摘要
专病数据库作为医学研究的数据加速器对于科研型医院有重要意义,上海市肺科医院基于长期临床数据建立肺癌专病数据库进一步提高和巩固医院在肺科疾病方面的科研领先地位。利用大数据技术,克服临床数据结构多样性、质量不稳定等问题,项目建设中通过设计病种科研数据集和临床知识库利用数据平台自然语言处理(natural language processing,NLP)能力完成数据抽取转化。平台建立后,医院在3个月内处理5年以上临床数据,生成14万份肺癌专病病历数据。
As the data accelerator of medical research,the special disease database is of great significance for scientific research hospitals.Shanghai Pulmonary Hospital established the special disease database of lung cancer based on long-term clinical data to further improve and consolidate the leading position of the hospital in scientific research of pulmonary diseases.The big data technology is used to solve problems such as the diversity of the structure of clinical data and unstable quality.In the project construction,by designing the scientific research data set of the disease and clinical knowledge base,the NLP ability of the data platform is used to complete data extraction and conversion.After the establishment of the platform,the hospital processed clinical data of more than 5 years within 3 months and generated the data of 140,000 medical records of lung cancer.
作者
陈嘉旖
陶蓉
CHEN Jia-yi;TAO Rong(不详;Information Division,Shanghai Pulmonary Hospital,Shanghai 200433,P.R.C.)
出处
《中国数字医学》
2021年第11期39-42,共4页
China Digital Medicine
关键词
大数据
专病数据库
自然语言处理
疾病数据集
big data
special disease database
natural language processing
disease data set
