Wanyan Tingyi, Vaid Akhil, De Freitas Jessica K, Somani Sulaiman, Miotto Riccardo, Nadkarni Girish N, Azad Ariful, Ding Ying, Glicksberg Benjamin S
Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY 10029 USA, and the School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN 47405 USA , and also with the School of Information, University of Texas at Austin, Austin, TX 78712 USA.
Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY 10029 USA.
IEEE Trans Big Data. 2021 Mar;7(1):38-44. doi: 10.1109/tbdata.2020.3048644. Epub 2020 Dec 31.
Traditional Machine Learning (ML) models have had limited success in predicting Coronoavirus-19 (COVID-19) outcomes using Electronic Health Record (EHR) data partially due to not effectively capturing the inter-connectivity patterns between various data modalities. In this work, we propose a novel framework that utilizes relational learning based on a heterogeneous graph model (HGM) for predicting mortality at different time windows in COVID-19 patients within the intensive care unit (ICU). We utilize the EHRs of one of the largest and most diverse patient populations across five hospitals in major health system in New York City. In our model, we use an LSTM for processing time varying patient data and apply our proposed relational learning strategy in the final output layer along with other static features. Here, we replace the traditional softmax layer with a Skip-Gram relational learning strategy to compare the similarity between a patient and outcome embedding representation. We demonstrate that the construction of a HGM can robustly learn the patterns classifying patient representations of outcomes through leveraging patterns within the embeddings of similar patients. Our experimental results show that our relational learning-based HGM model achieves higher area under the receiver operating characteristic curve (auROC) than both comparator models in all prediction time windows, with dramatic improvements to recall.
传统机器学习（ML）模型在利用电子健康记录（EHR）数据预测冠状病毒病-19（COVID-19）结果方面取得的成功有限，部分原因是未能有效捕捉各种数据模态之间的相互连接模式。在这项工作中，我们提出了一种新颖的框架，该框架利用基于异构图模型（HGM）的关系学习来预测重症监护病房（ICU）中COVID-19患者在不同时间窗口的死亡率。我们利用了纽约市一个主要医疗系统中五家医院最大且最多样化的患者群体之一的电子健康记录。在我们的模型中，我们使用长短期记忆网络（LSTM）来处理随时间变化的患者数据，并在最终输出层应用我们提出的关系学习策略以及其他静态特征。在这里，我们用跳字（Skip-Gram）关系学习策略取代传统的softmax层，以比较患者与结果嵌入表示之间的相似性。我们证明，通过利用相似患者嵌入中的模式，异构图模型的构建可以稳健地学习对患者结果表示进行分类的模式。我们的实验结果表明，在所有预测时间窗口中，我们基于关系学习的异构图模型在受试者工作特征曲线下面积（auROC）方面均高于两个比较模型，召回率也有显著提高。
