The widespread application of Electronic Health Records (EHR) data in the
medical field has led to early successes in disease risk prediction using deep
learning methods. These methods typically require extensive data for training
due to their large parameter sets. However, existing works do not exploit the
full potential of EHR data. A significant challenge arises from the infrequent
occurrence of many medical codes within EHR data, limiting their clinical
applicability. Current research often lacks in critical areas: 1) incorporating
disease domain knowledge; 2) heterogeneously learning disease representations
with rich meanings; 3) capturing the temporal dynamics of disease progression.
To overcome these limitations, we introduce a novel heterogeneous graph
learning model designed to assimilate disease domain knowledge and elucidate
the intricate relationships between drugs and diseases. This model innovatively
incorporates temporal data into visit-level embeddings and leverages a
time-aware transformer alongside an adaptive attention mechanism to produce
patient representations. When evaluated on two healthcare datasets, our
approach demonstrated notable enhancements in both prediction accuracy and
interpretability over existing methodologies, signifying a substantial
advancement towards personalized and proactive healthcare management.

通过利用电子健康记录 (EHR) 数据在医学领域的广泛应用，使用深度学习方法在疾病风险预测方面取得了早期成功。然而，现有研究对 EHR 数据的潜力未能充分利用，存在着许多关键问题，如融入疾病领域知识、异构学习疾病表示以及捕捉疾病进展的时间动态等。为了克服这些限制，本研究引入了一种新型的异构图学习模型，旨在融合疾病领域知识，阐明药物和疾病之间错综复杂的关系。该模型创新性地将时间数据融入到访问级嵌入中，并利用一个考虑时间的 Transformer 和自适应注意机制来生成患者表示。经过两个医疗数据集的评估，我们的方法在预测准确性和可解释性方面表现出显著提升，为个性化和主动式的医疗管理迈出了实质性的进展。

基于时间感知的异构图变换器与自适应注意力合并的健康事件预测

Time-aware Heterogeneous Graph Transformer with Adaptive Attention  Merging for Health Event Prediction

Heart diseases rank among the leading causes of global mortality,
demonstrating a crucial need for early diagnosis and intervention. Most
traditional electrocardiogram (ECG) based automated diagnosis methods are
trained at population level, neglecting the customization of personalized ECGs
to enhance individual healthcare management. A potential solution to address
this limitation is to employ digital twins to simulate symptoms of diseases in
real patients. In this paper, we present an innovative prospective learning
approach for personalized heart disease detection, which generates digital
twins of healthy individuals' anomalous ECGs and enhances the model sensitivity
to the personalized symptoms. In our approach, a vector quantized feature
separator is proposed to locate and isolate the disease symptom and normal
segments in ECG signals with ECG report guidance. Thus, the ECG digital twins
can simulate specific heart diseases used to train a personalized heart disease
detection model. Experiments demonstrate that our approach not only excels in
generating high-fidelity ECG signals but also improves personalized heart
disease detection. Moreover, our approach ensures robust privacy protection,
safeguarding patient data in model development.

基于数字孪生技术的个性化心脏病检测模型可以生成高质量的心电图信号，并改善个性化心脏病检测，在保证隐私安全的前提下有效管理患者数据。