0


通过时间感知 LSTM 网络进行患者子类型分析

Patient Subtyping via Time-­Aware LSTM Network
课程网址: http://videolectures.net/kdd2017_baytas_patient_subtyping/  
主讲教师: Inci M. Baytas
开课单位: 密歇根州立大学
开课时间: 2017-10-09
课程语种: 英语
中文简介:
在各种疾病的研究中，患者之间的异质性通常会导致不同的进展模式，并且可能需要不同类型的治疗干预。因此，研究患者亚型非常重要，即将患者分为疾病特征亚型。由于信息异质性和时间动态性，从复杂的患者数据中进行子类型化具有挑战性。长短期记忆 (LSTM) 已成功应用于许多领域来处理顺序数据，最近还应用于分析纵向患者记录。LSTM 单元旨在处理序列的连续元素之间经过时间恒定的数据。鉴于患者记录中连续元素之间的时间间隔可能从几天到几个月不等，传统 LSTM 的设计可能会导致性能不佳。在本文中，我们提出了一种称为时间感知 LSTM (T-LSTM) 的新型 LSTM 单元，用于处理纵向患者记录中的不规则时间间隔。我们学习细胞记忆的子空间分解，它使时间衰减能够根据经过的时间来折扣记忆内容。我们提出了一种患者子类型模型，该模型利用自动编码器中提出的 T-LSTM 来学习患者顺序记录的强大单一表示，然后用于将患者聚类为临床亚型。对合成数据集和现实世界数据集的实验表明，所提出的 T-LSTM 架构捕获了具有时间不规则性的序列中的底层结构。
课程简介: In the study of various diseases, heterogeneity among patients usually leads to different progression patterns and may require different types of therapeutic intervention. Therefore, it is important to study patient subtyping, which is grouping of patients into disease characterizing subtypes. Subtyping from complex patient data is challenging because of the information heterogeneity and temporal dynamics. Long-Short Term Memory (LSTM) has been successfully used in many domains for processing sequential data, and recently applied for analyzing longitudinal patient records. The LSTM units are designed to handle data with constant elapsed times between consecutive elements of a sequence. Given that time lapse between successive elements in patient records can vary from days to months, the design of traditional LSTM may lead to suboptimal performance. In this paper, we propose a novel LSTM unit called Time-Aware LSTM (T-LSTM) to handle irregular time intervals in longitudinal patient records. We learn a subspace decomposition of the cell memory which enables time decay to discount the memory content according to the elapsed time. We propose a patient subtyping model that leverages the proposed T-LSTM in an auto-encoder to learn a powerful single representation for sequential records of patients, which are then used to cluster patients into clinical subtypes. Experiments on synthetic and real world datasets show that the proposed T-LSTM architecture captures the underlying structures in the sequences with time irregularities.
关 键 词: 合成数据集; 长短期记忆; 数据科学
课程来源: 视频讲座网
数据采集: 2023-12-26：wujk
最后编审: 2023-12-26：wujk
阅读次数: 20

纠错/补充/评论/留言
评论/留言 纠错/补充
验证算术题： 6 + 10 =