UNSUPERVISED DYNAMIC TOPIC MODEL FOR EXTRACTING ADVERSE DRUG REACTION FROM HEALTH FORUMS

The relationship between drug and its side effects has been outlined in two websites: Sider and WebMD. The aim of this study was to find the association between drug and its side effects. We compared the reports of typical users of a web site called: "Ask a patient" website with reported...

Full description

Saved in:
Bibliographic Details
Main Authors: Behnaz ESLAMI, Mehdi HABIBZADEH MOTLAGH, Zahra REZAEI, Mohammad ESLAMI, Mohammad AMIN AMINI
Format: Article
Language:English
Published: Polish Association for Knowledge Promotion 2020-03-01
Series:Applied Computer Science
Subjects:
Online Access:https://ph.pollub.pl/index.php/acs/article/view/3142
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850149234085462016
author Behnaz ESLAMI
Mehdi HABIBZADEH MOTLAGH
Zahra REZAEI
Mohammad ESLAMI
Mohammad AMIN AMINI
author_facet Behnaz ESLAMI
Mehdi HABIBZADEH MOTLAGH
Zahra REZAEI
Mohammad ESLAMI
Mohammad AMIN AMINI
author_sort Behnaz ESLAMI
collection DOAJ
description The relationship between drug and its side effects has been outlined in two websites: Sider and WebMD. The aim of this study was to find the association between drug and its side effects. We compared the reports of typical users of a web site called: "Ask a patient" website with reported drug side effects in reference sites such as Sider and WebMD. In addition, the typical users' comments on highly-commented drugs (Neurotic drugs, Anti-Pregnancy drugs and Gastrointestinal drugs) were analyzed, using deep learning method. To this end, typical users' comments on drugs' side effects, during last decades, were collected from the website “Ask a patient”. Then, the data on drugs were classified based on deep learning model (HAN) and the drugs' side effect. And the main topics of side effects for each group of drugs were identified and reported, through Sider and WebMD websites. Our model demonstrates its ability to accurately describe and label side effects in a temporal text corpus by a deep learning classifier which is shown to be an effective method to precisely discover the association between drugs and their side effects. Moreover, this model has the capability to immediately locate information in reference sites to recognize the side effect of new drugs, applicable for drug companies. This study suggests that the sensitivity of internet users and the diverse scientific findings are for the benefit of dis¬tinct detection of adverse effects of drugs, and deep learning would facilitate it.
format Article
id doaj-art-b8d6ff2887db4ea4a5f1698ad9f35a9e
institution OA Journals
issn 2353-6977
language English
publishDate 2020-03-01
publisher Polish Association for Knowledge Promotion
record_format Article
series Applied Computer Science
spelling doaj-art-b8d6ff2887db4ea4a5f1698ad9f35a9e2025-08-20T02:26:59ZengPolish Association for Knowledge PromotionApplied Computer Science2353-69772020-03-0116110.35784/acs-2020-04UNSUPERVISED DYNAMIC TOPIC MODEL FOR EXTRACTING ADVERSE DRUG REACTION FROM HEALTH FORUMSBehnaz ESLAMI0Mehdi HABIBZADEH MOTLAGH1Zahra REZAEI2Mohammad ESLAMI3Mohammad AMIN AMINI4Islamic Azad University, Science and Research Branch, Department of Computer Engineering, Islamic Azad University, TehranP/S/L Group, 1801 McGill College Ave, Montreal, Quebec H3A 2N4, MontrealUniversity of Kashan, Department of Computer and Electrical Engineering, Isfahan Province, Qotb-e Ravandi Blvd, Kashan* Islamic Azad University of Qazvin,Department of Computer Engineering, QazvinIslamic Azad University of Jasb, Department of Computer Engineering, Markazi The relationship between drug and its side effects has been outlined in two websites: Sider and WebMD. The aim of this study was to find the association between drug and its side effects. We compared the reports of typical users of a web site called: "Ask a patient" website with reported drug side effects in reference sites such as Sider and WebMD. In addition, the typical users' comments on highly-commented drugs (Neurotic drugs, Anti-Pregnancy drugs and Gastrointestinal drugs) were analyzed, using deep learning method. To this end, typical users' comments on drugs' side effects, during last decades, were collected from the website “Ask a patient”. Then, the data on drugs were classified based on deep learning model (HAN) and the drugs' side effect. And the main topics of side effects for each group of drugs were identified and reported, through Sider and WebMD websites. Our model demonstrates its ability to accurately describe and label side effects in a temporal text corpus by a deep learning classifier which is shown to be an effective method to precisely discover the association between drugs and their side effects. Moreover, this model has the capability to immediately locate information in reference sites to recognize the side effect of new drugs, applicable for drug companies. This study suggests that the sensitivity of internet users and the diverse scientific findings are for the benefit of dis¬tinct detection of adverse effects of drugs, and deep learning would facilitate it. https://ph.pollub.pl/index.php/acs/article/view/3142Deep Learningtopic modelingText MiningADRNMF
spellingShingle Behnaz ESLAMI
Mehdi HABIBZADEH MOTLAGH
Zahra REZAEI
Mohammad ESLAMI
Mohammad AMIN AMINI
UNSUPERVISED DYNAMIC TOPIC MODEL FOR EXTRACTING ADVERSE DRUG REACTION FROM HEALTH FORUMS
Applied Computer Science
Deep Learning
topic modeling
Text Mining
ADR
NMF
title UNSUPERVISED DYNAMIC TOPIC MODEL FOR EXTRACTING ADVERSE DRUG REACTION FROM HEALTH FORUMS
title_full UNSUPERVISED DYNAMIC TOPIC MODEL FOR EXTRACTING ADVERSE DRUG REACTION FROM HEALTH FORUMS
title_fullStr UNSUPERVISED DYNAMIC TOPIC MODEL FOR EXTRACTING ADVERSE DRUG REACTION FROM HEALTH FORUMS
title_full_unstemmed UNSUPERVISED DYNAMIC TOPIC MODEL FOR EXTRACTING ADVERSE DRUG REACTION FROM HEALTH FORUMS
title_short UNSUPERVISED DYNAMIC TOPIC MODEL FOR EXTRACTING ADVERSE DRUG REACTION FROM HEALTH FORUMS
title_sort unsupervised dynamic topic model for extracting adverse drug reaction from health forums
topic Deep Learning
topic modeling
Text Mining
ADR
NMF
url https://ph.pollub.pl/index.php/acs/article/view/3142
work_keys_str_mv AT behnazeslami unsuperviseddynamictopicmodelforextractingadversedrugreactionfromhealthforums
AT mehdihabibzadehmotlagh unsuperviseddynamictopicmodelforextractingadversedrugreactionfromhealthforums
AT zahrarezaei unsuperviseddynamictopicmodelforextractingadversedrugreactionfromhealthforums
AT mohammadeslami unsuperviseddynamictopicmodelforextractingadversedrugreactionfromhealthforums
AT mohammadaminamini unsuperviseddynamictopicmodelforextractingadversedrugreactionfromhealthforums