对来自法国社交媒体的患者数据的基于BERT的模型的评估
Emma Le Priol1,2,3, Manissa Talmatkadi3, Stéphane Schück3
1HeKA team, Inria, Inserm, France.
Studies in health technology and informatics
|August 23, 2024
概括
这项研究评估了从社交媒体中提取罕见疾病信息的模型. 卡梅伯特和卡梅伯特-生物表现相似,在表型和治疗方面表现优于DrBERT.
科学领域:
- 自然语言处理自然语言处理.
- 医疗信息学 医疗信息学
- 罕见疾病研究 罕见疾病研究
背景情况:
- 社交媒体为罕见疾病研究提供了有价值的信息.
- 从社交媒体中提取表型和治疗方法具有挑战性.
- 命名实体识别 (NER) 模型是解锁这些数据的关键.
研究的目的:
- 评估三个命名实体识别 (NER) 模型的性能.
- 评估模型的能力,从社交媒体数据中提取与罕见疾病相关的表型和治疗方法.
- 在这个特定的任务上比较CamemBERT,CamemBERT-bio和DrBERT.
主要方法:
- 在社交媒体信息数据集上训练了三个NER模型 (CamemBERT,CamemBERT-bio,DrBERT).
- 数据集包括关于发育性和性脑病以及常见疾病的信息.
- 对提取表型和治疗方法的评估模型性能.
主要成果:
- 卡梅伯特和卡梅伯特生物表现相似,略高于DrBERT.
- 社交媒体数据的模型性能低于结构化健康数据集.
- 该研究的重点是特定数据集中的NER性能.
结论:
- 卡梅伯特和卡梅伯特生物显示出从社交媒体中提取罕见疾病信息的希望.
- 需要对更大,更多样化的数据集进行进一步的研究,以确认模型的概括性.
- 与结构化数据相比,在非结构化社交媒体数据上的模型性能需要改进.
相关概念视频
Stereotype Content Model
13.1K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
13.1K
Classification of Illness
9.4K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
9.4K


