Modeling Method for Leveraging Data Quality in Healthcare Big Data
Madhu H. K.1, D. Ramesh2
1Madhu H. K.*, Assistant Professor, Department of Master of Computer Applications, Bangalore Institute of Technology, Bengaluru, India.
2Dr. D. Ramesh, Professor and HOD, Sri Siddaratha Academy of Higher Eduction, Tumkur, India.
Manuscript received on February 10, 2020. | Revised Manuscript received on February 23, 2020. | Manuscript published on March 10, 2020. | PP: 1373-1379 | Volume-9 Issue-5, March 2020. | Retrieval Number: E2528039520/2020©BEIESP | DOI: 10.35940/ijitee.E2528.039520
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: An accurate diagnosis of the healthcare-based Big Data will always demand a significant level of quality in its input data itself, which is a serious level of concern in the area of healthcare analytics. Review of existing approaches shows that there has been various learning-based approaches being used for disease diagnosis which often ignores various issues viz. data aggregation, presence of error prone data, accuracy etc. Therefore, this paper presents a novel framework which offers cost effective modeling of the aggregation process of healthcare-big data followed by facilitating solution towards identifying and rectifying all the positions within a database system where there are presence of an error. The proposed system offer a mechanism where the error-prone data has been identified and substituted with data of better quality in order to offer better analytical outcomes. The study offers a strong baseline in order to leverage the data quality in healthcare big data.
Keywords: Analytics, Big Data, Data Aggregation, Error, Healthcare, Medical Data.
Scope of the Article: Aggregation, Integration, and Transformation