Please wait a minute...
Vis Inf  2020, Vol. 4 Issue (2): 86-98    DOI: 10.1016/j.visinf.2020.04.001
论文     
借助于序列嵌入实现相似患者病历的比较式可视分析
Rongchen Guoa,Takanori Fujiwarab, Yiran Lib, Kelly M. Limac, Soman Send, Nam K. Tranc, Kwan-Liu Mab
aDepartment of Computer Science, Beihang University, Beijing, China  bDepartment of Computer Science, University of California, Davis, United States  cDepartment of Pathology and Laboratory Medicine, University of California, Davis, United States dDepartment of Surgery, University of California, Davis, United States
Comparative visual analytics for assessing medical records with sequence embedding
Rongchen Guoa,Takanori Fujiwarab, Yiran Lib, Kelly M. Limac, Soman Send, Nam K. Tranc, Kwan-Liu Mab
aDepartment of Computer Science, Beihang University, Beijing, China  bDepartment of Computer Science, University of California, Davis, United States  cDepartment of Pathology and Laboratory Medicine, University of California, Davis, United States dDepartment of Surgery, University of California, Davis, United States
 全文: PDF 
摘要:

为了提供更好的医疗保健服务,医学界对可用于数据驱动诊断的机器学习方法进行了积极的研究。对于临床医生来说,一项重要的任务是对与正在接受治疗的患者具有相似病情的一系列患者的病历进行分析,使得他们能高自信地做出诊断。但是,由于这些病历的高维性、时间上的不规则性、稀疏性等,进行这种分析并不容易。

为了解决这一难题,本文引入了一种病历相似度计算方法,在比对时采用事件和序列嵌入。当使用自动编码器进行事件嵌入时,我们采用它的变体连同自注意机制进行序列嵌入。此外,为了更好地处理数据的不规则性,考虑到不同的时间间隔,增强了自我注意机制。本文开发了一个可视分析系统来支持对病历的比较研究。为了便于比较不同长度的序列,本文的系统采用了序列对齐方法。

过交互界面,用户可以快速找到感兴趣的患者,并方便地查看其病历的时间和多变量方面的信息。我们使用加州大学戴维斯分校新生儿重症监护病房的真实数据集作为研究案例,证明了我们的设计和系统的有效性。



关键词: 电子病历事件序列数据自动编码器自我注意序列相似性可视分析    
Abstract: Machine learning for data-driven diagnosis has been actively studied in medicine to provide better healthcare. Supporting analysis of a patient cohort similar to a patient under treatment is a key task for clinicians to make decisions with high confidence. However, such analysis is not straightforward due to the characteristics of medical records: high dimensionality, irregularity in time, and sparsity. To address this challenge, we introduce a method for similarity calculation of medical records. Our method employs event and sequence embeddings. While we use an autoencoder for the event embedding, we apply its variant with the self-attention mechanism for the sequence embedding. Moreover, in order to better handle the irregularity of data, we enhance the self-attention mechanism with consideration of different time intervals. We have developed a visual analytics system to support comparative studies of patient records. To make a comparison of sequences with different lengths easier, our system incorporates a sequence alignment method. Through its interactive interface, the user can quickly identify patients of interest and conveniently review both the temporal and multivariate aspects of the patient records. We demonstrate the effectiveness of our design and system with case studies using a real-world dataset from the neonatal intensive care unit of UC Davis.
Key words: Electronic medical records    Event sequence data    Autoencoder    Self-attention    Sequence similarity    Visual analytics
出版日期: 2020-06-02
通讯作者: Rongchen Guo      E-mail: rongchen.guo1020@gmail.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
Rongchen Guo
Takanori Fujiwara
Yiran Li
Kelly M. Lima
Soman Sen
Nam K. Tran
Kwan-Liu Ma

引用本文:

Rongchen Guo, Takanori Fujiwara, Yiran Li, Kelly M. Lima, Soman Sen, Nam K. Tran, Kwan-Liu Ma. Comparative visual analytics for assessing medical records with sequence embedding . Vis Inf, 2020, 4(2): 86-98.

链接本文:

http://www.zjujournals.com/vi/CN/10.1016/j.visinf.2020.04.001        http://www.zjujournals.com/vi/CN/Y2020/V4/I2/86

[1] Xiaoyan Kui, Huihao Lv, Zhengliang Tang, Haowen Zhou, Wang Yang, Jinqiu Li, Jialin Guo, Jiazhi Xia. TVseer:一个电视收视率的可视分析系统[J]. Vis Inf, 2020, 4(3): 1-11.
[2] Jingyi Shen, Runqi Wang, Han-Wei Shen. 对中国传统音乐潜在空间的可视探索 [J]. Vis Inf, 2020, 4(2): 99-108.
[3] Yiran Li, Takanori Fujiwara, Yong K. Choi, Katherine K. Kim, Kwan-Liu Ma. 对用于临床数据预测的多个模型进行比较的可视分析系统 [J]. Vis Inf, 2020, 4(2): 122-131.
[4] Tianxiao Hu, Hao Zheng, Chen Liang, Sirou Zhu, Natalie Imirzian, Yizhe Zhang, Chaoli Wang, David P.Hughes, Danny Z.Chen. AntVis:基于网络分析蚂蚁移动数据的可视分析工具 [J]. Vis Inf, 2020, 4(1): 58-70.
[5] Cui Xie, Mingkui Li, Haoying wang, Junyu Dong. 海洋数据可视化分析综述 [J]. Vis Inf, 2019, 3(3): 113-128.
[6] Debajyoti Mondal, Manishankar Mondal, Chanchal K. Roy, Kevin A.Schneider, Yukun Li, Shisong Wang. Clone-World:大规模软件克隆的可视分析系统[J]. Vis Inf, 2019, 3(1): 18-26.
[7] Jenny Vuong, Sandeep Kaur, Julian Heinrich, Bosco K.Ho, Christopher J.Hammang, Benedetta F.Baldi, Seán I.O’Donoghue. Versus——使用2AFC方法评估可视化和图像质量的工具[J]. Vis Inf, 2018, 2(4): 225-234.
[8] Shixia Liu, Gennady Andrienko, Yingcai Wu, Nan Cao, Liu Jiang, Conglei Shi, Yu-Shuen Wang, Seokhee Hong. 运用可视分析控制数据质量:数据复杂性挑战 [J]. Vis Inf, 2018, 2(4): 191-197.
[9] Maha El Meseery, Orland Hoeber. 地理协同平行坐标(GCPC):环境数据分析的现场试验研究 [J]. Vis Inf, 2018, 2(2): 111-124.
[10] WeiZeng, Chi-Wing Fu, Stefan Müller Arisona, Simon Schubiger, Remo Burkhard, Kwan-Liu Ma.

城市人日常出行数据中所含规律的可视分析 [J]. Vis Inf, 2017, 1(2): 132-142.