释其结果。BEHRT仅考虑诊断结果与患者年龄，而我们的模型通过一种新颖方法统一不同特征的频率与时间维度，将特征空间扩展至多种模态记录，包括人口学特征、临床特征、生命体征、吸烟状况、诊断结果、手术操作、用药情况及实验室检测数据。实验表明，额外特征显著提升了模型在多类疾病下游任务中的性能。为确保鲁棒性，我们采用经适应性改造的期望梯度法（该方法此前未应用于基于电子健康记录的Transformer模型，且能提供比特征重要性、词元重要性等传统方法更细粒度的解释）对模型预测进行可解释性分析。此外，通过对肿瘤患者模型表征进行聚类分析，发现模型具备对疾病的隐含理解能力，并能将相同癌症类型的患者划分为不同风险组。得益于扩展的特征体系与可解释能力，ExBEHRT可为多种疾病的病程轨迹、诊断结果及风险因素提供辅助决策支持。