临床实验室数据存储系统的自然语言处理:呼吸系统病毒的实施和评估
Elham Dolatabadi1,2,3, Branson Chen4, Sarah A Buchan3,4,5,6
1Vector Institute, Toronto, ON, Canada.
JMIR AI
|June 14, 2024
概括
一个新的深度学习自然语言处理 (NLP) 模型有效地从实验室报告中提取数据. 这种方法为手动数据提取提供了一个可扩展的替代方案,以改进二级数据的使用.
科学领域:
- 医疗信息学 医疗信息学
- 计算生物学 计算生物学
- 人工智能的人工智能
背景情况:
- 实验室数据存储库的数量和复杂性在不断增长,这使得手动提取二次用途的数据具有挑战性.
- 自然语言处理 (NLP) 为从非结构化文本中提取临床上有意义的信息提供了自动化解决方案.
研究的目的:
- 评估基于深度学习的NLP模型,作为资源密集型基于规则的信息提取系统的替代方案.
- 开发和评估NLP模型,从基于文本的实验室报告中提取知识.
主要方法:
- 对14种呼吸道病毒的87,500份实验室报告进行了训练.
- 该模型被训练将报告分为24个细粒度和6个粗粒度标签.
- 对内部和外部测试集的稳定性,变异性和通用性进行了性能评估.
主要成果:
- 在内部,历史和外部测试集中,NLP模型在所有类别中实现了微平均F1分数> 94%.
- 在内部和历史数据上观察到更高的精度和回忆,由于数据不平衡而导致的性能变化.
- 与测试病例相比,该模型的性能在病毒检测病例中较低 (最低F1得分为57%).
结论:
- 深度学习NLP模型显示出从实验室报告中提取信息的重大前景.
- 这些模型提供可扩展,及时和实用的访问高质量的编码实验室数据.
- 集成到实验室信息系统可以提高数据的可访问性和实用性.
相关概念视频
The Respiratory System
The respiratory system is comprised of the organs that enable breathing. Air enters the nostrils and mouth, followed by the pharynx (throat) and larynx (voice box), which lead to the trachea (windpipe). In the thoracic cavity, the trachea splits into two bronchi that allow air to enter the lungs. The bronchi split into progressively smaller bronchioles and terminate in small groups of tiny sacs in the lungs called alveoli, where gas exchange occurs.
Common Respiratory Disorders
Respiratory disorders, a prevalent health concern globally, are generally divided into two primary categories: upper and lower respiratory tract disorders. The categorization is based on the area of the respiratory system they affect.
Upper respiratory disorders impact the airways above the vocal cords, encompassing areas like the nose, sinuses, and throat. Various conditions fall under this category, including the common cold and allergic rhinitis. These disorders can stem from several causes,...
Upper respiratory disorders impact the airways above the vocal cords, encompassing areas like the nose, sinuses, and throat. Various conditions fall under this category, including the common cold and allergic rhinitis. These disorders can stem from several causes,...
Respiratory Syncytial Virus Disease
Human respiratory syncytial virus (RSV) is a widespread pathogen that primarily targets infants and young children but also poses a serious health risk to elderly and immunocompromised individuals. Belonging to the Pneumoviridae family, RSV is a negative-sense, single-stranded RNA virus within the Pneumovirus genus. Its global health burden is significant, with millions of cases annually resulting in hospitalizations and mortality, particularly in resource-limited settings. Although most...


