Knowledge discovery from a more than a decade studies on healthcare Big Data systems: a scientometrics study
Annually, lots of research papers are published in scientific journals around the world. The knowledge of the status of research is a prerequisite for research planning and policy making. This type of knowledge could be gained through a scientometrics study on the published literature that analyzes...
Saved in:
Published in: | Journal of big data Vol. 6; no. 1; pp. 1 - 15 |
---|---|
Main Authors: | , , |
Format: | Journal Article |
Language: | English |
Published: |
Cham
Springer International Publishing
31-01-2019
Springer Nature B.V SpringerOpen |
Subjects: | |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Annually, lots of research papers are published in scientific journals around the world. The knowledge of the status of research is a prerequisite for research planning and policy making. This type of knowledge could be gained through a scientometrics study on the published literature that analyzes research products in a scientific field. Always healthcare was a permanent concern of researchers and also rapidly expanding field of Big Data analytics has started to play a pivotal role in the evolution of healthcare practices and research. It leads attracting attention from academia, industry and even governments around the world to “Big data in Healthcare”. Therefore, this paper has done a meta-analysis on published researches methodology in this field in the period of 2008–2018. Statistical finding shows the “Meta-analysis and evidence” is the most used methodology in published papers. We applied data mining techniques for predicting using methodologies in the various databases to achieving knowledge discovery in the field. Naïve Bayes classifier in RapidMiner has been applied and results show eight main categories for words used in papers while “Developing methods to evaluate of care” averagely is the most intended using methodology for publishing papers and “Agent-based modeling” in nature is most using methodology and could be better predicted. |
---|---|
ISSN: | 2196-1115 2196-1115 |
DOI: | 10.1186/s40537-018-0167-y |