Detecting potential adverse drug reactions using a deep neural network model

Chi Shiang Wang, Pei Ju Lin, Ching-Lan Cheng, Shu Hua Tai, Yea-Huei Kao, Jung-Hsien Chiang

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Background: Adverse drug reactions (ADRs) are common and are the underlying cause of over a million serious injuries and deaths each year. The most familiar method to detect ADRs is relying on spontaneous reports. Unfortunately, the low reporting rate of spontaneous reports is a serious limitation of pharmacovigilance. Objective: The objective of this study was to identify a method to detect potential ADRs of drugs automatically using a deep neural network (DNN). Methods: We designed a DNN model that utilizes the chemical, biological, and biomedical information of drugs to detect ADRs. This model aimed to fulfill two main purposes: identifying the potential ADRs of drugs and predicting the possible ADRs of a new drug. For improving the detection performance, we distributed representations of the target drugs in a vector space to capture the drug relationships using the word-embedding approach to process substantial biomedical literature. Moreover, we built a mapping function to address new drugs that do not appear in the dataset. Results: Using the drug information and the ADRs reported up to 2009, we predicted the ADRs of drugs recorded up to 2012. There were 746 drugs and 232 new drugs, which were only recorded in 2012 with 1325 ADRs. The experimental results showed that the overall performance of our model with mean average precision at top-10 achieved is 0.523 and the rea under the receiver operating characteristic curve (AUC) score achieved is 0.844 for ADR prediction on the dataset. Conclusions: Our model is effective in identifying the potential ADRs of a drug and the possible ADRs of a new drug. Most importantly, it can detect potential ADRs irrespective of whether they have been reported in the past.

Original languageEnglish
Article numbere11016
JournalJournal of medical Internet research
Volume21
Issue number2
DOIs
Publication statusPublished - 2019 Feb 1

Fingerprint

Neural Networks (Computer)
Drug-Related Side Effects and Adverse Reactions
Pharmaceutical Preparations
Pharmacovigilance
ROC Curve
Area Under Curve

All Science Journal Classification (ASJC) codes

  • Health Informatics

Cite this

@article{6c864994f4ca4bf896a8f83f7cac180c,
title = "Detecting potential adverse drug reactions using a deep neural network model",
abstract = "Background: Adverse drug reactions (ADRs) are common and are the underlying cause of over a million serious injuries and deaths each year. The most familiar method to detect ADRs is relying on spontaneous reports. Unfortunately, the low reporting rate of spontaneous reports is a serious limitation of pharmacovigilance. Objective: The objective of this study was to identify a method to detect potential ADRs of drugs automatically using a deep neural network (DNN). Methods: We designed a DNN model that utilizes the chemical, biological, and biomedical information of drugs to detect ADRs. This model aimed to fulfill two main purposes: identifying the potential ADRs of drugs and predicting the possible ADRs of a new drug. For improving the detection performance, we distributed representations of the target drugs in a vector space to capture the drug relationships using the word-embedding approach to process substantial biomedical literature. Moreover, we built a mapping function to address new drugs that do not appear in the dataset. Results: Using the drug information and the ADRs reported up to 2009, we predicted the ADRs of drugs recorded up to 2012. There were 746 drugs and 232 new drugs, which were only recorded in 2012 with 1325 ADRs. The experimental results showed that the overall performance of our model with mean average precision at top-10 achieved is 0.523 and the rea under the receiver operating characteristic curve (AUC) score achieved is 0.844 for ADR prediction on the dataset. Conclusions: Our model is effective in identifying the potential ADRs of a drug and the possible ADRs of a new drug. Most importantly, it can detect potential ADRs irrespective of whether they have been reported in the past.",
author = "Wang, {Chi Shiang} and Lin, {Pei Ju} and Ching-Lan Cheng and Tai, {Shu Hua} and Yea-Huei Kao and Jung-Hsien Chiang",
year = "2019",
month = "2",
day = "1",
doi = "10.2196/11016",
language = "English",
volume = "21",
journal = "Journal of Medical Internet Research",
issn = "1439-4456",
publisher = "Journal of medical Internet Research",
number = "2",

}

Detecting potential adverse drug reactions using a deep neural network model. / Wang, Chi Shiang; Lin, Pei Ju; Cheng, Ching-Lan; Tai, Shu Hua; Kao, Yea-Huei; Chiang, Jung-Hsien.

In: Journal of medical Internet research, Vol. 21, No. 2, e11016, 01.02.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Detecting potential adverse drug reactions using a deep neural network model

AU - Wang, Chi Shiang

AU - Lin, Pei Ju

AU - Cheng, Ching-Lan

AU - Tai, Shu Hua

AU - Kao, Yea-Huei

AU - Chiang, Jung-Hsien

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Background: Adverse drug reactions (ADRs) are common and are the underlying cause of over a million serious injuries and deaths each year. The most familiar method to detect ADRs is relying on spontaneous reports. Unfortunately, the low reporting rate of spontaneous reports is a serious limitation of pharmacovigilance. Objective: The objective of this study was to identify a method to detect potential ADRs of drugs automatically using a deep neural network (DNN). Methods: We designed a DNN model that utilizes the chemical, biological, and biomedical information of drugs to detect ADRs. This model aimed to fulfill two main purposes: identifying the potential ADRs of drugs and predicting the possible ADRs of a new drug. For improving the detection performance, we distributed representations of the target drugs in a vector space to capture the drug relationships using the word-embedding approach to process substantial biomedical literature. Moreover, we built a mapping function to address new drugs that do not appear in the dataset. Results: Using the drug information and the ADRs reported up to 2009, we predicted the ADRs of drugs recorded up to 2012. There were 746 drugs and 232 new drugs, which were only recorded in 2012 with 1325 ADRs. The experimental results showed that the overall performance of our model with mean average precision at top-10 achieved is 0.523 and the rea under the receiver operating characteristic curve (AUC) score achieved is 0.844 for ADR prediction on the dataset. Conclusions: Our model is effective in identifying the potential ADRs of a drug and the possible ADRs of a new drug. Most importantly, it can detect potential ADRs irrespective of whether they have been reported in the past.

AB - Background: Adverse drug reactions (ADRs) are common and are the underlying cause of over a million serious injuries and deaths each year. The most familiar method to detect ADRs is relying on spontaneous reports. Unfortunately, the low reporting rate of spontaneous reports is a serious limitation of pharmacovigilance. Objective: The objective of this study was to identify a method to detect potential ADRs of drugs automatically using a deep neural network (DNN). Methods: We designed a DNN model that utilizes the chemical, biological, and biomedical information of drugs to detect ADRs. This model aimed to fulfill two main purposes: identifying the potential ADRs of drugs and predicting the possible ADRs of a new drug. For improving the detection performance, we distributed representations of the target drugs in a vector space to capture the drug relationships using the word-embedding approach to process substantial biomedical literature. Moreover, we built a mapping function to address new drugs that do not appear in the dataset. Results: Using the drug information and the ADRs reported up to 2009, we predicted the ADRs of drugs recorded up to 2012. There were 746 drugs and 232 new drugs, which were only recorded in 2012 with 1325 ADRs. The experimental results showed that the overall performance of our model with mean average precision at top-10 achieved is 0.523 and the rea under the receiver operating characteristic curve (AUC) score achieved is 0.844 for ADR prediction on the dataset. Conclusions: Our model is effective in identifying the potential ADRs of a drug and the possible ADRs of a new drug. Most importantly, it can detect potential ADRs irrespective of whether they have been reported in the past.

UR - http://www.scopus.com/inward/record.url?scp=85061124203&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061124203&partnerID=8YFLogxK

U2 - 10.2196/11016

DO - 10.2196/11016

M3 - Article

C2 - 30724742

AN - SCOPUS:85061124203

VL - 21

JO - Journal of Medical Internet Research

JF - Journal of Medical Internet Research

SN - 1439-4456

IS - 2

M1 - e11016

ER -