📄 中文摘要
EQ-5D（欧洲质量生命五维度）是一种标准化的健康相关生活质量评估工具。在健康经济学中，系统文献综述（SLR）依赖于正确识别使用EQ-5D的出版物，但对大量科学文献的手动筛选既耗时又容易出错且不一致。研究通过对通用（BERT）和领域特定（SciBERT、BioBERT）预训练语言模型进行微调，并结合通过scispaCy模型提取的生物医学实体信息，旨在提高从摘要中检测EQ-5D的准确性。进行了九种实验设置，包括将三种scispaCy模型与三种PLM结合，并对结果进行了评估。
基于生物医学实体增强的预训练语言模型和多实例学习的EQ-5D分类
📄 English Summary
EQ-5D Classification Using Biomedical Entity-Enriched Pre-trained Language Models and Multiple Instance Learning
The EQ-5D (EuroQol 5-Dimensions) is a standardized instrument for evaluating health-related quality of life. In health economics, systematic literature reviews (SLRs) rely on the accurate identification of publications utilizing the EQ-5D; however, manual screening of large volumes of scientific literature is time-consuming, error-prone, and inconsistent. This study investigates the fine-tuning of general-purpose (BERT) and domain-specific (SciBERT, BioBERT) pre-trained language models (PLMs), enriched with biomedical entity information extracted via scispaCy models for each statement, to enhance EQ-5D detection from abstracts. Nine experimental setups are conducted, combining three scispaCy models with three PLMs, and the results are evaluated.