arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1602.02685cs.LGcs.AIcs.NE
收藏

利用循环神经网络结合静态和动态信息预测临床事件

Predicting Clinical Events by Combining Static and Dynamic Information Using Recurrent Neural Networks

Siemens AG(西门子股份公司);Ludwig Maximilian University of Munich(慕尼黑路德维希-马克西米利安大学)

Cristóbal Esteban, Oliver Staeck, Yinchong Yang, Volker Tresp

摘要:

在临床数据集中,我们经常发现静态信息(例如患者性别,血型等)。与在多次医院访问期间记录的数据序列(例如,处方的药物、执行的测试等)相结合。循环神经网络(RNN)已被证明在机器学习的许多领域中对数据序列建模非常成功。在这项工作中,我们提出了一种基于RNN的方法,专门为临床领域设计,结合静态和动态信息来预测未来事件。我们使用柏林Charité医院收集的数据库,该数据库包含有关接受肾移植患者的完整信息。移植后可能发生三个主要终点:肾排斥反应、肾功能丧失和患者死亡。我们的目标是根据每位患者的电子健康记录中记录的信息,预测在每次就诊后的6个月或12个月内是否会发生任何这些终点。我们比较了我们为此工作开发的不同类型的RNN,以及基于前馈神经网络和逻辑回归模型的模型。我们发现,我们基于门控递归单元开发的RNN为这项任务提供了最佳性能。我们还将相同的模型用于第二个任务,即,下一个事件的预测,并发现在这里的模型的基础上前馈神经网络优于其他模型。我们的假设是,长期依赖性在这项任务中并不相关。

英文摘要:

In clinical data sets we often find static information (e.g. patient gender, blood type, etc.) combined with sequences of data that are recorded during multiple hospital visits (e.g. medications prescribed, tests performed, etc.). Recurrent Neural Networks (RNNs) have proven to be very successful for modelling sequences of data in many areas of Machine Learning. In this work we present an approach based on RNNs, specifically designed for the clinical domain, that combines static and dynamic information in order to predict future events. We work with a database collected in the Charité Hospital in Berlin that contains complete information concerning patients that underwent a kidney transplantation. After the transplantation three main endpoints can occur: rejection of the kidney, loss of the kidney and death of the patient. Our goal is to predict, based on information recorded in the Electronic Health Record of each patient, whether any of those endpoints will occur within the next six or twelve months after each visit to the clinic. We compared different types of RNNs that we developed for this work, with a model based on a Feedforward Neural Network and a Logistic Regression model. We found that the RNN that we developed based on Gated Recurrent Units provides the best performance for this task. We also used the same models for a second task, i.e., next event prediction, and found that here the model based on a Feedforward Neural Network outperformed the other models. Our hypothesis is that long-term dependencies are not as relevant in this task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑