CoChat
Sign Up
Cited by 24Artificial Intelligence in HealthcareChronic Kidney Disease and DiabetesMachine Learning in Healthcare

Predicting diabetic nephropathy in type 2 diabetic patients using machine learning algorithms

Open access
Hosseini Sarkhosh, Seyyed Mahdi, Esteghamati, Alireza, Hemmatabadi, Mahboobeh, Daraei, Morteza·2022·Journal of Diabetes & Metabolic Disorders
DOI 10.1007/s40200-022-01076-2PMC PMC9672147
Open this paper in CoChat — free account

Abstract

Background Global healthcare centers today are challenged by the dramatic increase in the prevalence of diabetes. Also, complications from diabetes are a major cause of deaths worldwide. One of the most frequent microvascular complications in diabetic patients is diabetic nephropathy (DN) which is the leading cause of death and end-stage renal disease (ESRD). Despite the different risk factors for DN identified in previous research, machine learning (ML) methods can help determine the importance of the predictors and prioritize them. Objective The main focus of this investigation is on predicting the incidence of DN in type 2 diabetic mellitus (T2DM) patients using ML algorithms. Methods Demographic information, laboratory results, and examinations on 6235 patients with T2DM covering a period of 10 years (2011-2020) were extracted from the electronic database of the Diabetes Clinic of the Imam Khomeini Hospital Complex (IKHC) in Iran. Recursive feature elimination using the cross-validation (RFECV) technique was then used with the three classification algorithms to select the important risk factors. Next, five ML algorithms were used to construct a predictive model for DN in T2DM patients. Finally, the results of the algorithms were evaluated according to the AUC criteria and the one with the best performance in terms of prediction and classification was selected. Results The 18 DN risk factors selected by RFECV were age, diabetes duration, BMI, SBP, hypertension, retinopathy, ALT, CVD, 2HPP, uric acid, HbA1c, waist-to-hip ratio, cholesterol, LDL, HDL, FBS, triglyceride, and serum insulin. Based on a 10-fold cross-validation, the best performance among the five classification algorithms was that of the random forest with 85% AUC. Conclusions This investigation validates the known risk factors for DN and emphasizes the importance of controlling the blood pressure, weight, cholesterol, and blood sugar of T2DM patients. In addition, as an example of the application of ML approaches in medical predictions, the findings of this study demonstrate the advantages of using these techniques.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s40200-022-01076-2

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 44 · Cited by 24

Research works printed but not linked: 42

  1. [1]Rodriguez-Romero V, Bergstrom RF, Decker BS, Lahu G, Vakilynejad M, Bies RR. Prediction of nephropathy in type 2 diabetes: an analysis of the ACCORD trial applying machine learning techniques. Clin Transl Sci. Wiley Online Library; 2019;12:519–528. [DOI] [PMC free article] [PubMed]
  2. [2]Zhao N, Gao JD, Zhang HL. Research progress of glycosylated haemoglobin as a diagnostic criterion for diabetes. Chin Clin Res. 2015;1:127–128. [Google Scholar]
  3. [3]Ahmad J. Management of diabetic nephropathy: recent progress and future perspective. Diabetes Metab Syndr Clin Res Rev. Elsevier; 2015;9:343–358. [DOI] [PubMed]
  4. [4]Radcliffe NJ, Seah J, Clarke M, MacIsaac RJ, Jerums G, Ekinci EI. Clinical predictive factors in diabetic kidney disease progression. J Diabetes Investig. Wiley Online Library; 2017;8:6–18. [DOI] [PMC free article] [PubMed]
  5. [5]Narres M, Claessen H, Droste S, Kvitkina T, Koch M, Kuss O, et al. The incidence of end-stage renal disease in the diabetic (compared to the non-diabetic) population: a systematic review. PLoS One. Public Library of Science San Francisco, CA USA; 2016;11:e0147329. [DOI] [PMC free article] [PubMed]
  6. [6]Rao V, Rao LBV, Tan SH, Candasamy M, Bhattamisra SK. Diabetic nephropathy: an update on pathogenesis and drug development. Diabetes Metab Syndr Clin Res Rev. Elsevier; 2019;13:754–762. [DOI] [PubMed]
  7. [7]Gans D, Kralewski J, Hammons T, Dowd B. Medical groups’ adoption of electronic health records and information systems. Health Aff. Project HOPE-The People-to-People Health Foundation, Inc.; 2005;24:1323–33. [DOI] [PubMed]
  8. [9]Magoulas GD, Prentza A. Machine learning in medical applications. Adv course Artif Intell. Springer; 1999. p. 300–307.
  9. [10]Kavakiotis I, Tsave O, Salifoglou A, Maglaveras N, Vlahavas I, Chouvarda I. Machine learning and data mining methods in diabetes research. Comput Struct Biotechnol J. Elsevier; 2017;15:104–116. [DOI] [PMC free article] [PubMed]
  10. [11]Dinh A, Miertschin S, Young A, Mohanty SD. A data-driven approach to predicting diabetes and cardiovascular disease with machine learning. BMC Med Inform Decis Mak. Springer; 2019;19:211. [DOI] [PMC free article] [PubMed]
  11. [14]Yu W, Liu T, Valdez R, Gwinn M, Khoury MJ. Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes. BMC Med Inform Decis Mak. Springer; 2010;10:16. [DOI] [PMC free article] [PubMed]
  12. [15]Semerdjian J, Frank S. An ensemble classifier for predicting the onset of type II diabetes. arXiv Prepr arXiv170807480. 2017;
  13. [16]Teimouri M, Ebrahimi E, Alavinia SM. Comparison of various machine learning methods in diagnosis of hypertension in diabetics with/without consideration of costs. Iran J Epidemiol. 2016;11:46–54. [Google Scholar]
  14. [17]Parthiban G, Srivatsa SK. Applying machine learning methods in diagnosing heart disease for diabetic patients. Int J Appl Inf Syst. Citeseer; 2012;3:25–30.
  15. [18]Cho BH, Yu H, Kim K-W, Kim TH, Kim IY, Kim SI. Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods. Artif Intell Med. Elsevier; 2008;42:37–53. [DOI] [PubMed]
  16. [20]Chang W, Liu Y, Xiao Y, Yuan X, Xu X, Zhang S, et al. A machine-learning-based prediction method for hypertension outcomes based on medical data. Diagnostics. Multidisciplinary Digital Publishing Institute; 2019;9:178. [DOI] [PMC free article] [PubMed]
  17. [21]Choudhury A, Gupta D. A survey on medical diagnosis of diabetes using machine learning techniques. Recent Dev Mach Learn data Anal. Springer; 2019. p. 67–78.
  18. [22]American Diabetes Association. Diagnosis and classification of diabetes mellitus. Diabetes Care. Am Diabetes Assoc; 2014;37:S81–S90. [DOI] [PubMed]
  19. [23]Tziomalos K, Athyros VG. Diabetic nephropathy: new risk factors and improvements in diagnosis. Rev Diabet Stud RDS. Society for Biomedical Diabetes Research; 2015;12:110. [DOI] [PMC free article] [PubMed]
  20. [25]Lou J, Jing L, Yang H, Qin F, Long W, Shi R. Risk factors for diabetic nephropathy complications in community patients with type 2 diabetes mellitus in Shanghai: logistic regression and classification tree model analysis. Int J Health Plann Manage. Wiley Online Library; 2019;34:1013–1024. [DOI] [PubMed]
  21. [26]Granitto PM, Furlanello C, Biasioli F, Gasperi F. Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial products. Chemom Intell Lab Syst. Elsevier; 2006;83:83–90.
  22. [27]Lundberg SM, Erion G, Chen H, DeGrave A, Prutkin JM, Nair B, et al. From local explanations to global understanding with explainable AI for trees. Nat Mach Intell. Nature Publishing Group; 2020;2:56–67. [DOI] [PMC free article] [PubMed]
  23. [28]Rossing K, Christensen PK, Hovind P, Tarnow L, Rossing P, Parving H-H. Progression of nephropathy in type 2 diabetic patients. Kidney Int. Elsevier; 2004;66:1596–1605. [DOI] [PubMed]
  24. [29]Zoppini G, Targher G, Chonchol M, Ortalda V, Negri C, Stoico V, et al. Predictors of estimated GFR decline in patients with type 2 diabetes and preserved kidney function. Clin J Am Soc Nephrol Am Soc Nephrol. 2012;7:401–408. doi: 10.2215/CJN.07650711. [DOI] [PubMed] [Google Scholar] · DOI
  25. [30]Elley CR, Robinson T, Moyes SA, Kenealy T, Collins J, Robinson E, et al. Derivation and validation of a renal risk score for people with type 2 diabetes. Diabetes Care. Am Diabetes Assoc; 2013;36:3113–3120. [DOI] [PMC free article] [PubMed]
  26. [31]Coresh J, Astor BC, Greene T, Eknoyan G, Levey AS. Prevalence of chronic kidney disease and decreased kidney function in the adult US population: third National Health and nutrition examination survey. Am J kidney Dis. Elsevier; 2003;41:1–12. [DOI] [PubMed]
  27. [32]Zhou JJ, Coleman R, Holman RR, Reaven P. Long-term glucose variability and risk of nephropathy complication in UKPDS, ACCORD and VADT trials. Diabetologia. Springer; 2020;63:2482–2485. [DOI] [PMC free article] [PubMed]
  28. [33]Larroumet A, Molina O, Foussard N, Monlun M, Blanco L, Mohammedi K, et al. Early worsening of diabetic nephropathy in type 2 diabetes after rapid improvement in chronic severe hyperglycemia. Diabetes Care 2021; 44: e55–e56. Diabetes Care. Am Diabetes Assoc; 2021;44:e110–e111. [DOI] [PubMed]
  29. [34]Butt A, Mustafa N, Fawwad A, Askari S, Haque MS, Tahir B, et al. Relationship between diabetic retinopathy and diabetic nephropathy; a longitudinal follow-up study from a tertiary care unit of Karachi, Pakistan. Diabetes Metab Syndr Clin Res Rev. Elsevier; 2020;14:1659–1663. [DOI] [PubMed]
  30. [35]Wu H-Q, Wei X, Yao J-Y, Qi J-Y, Xie H-M, Sang A-M, et al. Association between retinopathy, nephropathy, and periodontitis in type 2 diabetic patients: a Meta-analysis. Int J Ophthalmol. Press of International Journal of Ophthalmology; 2021;14:141. [DOI] [PMC free article] [PubMed]
  31. [36]Verani RR. Obesity-associated focal segmental glomerulosclerosis: pathological features of the lesion and relationship with cardiomegaly and hyperlipidemia. Am J kidney Dis. Elsevier; 1992;20:629–634. [DOI] [PubMed]
  32. [37]Kambham N, Markowitz GS, Valeri AM, Lin J, D’Agati VD. Obesity-related glomerulopathy: an emerging epidemic. Kidney Int. Elsevier; 2001;59:1498–1509. [DOI] [PubMed]
  33. [38]Darouich S, Goucha R, Jaafoura MH, Zekri S, Maiz H Ben, Kheder A. Clinicopathological characteristics of obesity-associated focal segmental glomerulosclerosis. Ultrastruct Pathol. Taylor & Francis; 2011;35:176–182. [DOI] [PubMed]
  34. [39]Huang W-H, Chen C-Y, Lin J-L, Lin-Tan D-T, Hsu C-W, Yen T-H. High body mass index reduces glomerular filtration rate decline in type II diabetes mellitus patients with stage 3 or 4 chronic kidney disease. Medicine (Baltimore). Wolters Kluwer Health; 2014;93. [DOI] [PMC free article] [PubMed]
  35. [40]Hovind P, Tarnow L, Rossing P, Graae M, Torp I, Binder C, et al. Predictors for the development of microalbuminuria and macroalbuminuria in patients with type 1 diabetes: inception cohort study. Bmj. British Medical Journal Publishing Group; 2004;328:1105. [DOI] [PMC free article] [PubMed]
  36. [41]Tapp RJ, Shaw JE, Zimmet PZ, Balkau B, Chadban SJ, Tonkin AM, et al. Albuminuria is evident in the early stages of diabetes onset: results from the Australian diabetes, obesity, and lifestyle study (AusDiab). Am J Kidney Dis. Elsevier; 2004;44:792–798. [PubMed]
  37. [42]De Boer IH, Rue TC, Cleary PA, Lachin JM, Molitch ME, Steffes MW, et al. Long-term renal outcomes of patients with type 1 diabetes mellitus and microalbuminuria: an analysis of the diabetes control and complications trial/epidemiology of diabetes interventions and complications cohort. Arch Intern Med. American Medical Association; 2011;171:412–420. [DOI] [PMC free article] [PubMed]
  38. [43]Araki S, Haneda M, Sugimoto T, Isono M, Isshiki K, Kashiwagi A, et al. Factors associated with frequent remission of microalbuminuria in patients with type 2 diabetes. Diabetes. Am Diabetes Assoc; 2005;54:2983–2987. [DOI] [PubMed]
  39. [44]Hirsch IB, Brownlee M. Beyond hemoglobin A1c—need for additional markers of risk for diabetic microvascular complications. Jama. American Medical Association; 2010;303:2291–2292. [DOI] [PubMed]
  40. [45]Pavkov ME, Bennett PH, Sievers ML, Krakoff J, Williams DE, Knowler WC, et al. Predominant effect of kidney disease on mortality in Pima Indians with or without type 2 diabetes. Kidney Int. Elsevier; 2005;68:1267–1274. [DOI] [PMC free article] [PubMed]
  41. [46]Skupien J, Warram JH, Smiles AM, Niewczas MA, Gohda T, Pezzolesi MG, et al. The early decline in renal function in patients with type 1 diabetes and proteinuria predicts the risk of end-stage renal disease. Kidney Int. Elsevier; 2012;82:589–597. [DOI] [PMC free article] [PubMed]
  42. [47]Coca SG, Nadkarni GN, Huang Y, Moledina DG, Rao V, Zhang J, et al. Plasma biomarkers and kidney function decline in early and established diabetic kidney disease. J Am Soc Nephrol. 2017;28:2786–2793. doi: 10.1681/ASN.2016101101. [DOI] [PMC free article] [PubMed] [Google Scholar] · DOI

Authors
Hosseini Sarkhosh, S. M., Esteghamati, A., Hemmatabadi, M., & Daraei, M.
Affiliations
  • Imam Khomeini Hospital (IR)
  • Tehran University of Medical Sciences (IR)
Corresponding author
  • Esteghamati, Alireza
  • Hemmatabadi, Mahboobeh
  • Daraei, Morteza
ORCID
Venue
Journal of Diabetes & Metabolic Disorders
Publisher
Springer Science and Business Media LLC
Published
2022-07-26
Volume
21
Issue
2
Pages
1433-1441
ISSN
2251-6581 (ISSN-L)
DOI
10.1007/s40200-022-01076-2
PMC
PMC9672147
OpenAlex
W4287877229
Cited by
24
References
44
Citations by year
2026: 6 · 2025: 5 · 2024: 9 · 2023: 4
FWCI
3.37
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Diabetes & Metabolic Disorders (publishedVersion)
  • PubMed Central (publishedVersion)
  • PubMed (publishedVersion)
Topics
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Medicine › Nephrology › Chronic Kidney Disease and Diabetes
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
diabetic nephropathy, type 2 diabetes, risk factor prediction, risk factor selection, recursive feature elimination, random forest, blood pressure control, glycemic control, HbA1c, hypertension, diabetic retinopathy, end-stage renal disease

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review