Abstract
Purpose
Timely risk assessment of chronic kidney disease (CKD) and proper community-based CKD monitoring are important to prevent patients with potential risk from further kidney injuries. As many symptoms are associated with the progressive development of CKD, evaluating risk of CKD through a set of clinical data of symptoms coupled with multivariate models can be considered as an available method for prevention of CKD and would be useful for community-based CKD monitoring.
Methods
Three common used multivariate models, i.e., K-nearest neighbor (KNN), support vector machine (SVM), and soft independent modeling of class analogy (SIMCA), were used to evaluate risk of 386 patients based on a series of clinical data taken from UCI machine learning repository. Different types of composite data, in which proportional disturbances were added to simulate measurement deviations caused by environment and instrument noises, were also utilized to evaluate the feasibility and robustness of these models in risk assessment of CKD.
Results
For the original data set, three mentioned multivariate models can differentiate patients with CKD and non-CKD with the overall accuracies over 93 %. KNN and SVM have better performances than SIMCA has in this study. For the composite data set, SVM model has the best ability to tolerate noise disturbance and thus are more robust than the other two models.
Conclusions
Using clinical data set on symptoms coupled with multivariate models has been proved to be feasible approach for assessment of patient with potential CKD risk. SVM model can be used as useful and robust tool in this study.
Similar content being viewed by others
References
Zhang LX, Wang F, Wang L et al (2012) Prevalence of chronic kidney disease in China: a cross-sectional survey. Lancet 379:815–822
Cueto-Manzano AM, Cortes-Sanabria L, Martínez-Ramirez HR et al (2014) Prevalence of chronic kidney disease in an adult population. Arch Med Res 45:507–513
Kidney Disease: Improving Global Outcomes (KDIGO) CKD Work Group (2013) KDIGO 2012 clinical practice guideline for the evaluation and management of chronic kidney disease. Kidney Int Suppl 3:1–150
National Institute for Health and Care Excellence (2014) Chronic Kidney Disease: early identification and management of chronic kidney disease in adults in primary and secondary care. Clinical Guidelines, London, National Institute for Health and Care Excellence
Wish JB (2014) 57-anemia and other hematologic complications of chronic kidney disease. In: Gilbert SJ (ed) National kidney foundation primer on kidney diseases, 6th edn. Elsevier Saunders, Philadelphia, pp 497–506
Kutuby F, Wang S, Desai C et al (2015) Anemia of chronic kidney disease. DM Dis Mon 61:421–424
Fernandez H, Singh AK (2015) Chapter 51—management of anemia in chronic kidney disease. In: Kimmel PL (ed) Chronic renal disease. Academic Press, New York, pp 624–633
Metsarinne K, Broijersen A, Kantola I et al (2015) High prevalence of chronic kidney disease in Finnish patients with type 2 diabetes treated in primary care. Prim Care Diabetes 9:31–38
Schroeder EB, Powers JD, O’Connor PJ et al (2015) Prevalence of chronic kidney disease among individuals with diabetes in the SUPREME-DM project, 2005–2011. J Diabetes Complicat 29:637–643
Afkarian M, Sachs MC, Kestenbaum B et al (2013) Kidney disease and increased mortality risk in type 2 diabetes. J Am Soc Nephro 24:302–308
Campese VM (2014) Pathophysiology of resistant hypertension in chronic kidney disease. Semin Nephrol 34:571–576
Gargiulo R, Suhail F, Lerma EV (2015) Hypertension and chronic kidney disease. DM Dis Mon 61:387–395
Kumar N, Bansal A, Sarma GS et al (2014) Chemometrics tools used in analytical chemistry: an overview. Talanta 123:186–199
Lavine BK, Workman J (2013) Chemometrics. Anal Chem 85:705–714
Brereton RG (2015) Pattern recognition in chemometrics. Chemom Intell Lab Syst 149:90–96
Jabbar MA, Deekshatulu BL, Chandra P (2013) Classification of heart disease using k- nearest neighbor and genetic algorithm. Procedia Technol 10:85–94
Wang GY, Ma MY, Zhang ZY et al (2013) A novel DPSO-SVM system for variable interval selection of endometrial tissue sections by near-infrared spectroscopy. Talanta 112:136–142
Zhang JJ, Zhang ZY, Xiang YH et al (2011) An emphatic orthogonal signal correction-support vector machine method for the classification of tissue sections of endometrial carcinoma by near infrared spectroscopy. Talanta 83:1401–1409
Khanmohammadi M, Garmarudi AB, Ramin M et al (2013) Diagnosis of renal failure by infrared spectrometric analysis of human serum samples and soft independent modeling of class analogy. Microchem J 106:67–72
Lichman M (2013) UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science [The clinical data are available at http://archive.ics.uci.edu/ml/datasets/Chronic_Kidney_Disease]
Tominaga Y (1999) Comparative study of class data analysis with PCA-LDA, SIMCA, PLS, ANNs, and k-NN. Chemom Intell Lab Syst 49:105–115
Li C, Yang SC, Guo QS et al (2015) Geographical traceability of marsdenia tenacissima by Fourier transform infrared spectroscopy and chemometrics. Spectrochim Acta Part A 152:391–396
Cortes CC, Vapnik V (1995) Support-vector network. Mach Learn 20:273–297
Harrington PB (2015) Support vector machine classification trees. Anal Chem 87:11065–11071
Maesschalck RD, Candolfi A, Massart DL et al (1999) Decision criteria for soft independent modeling of class analogy applied to near infrared data. Chemom Intell Lab Syst 47:65–77
Harrington PB (2006) Statistical validation of classification and calibration models using bootstrapped Latin partitions. Trend Anal Chem 25:1112–1124
Acknowledgments
The UCI Machine Learning Repository and the CKD data donators are thanked.
Funding
This work is partly supported by the National Natural Science Foundation of China (21275101). The funding agency had no role in the study design; collection, analysis, and interpretation of data; writing the report; and the decision to submit this paper for publication.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Informed consent
Informed consent was obtained from all individual participants included in the study.
Rights and permissions
About this article
Cite this article
Chen, Z., Zhang, X. & Zhang, Z. Clinical risk assessment of patients with chronic kidney disease by using clinical data and multivariate models. Int Urol Nephrol 48, 2069–2075 (2016). https://doi.org/10.1007/s11255-016-1346-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11255-016-1346-4