Predicting patients’ sentiments about medications using artificial intelligence techniques

Abstract The increasing development of technology has led to the increase of digital data in various fields, such as medication-related texts. Sentiment Analysis (SA) in medication is essential to give clinicians insights into patients’ feedback about the treatment procedure. Therefore, this study i...

Full description

Saved in:
Bibliographic Details
Main Authors: Amir Sorayaie Azar, Samin Babaei Rikan, Amin Naemi, Jamshid Bagherzadeh Mohasefi, Uffe Kock Wiil
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-83222-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841559511108681728
author Amir Sorayaie Azar
Samin Babaei Rikan
Amin Naemi
Jamshid Bagherzadeh Mohasefi
Uffe Kock Wiil
author_facet Amir Sorayaie Azar
Samin Babaei Rikan
Amin Naemi
Jamshid Bagherzadeh Mohasefi
Uffe Kock Wiil
author_sort Amir Sorayaie Azar
collection DOAJ
description Abstract The increasing development of technology has led to the increase of digital data in various fields, such as medication-related texts. Sentiment Analysis (SA) in medication is essential to give clinicians insights into patients’ feedback about the treatment procedure. Therefore, this study intends to develop Artificial Intelligence (AI) models to predict patients’ sentiments. This study used a large medication review dataset to perform a SA of medications. Three scenarios were considered for classification, including two, three, and ten classes. The Word2Vec algorithm and pre-trained word embeddings, including the general and clinical domains, were utilized in model development. Seven Machine Learning (ML) and Deep Learning (DL) models were developed for various scenarios. The best hyperparameters for all models were fine-tuned. Moreover, two ensemble learning models were developed from the proposed ML and DL models. For the first time, a technique was implemented to interpret the results for explainability and interpretability. The results showed that the developed deep ensemble model (DL_ENS), using PubMed and PMC, as pre-trained word embedding representation, achieved the best results, with accuracy and F1-Score of 92.96% and 92.27% in two classes, 92.18% and 88.50 in three classes, and 90.31% and 67.07% in ten classes, respectively. Combining DL models and developing a DL_ENS with clinical domain pre-trained word embedding representation can accurately predict classes and scores of patients’ sentiments about medications compared to previous studies on the same dataset. Due to the transparency in decision-making, our DL_ENS model can be used as an auxiliary tool to help clinicians prescribe medications.
format Article
id doaj-art-a7eee301b3324bbda44746245648b98d
institution Kabale University
issn 2045-2322
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-a7eee301b3324bbda44746245648b98d2025-01-05T12:26:03ZengNature PortfolioScientific Reports2045-23222024-12-0114112310.1038/s41598-024-83222-9Predicting patients’ sentiments about medications using artificial intelligence techniquesAmir Sorayaie Azar0Samin Babaei Rikan1Amin Naemi2Jamshid Bagherzadeh Mohasefi3Uffe Kock Wiil4SDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern DenmarkDepartment of Computer Engineering, Urmia UniversitySDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern DenmarkSDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern DenmarkSDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern DenmarkAbstract The increasing development of technology has led to the increase of digital data in various fields, such as medication-related texts. Sentiment Analysis (SA) in medication is essential to give clinicians insights into patients’ feedback about the treatment procedure. Therefore, this study intends to develop Artificial Intelligence (AI) models to predict patients’ sentiments. This study used a large medication review dataset to perform a SA of medications. Three scenarios were considered for classification, including two, three, and ten classes. The Word2Vec algorithm and pre-trained word embeddings, including the general and clinical domains, were utilized in model development. Seven Machine Learning (ML) and Deep Learning (DL) models were developed for various scenarios. The best hyperparameters for all models were fine-tuned. Moreover, two ensemble learning models were developed from the proposed ML and DL models. For the first time, a technique was implemented to interpret the results for explainability and interpretability. The results showed that the developed deep ensemble model (DL_ENS), using PubMed and PMC, as pre-trained word embedding representation, achieved the best results, with accuracy and F1-Score of 92.96% and 92.27% in two classes, 92.18% and 88.50 in three classes, and 90.31% and 67.07% in ten classes, respectively. Combining DL models and developing a DL_ENS with clinical domain pre-trained word embedding representation can accurately predict classes and scores of patients’ sentiments about medications compared to previous studies on the same dataset. Due to the transparency in decision-making, our DL_ENS model can be used as an auxiliary tool to help clinicians prescribe medications.https://doi.org/10.1038/s41598-024-83222-9Medication reviewsPatients’ sentiment analysisMachine learningDeep learningEnsemble learningExplainable artificial intelligence
spellingShingle Amir Sorayaie Azar
Samin Babaei Rikan
Amin Naemi
Jamshid Bagherzadeh Mohasefi
Uffe Kock Wiil
Predicting patients’ sentiments about medications using artificial intelligence techniques
Scientific Reports
Medication reviews
Patients’ sentiment analysis
Machine learning
Deep learning
Ensemble learning
Explainable artificial intelligence
title Predicting patients’ sentiments about medications using artificial intelligence techniques
title_full Predicting patients’ sentiments about medications using artificial intelligence techniques
title_fullStr Predicting patients’ sentiments about medications using artificial intelligence techniques
title_full_unstemmed Predicting patients’ sentiments about medications using artificial intelligence techniques
title_short Predicting patients’ sentiments about medications using artificial intelligence techniques
title_sort predicting patients sentiments about medications using artificial intelligence techniques
topic Medication reviews
Patients’ sentiment analysis
Machine learning
Deep learning
Ensemble learning
Explainable artificial intelligence
url https://doi.org/10.1038/s41598-024-83222-9
work_keys_str_mv AT amirsorayaieazar predictingpatientssentimentsaboutmedicationsusingartificialintelligencetechniques
AT saminbabaeirikan predictingpatientssentimentsaboutmedicationsusingartificialintelligencetechniques
AT aminnaemi predictingpatientssentimentsaboutmedicationsusingartificialintelligencetechniques
AT jamshidbagherzadehmohasefi predictingpatientssentimentsaboutmedicationsusingartificialintelligencetechniques
AT uffekockwiil predictingpatientssentimentsaboutmedicationsusingartificialintelligencetechniques