Temporal Clustering with External Memory Network for Disease Progression Modeling
Temporal Clustering with External Memory Network for Disease Progression Modeling
复制标题
DOI：
10.1109/icdm51629.2021.00107
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Zicong Zhang;Changchang Yin;Ping Zhang
中科院分区：
文献类型：
--
作者：
Zicong Zhang;Changchang Yin;Ping Zhang
疾病进展建模(DPM)涉及使用数学框架来定量衡量某些疾病进展的严重程度。DPM在预测健康状态、分类疾病分期、评估患者的疾病轨迹等方面有很大的应用价值。近年来，随着电子健康记录(EHR)的广泛应用和数据驱动的机器学习方法的广泛应用，DPM受到了越来越多的关注，但仍然存在两大挑战：(1)由于EHR中存在的不规则性、异构性和长期依赖性，大多数现有的DPM方法可能无法提供全面的患者表征。(Ii)EHR中的许多记录可能与目标疾病无关。大多数现有的模型学习自动关注相关信息，而不是显式地捕获与目标相关的事件，这可能会使学习的模型处于次优状态。为了解决这两个问题，我们提出了具有外部记忆网络的时间聚类(TC-EMNet)用于DPM，它将具有相似轨迹的患者分组以形成疾病簇/阶段。TC-EMNet使用变分自动编码器(VAE)从输入数据中捕获内部复杂性，并利用外部存储工作来捕获长期距离信息，这两者都有助于生成全面的患者健康状态。最后，采用k-均值算法对提取出的综合患者表示进行聚类，以捕捉疾病进展。在两个真实数据集上的实验表明，我们的模型显示出与最先进的方法相比具有竞争力的聚类性能，并能够识别出具有临床意义的聚类。患者描述的可视化表明，所提出的模型可以生成比基线更好的患者健康状态。
Disease progression modeling (DPM) involves using mathematical frameworks to quantitatively measure the severity of how certain disease progresses. DPM is useful in many ways such as predicting health state, categorizing disease stages, and assessing patients’ disease trajectory, etc. Recently, with the wider availability of electronic health records (EHR) and the broad application of data-driven machine learning methods, DPM has attracted much attention yet remains two major challenges: (i) Due to the existence of irregularity, heterogeneity, and long-term dependency in EHRs, most existing DPM methods might not be able to provide comprehensive patient representations. (ii) Lots of records in EHRs might be irrelevant to the target disease. Most existing models learn to automatically focus on the relevant information instead of explicitly capture the target-relevant events, which might make the learned model suboptimal. To address these two issues, we propose Temporal Clustering with External Memory Network (TC-EMNet) for DPM that groups patients with similar trajectories to form disease clusters/stages. TC-EMNet uses a variational autoencoder (VAE) to capture internal complexity from the input data and utilizes an external memory work to capture long-term distance information, both of which are helpful for producing comprehensive patient health states. Last but not least, the k-means algorithm is adopted to cluster the extracted comprehensive patient representation to capture disease progression. Experiments on two real-world datasets show that our model demonstrates competitive clustering performance against state-of-the-art methods and is able to identify clinically meaningful clusters. The visualization of the patient representations shows that the proposed model can generate better patient health states than the baselines.