Uncovering Different CKD-Related Medical Issues Among African American Gender Groups Using Apriori

Yong-Mi Kim, Pranay Kathuria and Dursun Delen

Chapter 2 in Knowledge Discovery and Data Design Innovation:Proceedings of the International Conference on Knowledge Management (ICKM 2017), 2017, pp 27-45 from World Scientific Publishing Co. Pte. Ltd.

Abstract: African Americans have a higher rate of chronic kidney diseases (CKD) — four times that of Caucasians. This may be a result of African Americans having higher rates of diabetes complications than their Caucasian counterparts: note that diabetes is the leading cause of CKD. Due to the very high rate of CKD experienced by African Americans, this study focuses on them in order to observe their CKD related medical problems, and will analyze male and female groups as individual categories in order to uncover medical problems unique to either gender. For the research sample, we used African American kidney patients among type 2 diabetes patients. The data presented is extracted from the Cerner Health Facts® Data Warehouse. We employed the apriori method, a machine learning technique. This method is an unsupervised data mining method that allows researchers to discover relevant information buried in a large dataset. The findings, utilizing this method, show that the medical afflictions for male and female groups vary widely. More specifically, a medical issue derived from one gender group can over-represent the finding of the whole sample in the analysis. For example, at the dialysis stage, the finding of the whole sample for abnormal cocaine metabolite is 1.98%. On the other hand, the subgroup analysis shows that it is 6.22% for the male group, making it the number one medical problem in that category, while this same issue did not even make the 1% cut for the female group. Such discrepancies are also present in many other examples. By using these gendered subcategories this research informs both medical practitioners and academicians that one cannot simply combine both genders for analysis and use the aggregated results for treatment of both groups.

Keywords: Knowledge Discovery; Big Data; Data Science; Data Analytics; Innovation (search for similar items in EconPapers)
JEL-codes: O30 (search for similar items in EconPapers)
Date: 2017
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.worldscientific.com/doi/pdf/10.1142/9789813234482_0002 (application/pdf)
https://www.worldscientific.com/doi/abs/10.1142/9789813234482_0002 (text/html)
Ebook Access is available upon purchase.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:wschap:9789813234482_0002

Ordering information: This item can be ordered from

Access Statistics for this chapter

More chapters in World Scientific Book Chapters from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().