Cargando…

Predicting Adverse Drug Reactions from Social Media Posts: Data Balance, Feature Selection and Deep Learning

Social forums offer a lot of new channels for collecting patients’ opinions to construct predictive models of adverse drug reactions (ADRs) for post-marketing surveillance. However, due to the characteristics of social posts, there are many challenges still to be solved when deriving such models, ma...

Descripción completa

Detalles Bibliográficos
Autores principales: Huang, Jhih-Yuan, Lee, Wei-Po, Lee, King-Der
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9024774/
https://www.ncbi.nlm.nih.gov/pubmed/35455795
http://dx.doi.org/10.3390/healthcare10040618
_version_ 1784690689372585984
author Huang, Jhih-Yuan
Lee, Wei-Po
Lee, King-Der
author_facet Huang, Jhih-Yuan
Lee, Wei-Po
Lee, King-Der
author_sort Huang, Jhih-Yuan
collection PubMed
description Social forums offer a lot of new channels for collecting patients’ opinions to construct predictive models of adverse drug reactions (ADRs) for post-marketing surveillance. However, due to the characteristics of social posts, there are many challenges still to be solved when deriving such models, mainly including problems caused by data sparseness, data features with a high-dimensionality, and term diversity in data. To tackle these crucial issues related to identifying ADRs from social posts, we perform data analytics from the perspectives of data balance, feature selection, and feature learning. Meanwhile, we design a comprehensive experimental analysis to investigate the performance of different data processing techniques and data modeling methods. Most importantly, we present a deep learning-based approach that adopts the BERT (Bidirectional Encoder Representations from Transformers) model with a new batch-wise adaptive strategy to enhance the predictive performance. A series of experiments have been conducted to evaluate the machine learning methods with both manual and automated feature engineering processes. The results prove that with their own advantages both types of methods are effective in ADR prediction. In contrast to the traditional machine learning methods, our feature learning approach can automatically achieve the required task to save the manual effort for the large number of experiments.
format Online
Article
Text
id pubmed-9024774
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-90247742022-04-23 Predicting Adverse Drug Reactions from Social Media Posts: Data Balance, Feature Selection and Deep Learning Huang, Jhih-Yuan Lee, Wei-Po Lee, King-Der Healthcare (Basel) Article Social forums offer a lot of new channels for collecting patients’ opinions to construct predictive models of adverse drug reactions (ADRs) for post-marketing surveillance. However, due to the characteristics of social posts, there are many challenges still to be solved when deriving such models, mainly including problems caused by data sparseness, data features with a high-dimensionality, and term diversity in data. To tackle these crucial issues related to identifying ADRs from social posts, we perform data analytics from the perspectives of data balance, feature selection, and feature learning. Meanwhile, we design a comprehensive experimental analysis to investigate the performance of different data processing techniques and data modeling methods. Most importantly, we present a deep learning-based approach that adopts the BERT (Bidirectional Encoder Representations from Transformers) model with a new batch-wise adaptive strategy to enhance the predictive performance. A series of experiments have been conducted to evaluate the machine learning methods with both manual and automated feature engineering processes. The results prove that with their own advantages both types of methods are effective in ADR prediction. In contrast to the traditional machine learning methods, our feature learning approach can automatically achieve the required task to save the manual effort for the large number of experiments. MDPI 2022-03-25 /pmc/articles/PMC9024774/ /pubmed/35455795 http://dx.doi.org/10.3390/healthcare10040618 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Huang, Jhih-Yuan
Lee, Wei-Po
Lee, King-Der
Predicting Adverse Drug Reactions from Social Media Posts: Data Balance, Feature Selection and Deep Learning
title Predicting Adverse Drug Reactions from Social Media Posts: Data Balance, Feature Selection and Deep Learning
title_full Predicting Adverse Drug Reactions from Social Media Posts: Data Balance, Feature Selection and Deep Learning
title_fullStr Predicting Adverse Drug Reactions from Social Media Posts: Data Balance, Feature Selection and Deep Learning
title_full_unstemmed Predicting Adverse Drug Reactions from Social Media Posts: Data Balance, Feature Selection and Deep Learning
title_short Predicting Adverse Drug Reactions from Social Media Posts: Data Balance, Feature Selection and Deep Learning
title_sort predicting adverse drug reactions from social media posts: data balance, feature selection and deep learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9024774/
https://www.ncbi.nlm.nih.gov/pubmed/35455795
http://dx.doi.org/10.3390/healthcare10040618
work_keys_str_mv AT huangjhihyuan predictingadversedrugreactionsfromsocialmediapostsdatabalancefeatureselectionanddeeplearning
AT leeweipo predictingadversedrugreactionsfromsocialmediapostsdatabalancefeatureselectionanddeeplearning
AT leekingder predictingadversedrugreactionsfromsocialmediapostsdatabalancefeatureselectionanddeeplearning