Predicting High-Order Directional Drug-Drug Interaction Relations

Xia Ning, Li Shen, Lang Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

High-order Drug-Drug Interactions (DDI) are common particularly for elderly people. It is highly non-trivial to detect such interactions via in vivo/in vitro experiments. In this paper, we present SVM-based classification methods to predict whether a high-order directional drug-drug interaction (HoDDDI) instance is associated with adverse drug reactions (ADRs) and induced side effects. Specifically, we developed kernels for HoDDDI instances of arbitrary orders that are constructed from various single-drug information. The experiments over datasets extracted from electronic health records demonstrate that our classification methods can achieve the best F1 as 0.793.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages556-561
Number of pages6
ISBN (Electronic)9781509048816
DOIs
StatePublished - Sep 8 2017
Event5th IEEE International Conference on Healthcare Informatics, ICHI 2017 - Park City, United States
Duration: Aug 23 2017Aug 26 2017

Other

Other5th IEEE International Conference on Healthcare Informatics, ICHI 2017
CountryUnited States
CityPark City
Period8/23/178/26/17

Fingerprint

Drug Interactions
Pharmaceutical Preparations
Electronic Health Records
Drug-Related Side Effects and Adverse Reactions

Keywords

  • High-Order Drug-Drug Interactions
  • Support Vector Machines

ASJC Scopus subject areas

  • Health Informatics

Cite this

Ning, X., Shen, L., & Li, L. (2017). Predicting High-Order Directional Drug-Drug Interaction Relations. In Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017 (pp. 556-561). [8031212] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHI.2017.76

Predicting High-Order Directional Drug-Drug Interaction Relations. / Ning, Xia; Shen, Li; Li, Lang.

Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 556-561 8031212.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ning, X, Shen, L & Li, L 2017, Predicting High-Order Directional Drug-Drug Interaction Relations. in Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017., 8031212, Institute of Electrical and Electronics Engineers Inc., pp. 556-561, 5th IEEE International Conference on Healthcare Informatics, ICHI 2017, Park City, United States, 8/23/17. https://doi.org/10.1109/ICHI.2017.76
Ning X, Shen L, Li L. Predicting High-Order Directional Drug-Drug Interaction Relations. In Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 556-561. 8031212 https://doi.org/10.1109/ICHI.2017.76
Ning, Xia ; Shen, Li ; Li, Lang. / Predicting High-Order Directional Drug-Drug Interaction Relations. Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 556-561
@inproceedings{3f6e02a5ca2d4f79b8c2d956f6da40bb,
title = "Predicting High-Order Directional Drug-Drug Interaction Relations",
abstract = "High-order Drug-Drug Interactions (DDI) are common particularly for elderly people. It is highly non-trivial to detect such interactions via in vivo/in vitro experiments. In this paper, we present SVM-based classification methods to predict whether a high-order directional drug-drug interaction (HoDDDI) instance is associated with adverse drug reactions (ADRs) and induced side effects. Specifically, we developed kernels for HoDDDI instances of arbitrary orders that are constructed from various single-drug information. The experiments over datasets extracted from electronic health records demonstrate that our classification methods can achieve the best F1 as 0.793.",
keywords = "High-Order Drug-Drug Interactions, Support Vector Machines",
author = "Xia Ning and Li Shen and Lang Li",
year = "2017",
month = "9",
day = "8",
doi = "10.1109/ICHI.2017.76",
language = "English (US)",
pages = "556--561",
booktitle = "Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Predicting High-Order Directional Drug-Drug Interaction Relations

AU - Ning, Xia

AU - Shen, Li

AU - Li, Lang

PY - 2017/9/8

Y1 - 2017/9/8

N2 - High-order Drug-Drug Interactions (DDI) are common particularly for elderly people. It is highly non-trivial to detect such interactions via in vivo/in vitro experiments. In this paper, we present SVM-based classification methods to predict whether a high-order directional drug-drug interaction (HoDDDI) instance is associated with adverse drug reactions (ADRs) and induced side effects. Specifically, we developed kernels for HoDDDI instances of arbitrary orders that are constructed from various single-drug information. The experiments over datasets extracted from electronic health records demonstrate that our classification methods can achieve the best F1 as 0.793.

AB - High-order Drug-Drug Interactions (DDI) are common particularly for elderly people. It is highly non-trivial to detect such interactions via in vivo/in vitro experiments. In this paper, we present SVM-based classification methods to predict whether a high-order directional drug-drug interaction (HoDDDI) instance is associated with adverse drug reactions (ADRs) and induced side effects. Specifically, we developed kernels for HoDDDI instances of arbitrary orders that are constructed from various single-drug information. The experiments over datasets extracted from electronic health records demonstrate that our classification methods can achieve the best F1 as 0.793.

KW - High-Order Drug-Drug Interactions

KW - Support Vector Machines

UR - http://www.scopus.com/inward/record.url?scp=85032345217&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032345217&partnerID=8YFLogxK

U2 - 10.1109/ICHI.2017.76

DO - 10.1109/ICHI.2017.76

M3 - Conference contribution

AN - SCOPUS:85032345217

SP - 556

EP - 561

BT - Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -