JMIR Med Inform
Department of Computer Engineering, College of IT Convergence, Gachon University, Seongnam, Republic of Korea.
Published: November 2024
Background: Social networking services (SNS) closely reflect the lives of individuals in modern society and generate large amounts of data. Previous studies have extracted drug information using relevant SNS data. In particular, it is important to detect adverse drug reactions (ADRs) early using drug surveillance systems. To this end, various deep learning methods have been used to analyze data in multiple languages in addition to English.
Objective: A cautionary drug that can cause ADRs in older patients was selected, and Korean SNS data containing this drug information were collected. Based on this information, we aimed to develop a deep learning model that classifies drug ADR posts based on a recurrent neural network.
Methods: In previous studies, ketoprofen, which has a high prescription frequency and, thus, was referred to the most in posts secured from SNS data, was selected as the target drug. Blog posts, café posts, and NAVER Q&A posts from 2005 to 2020 were collected from NAVER, a portal site containing drug-related information, and natural language processing techniques were applied to analyze data written in Korean. Posts containing highly relevant drug names and ADR word pairs were filtered through association analysis, and training data were generated through manual labeling tasks. Using the training data, an embedded layer of word2vec was formed, and a Bidirectional Long Short-Term Memory (Bi-LSTM) classification model was generated. Then, we evaluated the area under the curve with other machine learning models. In addition, the entire process was further verified using the nonsteroidal anti-inflammatory drug aceclofenac.
Results: Among the nonsteroidal anti-inflammatory drugs, Korean SNS posts containing information on ketoprofen and aceclofenac were secured, and the generic name lexicon, ADR lexicon, and Korean stop word lexicon were generated. In addition, to improve the accuracy of the classification model, an embedding layer was created considering the association between the drug name and the ADR word. In the ADR post classification test, ketoprofen and aceclofenac achieved 85% and 80% accuracy, respectively.
Conclusions: Here, we propose a process for developing a model for classifying ADR posts using SNS data. After analyzing drug name-ADR patterns, we filtered high-quality data by extracting posts, including known ADR words based on the analysis. Based on these data, we developed a model that classifies ADR posts. This confirmed that a model that can leverage social data to monitor ADRs automatically is feasible.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11601139 | PMC |
http://dx.doi.org/10.2196/45289 | DOI Listing |
Front Psychol
January 2025
School of Marxism, Jiangnan University, Wuxi, China.
Based on the General Aggression Model (GAM), this study explores the relationship between social media fatigue and online trolling behavior among Chinese college students, focusing on the mediating roles of relative deprivation and hostile attribution bias as key affective and cognitive mechanisms proposed by GAM. Using a cross-sectional survey design, data were collected from 349 college students from Guangdong via an online questionnaire. Key variables, including social media fatigue, relative deprivation, and hostile attribution bias, were measured using validated scales: the SNS Fatigue Questionnaire, the Personal Relative Deprivation Scale, the Word Sentence Association Paradigm for Hostility, and the revised Global Assessment of Internet Trolling.
View Article and Find Full Text PDFAnal Chem
January 2025
Los Alamos National Laboratory, Q-5, High Explosives Science and Technology, Los Alamos, New Mexico 87545, United States.
Alteration analysis (ALA), an unsupervised chemometric technique, was evaluated for its ability to discover statistically significant trends in chromatographic data sets. Recently introduced, adoption of ALA has been limited due to uncertainty regarding its sensitivity to minor changes, and there are no rules implementing ALA especially for multivariate data sets such as liquid or gas chromatography coupled to mass spectrometry. Using in-silico data sets, ALA limits of discovery for various signal-to-noises (S/Ns), rates of change across samples, and a number of samples were assessed.
View Article and Find Full Text PDFJ Appl Gerontol
January 2025
School of Social Work, University of Cincinnati, Cincinnati, OH, USA.
The daily Internet use among older adults has increased. This study examines how Internet usage affects depressive symptoms among older adults, focusing on gender differences. Using data from the 2015 National Health and Aging Trends Study ( = 6380), weighted multinomial logistic regression analysis was conducted.
View Article and Find Full Text PDFFront Psychol
December 2024
College of Business, Gachon University, Seongnam, Republic of Korea.
Purpose: This study examines the relationship between social networking sites addiction and pro-social behavior, considering the increasing importance of social networking sites in daily life. It explores the mediating role of Fear of Missing Out in this relationship and investigates the moderating role of basic psychological need satisfaction.
Research Design Data And Methodology: This study employed a snowball sampling method to conduct an online survey among social network users in China.
Curr Vasc Pharmacol
January 2025
Department of Cardiology, Ippokrateio University Hospital, Athens, Greece.
Introduction/objective: Emotional, mental, or psychological distress, defined as increased symptoms of depression, anxiety, and/or stress, is common in patients with chronic diseases, such as cardiovascular (CV) disease (CVD).
Methods: Literature was reviewed regarding data from studies and meta-analyses examining the impact of emotional stress on the occurrence and outcome of several CVDs (coronary disease, heart failure, hypertension, arrhythmias, stroke). These influences' pathophysiology and clinical spectrum are detailed, tabulated, and pictorially illustrated.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!
© LitMetric 2025. All rights reserved.