An objective-driven analyses framework utilizing the characters of medical big data: the roles anti-platelet agents play in the associations between hypertension and stroke as an application

Konferenz: BIBE 2018 - International Conference on Biological Information and Biomedical Engineering
06.06.2018 - 08.06.2018 in Shanghai, China

Tagungsband: BIBE 2018

Seiten: 5Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Wang, Yingying; Li, Qi; Li, Ye; Cai, Yunpeng (Research Center for Biomedical Information Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences & Shenzhen Engineering Laboratory of Health Big Data Analyses Technology, Shenzhen, China)
Zhang, Jiandong (School of Software Engineering (SSE) of the University of Science and Technology of China (USTC), Suzhou, China)
Lin, Denan; Zheng, Jing (Shenzhen Medical Information Center, Shenzhen, China)
Wang, Lihua (Department of Neurology, The Second Affiliated Hospital, Harbin Medical University, Harbin, China)

The fast developments of big data have brought great opportunities and challenges to different fields including medicine. The ‘volume, velocity, variety, and veracity’ characters of medical big data may identify relationships between patients that a single data set alone cannot discover. Compared with the traditional hypothesis-driven studies on small data sets, big data analyses have the possibility to facilitate new discoveries across different traditionally studies. In this paper, we proposed an objective-driven analyses framework utilizing the characters of medical big data to validate the reproducibility and accuracy, which is theoretical basis of medical big data related studies. A case study aiming to explore the roles different anti-platelet agents play in preventing hypertensive patients from suffering stroke was given to illustrate the available and detailed procedure of the framework. Our results proved that the framework we proposed could get same or similar results with traditional epidemiology experiment-based studies. This indicated us this framework could be used in more fields since it could get accurate results while saving the costs of money and time.