• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Suo, Qiuling (Suo, Qiuling.) | Ma, Fenglong (Ma, Fenglong.) | Yuan, Ye (Yuan, Ye.) | Huai, Mengdi (Huai, Mengdi.) | Zhong, Weida (Zhong, Weida.) | Zhang, Aidong (Zhang, Aidong.) | Gao, Jing (Gao, Jing.)

Indexed by:

EI Scopus

Abstract:

Predicting patients' risk of developing certain diseases is an important research topic in healthcare. Personalized predictive modeling, which focuses on building specific models for individual patients, has shown its advantages on utilizing heterogeneous health data compared to global models trained on the entire population. Personalized predictive models use information from similar patient cohorts, in order to capture the specific characteristics. Accurately identifying and ranking the similarity among patients based on their historical records is a key step in personalized modeling. The electric health records (EHRs), which are irregular sampled and have varied patient visit lengths, cannot be directly used to measure patient similarity due to lack of an appropriate vector representation. In this paper, we build a novel time fusion CNN framework to simultaneously learn patient representations and measure pairwise similarity. Compared to a traditional CNN, our time fusion CNN can learn not only the local temporal relationships but also the contributions from each time interval. Along with the similarity learning process, the output information which is the probability distribution is used to rank similar patients. Utilizing the similarity scores, we perform personalized disease predictions, and compare the effect of different vector representations and similarity learning metrics. © 2017 IEEE.

Keyword:

Predictive analytics Forecasting Bioinformatics Encoding (symbols) Probability distributions Population statistics Learning systems

Author Community:

  • [ 1 ] [Suo, Qiuling]Department of Computer Science and Engineering, State University of New York at Buffalo, NY, United States
  • [ 2 ] [Ma, Fenglong]Department of Computer Science and Engineering, State University of New York at Buffalo, NY, United States
  • [ 3 ] [Yuan, Ye]College of Information and Communication Engineering, Beijing University of Technology, Beijing, China
  • [ 4 ] [Huai, Mengdi]Department of Computer Science and Engineering, State University of New York at Buffalo, NY, United States
  • [ 5 ] [Zhong, Weida]Department of Computer Science and Engineering, State University of New York at Buffalo, NY, United States
  • [ 6 ] [Zhang, Aidong]Department of Computer Science and Engineering, State University of New York at Buffalo, NY, United States
  • [ 7 ] [Gao, Jing]Department of Computer Science and Engineering, State University of New York at Buffalo, NY, United States

Reprint Author's Address:

Email:

Show more details

Related Keywords:

Source :

Year: 2017

Volume: 2017-January

Page: 811-816

Language: English

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count: 83

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 2

Affiliated Colleges:

Online/Total:588/5288816
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.