A5090815016- Health Literacy and Information Accessibility
- Mental Health via Writing
- Topic Modeling
- Pharmacovigilance and Adverse Drug Reactions
- Social Media in Health Education
- Traditional Chinese Medicine Studies
- Machine Learning in Healthcare
- Chemotherapy-related skin toxicity
- Biomedical Text Mining and Ontologies
- Cancer Treatment and Pharmacology
Nara Institute of Science and Technology
2024
Early detection and management of adverse drug reactions (ADRs) is crucial for improving patients’ quality life. Hand-foot syndrome (HFS) one the most problematic ADRs cancer patients. Recently, an increasing number patients post their daily experiences to internet community, example in blogs, where potential ADR signals not captured through routine clinic visits can be described. Therefore, this study aimed identify with ADRs, focusing on HFS, from blogs by using natural language processing...
Patients with breast cancer have a variety of worries and need multifaceted information support. Their accumulated posts on social media contain rich descriptions their daily concerning issues such as treatment, family, finances. It is important to identify these help patients resolve obtain reliable information.This study aimed extract classify multiple from text generated by using Bidirectional Encoder Representations From Transformers (BERT), context-aware natural language processing...
Adverse event (AE) management is crucial to improve anti-cancer treatment outcomes, but it reported that some AE signals can be missed in clinical visits. Thus, monitoring seamlessly, including events outside hospitals, would helpful for early intervention. Here we investigated how detect from texts written by cancer patients themselves developing deep-learning (DL) models classify posts mentioning AEs according severity grade, order focus on those might need immediate interventions. Using...
Abstract Adverse event (AE) management is important to improve anti-cancer treatment outcomes, but it known that some AE signals can be missed during clinical visits. In particular, AEs affect patients’ activities of daily living (ADL) need careful monitoring as they may require immediate medical intervention. This study aimed build deep-learning (DL) models for extracting limiting ADL from narratives. The data source was blog posts written in Japanese by breast cancer patients. After...
Narratives posted on the internet by patients contain a vast amount of information about various concerns. This study aimed to extract multiple concerns from interviews with breast cancer using natural language processing (NLP) model bidirectional encoder representations transformers (BERT). A total 508 interview transcriptions written in Japanese were labeled five types concern labels: "treatment," "physical," "psychological," "work/financial," and "family/friends." The texts used create...
<sec> <title>BACKGROUND</title> Patients with breast cancer have a variety of worries and need multifaceted information support. Their accumulated posts on social media contain rich descriptions their daily concerning issues such as treatment, family, finances. It is important to identify these help patients resolve obtain reliable information. </sec> <title>OBJECTIVE</title> This study aimed extract classify multiple from text generated by using Bidirectional Encoder Representations From...