GRAM: Graph-based Attention Model for Healthcare Representation Learning.
GRAM: Graph-based Attention Model for Healthcare Representation Learning.
复制标题
DOI：
10.1145/3097983.3098126
复制
发表时间：
2017-08
期刊：
影响因子：
--
通讯作者：
Sun J
中科院分区：
文献类型：
--
作者：
Choi E;Bahadori MT;Song L;Stewart WF;Sun J
数据不足：在医疗保健预测建模中，样本量通常不足以让深度学习方法获得令人满意的结果。解释：通过深度学习方法学习的表示应该与医学知识保持一致。深度学习方法在医疗保健领域的预测建模方面表现出了良好的性能，但仍然存在两个重要的挑战：为了解决这些挑战，我们提出了基于GRaph的注意力模型（Attention Model，简称EHR），该模型利用医学本体固有的分层信息补充电子健康记录（EHR）。基于数据量和本体结构，语义表示的医学概念的组合，其祖先在本体中通过注意力机制。我们比较了两个连续诊断预测任务和一个心力衰竭预测任务中的递归神经网络（RNN）的预测性能（即准确性，数据需求，可解释性）。与基本RNN相比，RNN在预测训练数据中很少观察到的疾病方面的准确率提高了10%，并且使用数量级更少的训练数据预测心力衰竭的ROC曲线下面积提高了3%。此外，与其他方法不同的是，通过XML学习的医学概念表示与医学本体很好地对齐。最后，当低层概念的数据不足时，神经网络通过自适应地泛化到高层概念来表现出直观的注意行为。
Data insufficiency: Often in healthcare predictive modeling, the sample size is insufficient for deep learning methods to achieve satisfactory results. Interpretation: The representations learned by deep learning methods should align with medical knowledge. Deep learning methods exhibit promising performance for predictive modeling in healthcare, but two important challenges remain: To address these challenges, we propose GRaph-based Attention Model (GRAM) that supplements electronic health records (EHR) with hierarchical information inherent to medical ontologies. Based on the data volume and the ontology structure, GRAM represents a medical concept as a combination of its ancestors in the ontology via an attention mechanism. We compared predictive performance (i.e. accuracy, data needs, interpretability) of GRAM to various methods including the recurrent neural network (RNN) in two sequential diagnoses prediction tasks and one heart failure prediction task. Compared to the basic RNN, GRAM achieved 10% higher accuracy for predicting diseases rarely observed in the training data and 3% improved area under the ROC curve for predicting heart failure using an order of magnitude less training data. Additionally, unlike other methods, the medical concept representations learned by GRAM are well aligned with the medical ontology. Finally, GRAM exhibits intuitive attention behaviors by adaptively generalizing to higher level concepts when facing data insufficiency at the lower level concepts.