An RNN architecture with dynamic temporal matching for personalized predictions of Parkinson's disease

Chao Che, Cao Xiao, Jian Liang, Bo Jin, Jiayu Zhou, Fei Wang

Research output: ResearchConference contribution

  • 1 Citations

Abstract

Parkinson's disease (PD) is a chronic disease that develops over years and varies dramatically in its clinical manifestations. A preferred strategy to resolve this heterogeneity and thus enable better prognosis and targeted therapies is to segment out more homogeneous patient sub-populations. However, it is challenging to evaluate the clinical similarities among patients because of the longitudinality and temporality of their records. To address this issue, we propose a deep model that directly learns patient similarity from longitudinal and multi-modal patient records with an Recurrent Neural Network (RNN) architecture, which learns the similarity between two longitudinal patient record sequences through dynamically matching temporal patterns in patient sequences. Evaluations on real world patient records demonstrate the promising utility and efficacy of the proposed architecture in personalized predictions.

LanguageEnglish (US)
Title of host publicationProceedings of the 17th SIAM International Conference on Data Mining, SDM 2017
PublisherSociety for Industrial and Applied Mathematics Publications
Pages198-206
Number of pages9
ISBN (Electronic)9781611974874
StatePublished - 2017
Event17th SIAM International Conference on Data Mining, SDM 2017 - Houston, United States
Duration: Apr 27 2017Apr 29 2017

Other

Other17th SIAM International Conference on Data Mining, SDM 2017
CountryUnited States
CityHouston
Period4/27/174/29/17

Profile

Recurrent neural networks
Network architecture

ASJC Scopus subject areas

  • Software
  • Computer Science Applications

Cite this

Che, C., Xiao, C., Liang, J., Jin, B., Zhou, J., & Wang, F. (2017). An RNN architecture with dynamic temporal matching for personalized predictions of Parkinson's disease. In Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017 (pp. 198-206). Society for Industrial and Applied Mathematics Publications.

An RNN architecture with dynamic temporal matching for personalized predictions of Parkinson's disease. / Che, Chao; Xiao, Cao; Liang, Jian; Jin, Bo; Zhou, Jiayu; Wang, Fei.

Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017. Society for Industrial and Applied Mathematics Publications, 2017. p. 198-206.

Research output: ResearchConference contribution

Che, C, Xiao, C, Liang, J, Jin, B, Zhou, J & Wang, F 2017, An RNN architecture with dynamic temporal matching for personalized predictions of Parkinson's disease. in Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017. Society for Industrial and Applied Mathematics Publications, pp. 198-206, 17th SIAM International Conference on Data Mining, SDM 2017, Houston, United States, 4/27/17.
Che C, Xiao C, Liang J, Jin B, Zhou J, Wang F. An RNN architecture with dynamic temporal matching for personalized predictions of Parkinson's disease. In Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017. Society for Industrial and Applied Mathematics Publications. 2017. p. 198-206.
Che, Chao ; Xiao, Cao ; Liang, Jian ; Jin, Bo ; Zhou, Jiayu ; Wang, Fei. / An RNN architecture with dynamic temporal matching for personalized predictions of Parkinson's disease. Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017. Society for Industrial and Applied Mathematics Publications, 2017. pp. 198-206
@inbook{751e557edbae4f75ba729e971397b0c7,
title = "An RNN architecture with dynamic temporal matching for personalized predictions of Parkinson's disease",
abstract = "Parkinson's disease (PD) is a chronic disease that develops over years and varies dramatically in its clinical manifestations. A preferred strategy to resolve this heterogeneity and thus enable better prognosis and targeted therapies is to segment out more homogeneous patient sub-populations. However, it is challenging to evaluate the clinical similarities among patients because of the longitudinality and temporality of their records. To address this issue, we propose a deep model that directly learns patient similarity from longitudinal and multi-modal patient records with an Recurrent Neural Network (RNN) architecture, which learns the similarity between two longitudinal patient record sequences through dynamically matching temporal patterns in patient sequences. Evaluations on real world patient records demonstrate the promising utility and efficacy of the proposed architecture in personalized predictions.",
author = "Chao Che and Cao Xiao and Jian Liang and Bo Jin and Jiayu Zhou and Fei Wang",
year = "2017",
pages = "198--206",
booktitle = "Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017",
publisher = "Society for Industrial and Applied Mathematics Publications",

}

TY - CHAP

T1 - An RNN architecture with dynamic temporal matching for personalized predictions of Parkinson's disease

AU - Che,Chao

AU - Xiao,Cao

AU - Liang,Jian

AU - Jin,Bo

AU - Zhou,Jiayu

AU - Wang,Fei

PY - 2017

Y1 - 2017

N2 - Parkinson's disease (PD) is a chronic disease that develops over years and varies dramatically in its clinical manifestations. A preferred strategy to resolve this heterogeneity and thus enable better prognosis and targeted therapies is to segment out more homogeneous patient sub-populations. However, it is challenging to evaluate the clinical similarities among patients because of the longitudinality and temporality of their records. To address this issue, we propose a deep model that directly learns patient similarity from longitudinal and multi-modal patient records with an Recurrent Neural Network (RNN) architecture, which learns the similarity between two longitudinal patient record sequences through dynamically matching temporal patterns in patient sequences. Evaluations on real world patient records demonstrate the promising utility and efficacy of the proposed architecture in personalized predictions.

AB - Parkinson's disease (PD) is a chronic disease that develops over years and varies dramatically in its clinical manifestations. A preferred strategy to resolve this heterogeneity and thus enable better prognosis and targeted therapies is to segment out more homogeneous patient sub-populations. However, it is challenging to evaluate the clinical similarities among patients because of the longitudinality and temporality of their records. To address this issue, we propose a deep model that directly learns patient similarity from longitudinal and multi-modal patient records with an Recurrent Neural Network (RNN) architecture, which learns the similarity between two longitudinal patient record sequences through dynamically matching temporal patterns in patient sequences. Evaluations on real world patient records demonstrate the promising utility and efficacy of the proposed architecture in personalized predictions.

UR - http://www.scopus.com/inward/record.url?scp=85027855331&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027855331&partnerID=8YFLogxK

M3 - Conference contribution

SP - 198

EP - 206

BT - Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017

PB - Society for Industrial and Applied Mathematics Publications

ER -