Abstract | ||
---|---|---|
Comparative effectiveness research (CER) is a new clinical study model featured by its strategic framework consists of four categories and three themes. The core strategy of CER is to conduct observational longitude research supported by electronic registry and large database based on real world practice. Since CER studies do not uses a classic randomized control trial (RCT) design, the well-developed data analytic methods for RCTs are challenged. The data groups which are not acquired from the same time point, or have significant difference at the baseline are unable to be compared by the classic differential statistical methods, or the outcome will be without robust statistical support. In this paper, we described the characteristics of the Zheng studies of Chinese medicine. Then some data analytic methods based on machine learning are introduced as potential solutions for the data processing in the CER research of Chinese medicine. Finally, a new strategic framework is introduced to establish the CER methodology for Chinese medicine. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/BIBMW.2012.6470360 | BIBM Workshops |
Keywords | Field | DocType |
chinese medicine,cer methodology,comparative effectiveness research,zheng study,clinical study model,learning (artificial intelligence),strategic framework,comparative effective research,observational longitude research,data processing,cer research,data analytic methods,zheng studies,well-developed data,data group,data mining,cer,medical computing,cer study,machine learning,large database,data analytic method,electronic registry,learning artificial intelligence | Data science,Data mining,Observational study,Computer science,Randomized controlled trial,Traditional Chinese medicine,Comparative effectiveness research,Clinical study,Bioinformatics | Conference |
ISBN | Citations | PageRank |
978-1-4673-2744-2 | 0 | 0.34 |
References | Authors | |
2 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
YeFeng Cai | 1 | 4 | 1.62 |
Zhaohui Liang | 2 | 26 | 15.31 |
Yue Zhang | 3 | 184 | 53.93 |