Healthc Inform Res.  2017 Oct;23(4):241-248. 10.4258/hir.2017.23.4.241.

Machine Learning to Compare Frequent Medical Problems of African American and Caucasian Diabetic Kidney Patients

• Kim YM
• Kathuria P
• Delen D

• KMID: 2396414
• DOI: http://doi.org/10.4258/hir.2017.23.4.241

Abstract

OBJECTIVES
End-stage renal disease (ESRD), which is primarily a consequence of diabetes mellitus, shows an exemplary health disparity between African American and Caucasian patients in the United States. Because diabetic chronic kidney disease (CKD) patients of these two groups show differences in their medical problems, the markers leading to ESRD are also expected to differ. The purpose of this study was, therefore, to compare their medical complications at various levels of kidney function and to identify markers that can be used to predict ESRD.
METHODS
The data of type 2 diabetic patients was obtained from the 2012 Cerner database, which totaled 1,038,499 records. The data was then filtered to include only African American and Caucasian outpatients with estimated glomerular filtration rates (eGFR), leaving 4,623 records. A priori machine learning was used to discover frequently appearing medical problems within the filtered data. CKD is defined as abnormalities of kidney structure, present for >3 months.
RESULTS
This study found that African Americans have much higher rates of CKD-related medical problems than Caucasians for all five stages, and prominent markers leading to ESRD were discovered only for the African American group. These markers are high glucose, high systolic blood pressure (BP), obesity, alcohol/drug use, and low hematocrit. Additionally, the roles of systolic BP and diastolic BP vary depending on the CKD stage.
CONCLUSIONS
This research discovered frequently appearing medical problems across five stages of CKD and further showed that many of the markers reported in previous studies are more applicable to African American patients than Caucasian patients.

Keyword

Machine Learning; Electronic Health Records, Renal Insufficiency; Kidney Failure; Glomerular Filtration Rate

MeSH Terms

African Americans
Blood Pressure
Diabetes Mellitus
Glomerular Filtration Rate
Glucose
Hematocrit
Humans
Kidney Failure, Chronic
Kidney*
Machine Learning*
Obesity
Outpatients
Renal Insufficiency
Renal Insufficiency, Chronic
United States
Glucose

Figure

• 

  Figure 1 Graphic depiction of the knowledge discovery process.

Reference

1. Agodoa L, Eggers P. Racial and ethnic disparities in end-stage kidney failure-survival paradoxes in African-Americans. Semin Dial. 2007; 20(6):577–585.

2. National Institute of Diabetes and Digestive and Kidney Diseases. Diabetic kidney disease: What is diabetic kidney disease? [Internet]. Bethesda (MD): National Institute of Diabetes and Digestive and Kidney Diseases;c2017. cited at 2017 Mar 28. Available from: https://www.niddk.nih.gov/health-information/diabetes/overview/preventing-problems/diabetic-kidney-disease.

3. National Institute of Diabetes and Digestive and Kidney Diseases. High blood pressure & kidney disease [Internet]. Bethesda (MD): National Institute of Diabetes and Digestive and Kidney Diseases;c2017. cited at 2017 Mar 28. Available from: https://www.niddk.nih.gov/healthinformation/kidney-disease/chronic-kidney-diseaseckd/high-blood-pressure.

4. National Institute of Diabetes and Digestive and Kidney Diseases. Anemia and chronic kidney disease [Internet]. Bethesda (MD): National Institute of Diabetes and Digestive and Kidney Diseases;c2017. cited at 2017 Mar 28. Available from: https://www.kidney.org.

5. Botev R, Mallie JP, Wetzels JF, Couchoud C, Schuck O. The clinician and estimation of glomerular filtration rate by creatinine-based formulas: current limitations and quo vadis. Clin J Am Soc Nephrol. 2011; 6(4):937–950.

6. Dinwiddie LC, Burrows-Hudson S, Peacock EJ. Stage 4 chronic kidney disease: preserving kidney function and preparing patients for stage 5 kidney disease. Am J Nurs. 2006; 106(9):40–51.

7. Lakshman SG, Ravikumar P, Kar G, Das D, Bhattacharjee K, Bhattacharjee P. A comparative study of neurological complications in chronic kidney disease with special reference to its stages and haemodialysis status. J Clin Diagn Res. 2016; 10(12):OC01–OC04.

8. United States Renal Data System. Chapter 2: identification and care of patients with CKD [Internet]. Ann Arbor (MI): United States Renal Data System;c2016. cited 2017 May 5. Available from: https://www.usrds.org/2016/view/v1_02.aspx.

9. Ceriello A. The glucose triad and its role in comprehensive glycaemic control: current status, future management. Int J Clin Pract. 2010; 64(12):1705–1711.

10. Hintsa S, Dube L, Abay M, Angesom T, Workicho A. Determinants of diabetic nephropathy in Ayder Referral Hospital, Northern Ethiopia: a case-control study. PLoS One. 2017; 12(4):e0173566.

11. de Lusignan S. Informatics as tool for quality improvement: rapid implementation of guidance for the management of chronic kidney disease in England as an exemplar. Healthc Inform Res. 2013; 19(1):9–15.

12. Yamamoto T, Miyazaki M, Nakayama M, Yamada G, Matsushima M, Sato M, et al. Impact of hemoglobin levels on renal and non-renal clinical outcomes differs by chronic kidney disease stages: the Gonryo study. Clin Exp Nephrol. 2016; 20(4):595–602.

13. Miranda E, Irwansyah E, Amelga AY, Maribondang MM, Salim M. Detection of cardiovascular disease risk's level for adults using naive Bayes classifier. Healthc Inform Res. 2016; 22(3):196–205.

14. Moon M, Lee SK. Applying of decision tree analysis to risk factors associated with pressure ulcers in long-term care facilities. Healthc Inform Res. 2017; 23(1):43–52.

15. Tsai CW, Ting IW, Yeh HC, Kuo CC. Longitudinal change in estimated GFR among CKD patients: a 10-year follow-up study of an integrated kidney disease care program in Taiwan. PLoS One. 2017; 12(4):e0173843.

16. Healthline. ALP (alkaline phosphatase level) test [Internet]. San Francisco (CA): Healthline Media;c2017. cited at 2017 Mar 28. Available from: http://www.healthline.com/health/alp.

17. Kim JH, Park HS, Ko SY, Hong SN, Sung IK, Shim CS, et al. Diabetic factors associated with gastrointestinal symptoms in patients with type 2 diabetes. World J Gastroenterol. 2010; 16(14):1782–1787.

18. Idorn T, Knop FK, Jorgensen M, Holst JJ, Hornum M, Feldt-Rasmussen B. Gastrointestinal factors contribute to glucometabolic disturbances in nondiabetic patients with end-stage renal disease. Kidney Int. 2013; 83(5):915–923.

19. Taliericio JJ, Navaneethan SD. Serum alkaline phosphatase has prognostic importance in chronic kidney disease: increasing levels signal higher risks of ESRD, mortality [Internet]. Cleveland (OH): Cleveland Clinic;c2014. cited at 2017 Mar 28. Available from: https://consultqd.clevelandclinic.org/2014/12/serum-alkalinephosphatase-has-prognostic-importance-in-chronickidney-disease/.

20. Chang WX, Xu N, Kumagai T, Shiraishi T, Kikuyama T, Omizo H, et al. The impact of normal range of serum phosphorus on the incidence of end-stage renal disease by a propensity score analysis. PLoS One. 2016; 11(4):e0154469.

21. DSa J, Shetty S, Bhandary RR, Rao AV. Association between serum cystatin C and creatinine in chronic kidney disease subjects attending a tertiary health care centre. J Clin Diagn Res. 2017; 11(4):BC09–BC12.

22. National Kidney Foundation. African Americans and kidney disease [Internet]. New York (NY): National Kidney Foundation;c2017. cited at 2017 Mar 29. Available from: https://www.kidney.org/atoz/content/AfricanAmericans-KD.

23. Tussing-Humphreys LM, Thomson JL, Onufrak SJ. A church-based pilot study designed to improve dietary quality for rural, lower Mississippi Delta, African American adults. J Relig Health. 2015; 54(2):455–469.

24. Tucker KL, Maras J, Champagne C, Connell C, Goolsby S, Weber J, et al. A regional food-frequency questionnaire for the US Mississippi Delta. Public Health Nutr. 2005; 8(1):87–96.

25. Zyga S, Christopoulou G, Malliarou M. Malnutritioninflammation-atherosclerosis syndrome in patients with end-stage renal disease. J Ren Care. 2011; 37(1):12–15.

26. MedlinePlus. BUN - blood test [Internet]. Bethesda (MD): US National Library of Medicine;c2017. cited at 2017 Mar 28. Available from: https://medlineplus.gov/ency/article/003474.htm.

27. Kaslow J. Anion gap [Internet]. Santa Ana (CA): drkaslow.com;c2017. cited at 2017 Mar 28. Available from: http://www.drkaslow.com/html/anion_gap.html.

28. Orth SR. Effects of smoking on systemic and intrarenal hemodynamics: influence on renal function. J Am Soc Nephrol. 2004; 15:Suppl 1. S58–S63.

29. American Association for Clinical Chemistry. Urine albumin and albumin/creatinine ratio [Internet]. Washington (DC): American Association for Clinical Chemistry;c2017. cited at 2017 May 23. Available from: https://labtestsonline.org/understanding/analytes/microalbumin/tab/test/.