Nomogram for predicting chronic kidney disease in children developed using artificial intelligence methods
https://doi.org/10.25881/18110193_2025_1_82
Abstract
Background. Modern artificial intelligence algorithms provide new insights into potential risk factors and modeling tools that predict the chronic course of kidney disease in children. Management of chronic kidney disease (CKD) is based on the use of tools that help the physician to timely predict the transition from acute kidney disease to chronic kidney disease and timely refer the child to a nephrologist.
Aim. Тo develop a graphical tool to predict chronic kidney disease in children.
Methods. The initial data for the development of the graphic tool (nomogram) were our own results published earlier. High quality prognostic model (ROC-AUC>90%) was constructed based on predictors of chronic kidney disease in children that we identified previously (proteinuria, haematuria, IL4 gene C598T polymorphic marker).
Results. The constructed nomogram has a high prognostic value – with an accuracy of 98.9% to predict CKD in children.
Conclusion: The developed nomogram can be used as a graphical assistant for physicians to predict the chronic course of the disease in patients with acute kidney disease.
About the Authors
O. A. Sedashkina
Samara State Medical University
Russian Federation
Russian Federation
PhD, Associate Professor
Samara
A. V. Kolsanov
Samara State Medical University
Russian Federation
Russian Federation
DSc, Professor, Professor, Professor of RAS
Samara
References
1. Gusev AV. Perspektivy nejronnyh setej i glubokogo mashinnogo obucheniya v sozdanii reshenij dlya zdravoohraneniya. Vrach i informacionnye tekhnologii. 2017; 3: 92-104. (In Russ.)
2. Karas' SI. Virtual'nye pacienty kak format simulyacionnogo obucheniya v nepreryvnom medicinskom obrazovanii. Byulleten' sibirskoj mediciny. 2020; 19(1): 140-149. (In Russ.) doi: 10.20538/1682-0363-2020-1-140-149.
3. Karas' SI, Arzhanik MB, Kara-Sal EE, et al. Virtual patients as a basis for problem-oriented training of cardiologists. Byulleten' sibirskoj mediciny. 2020; 19(4): 207-214. (In Russ.)
4. Levey AS, Coresh J, Balk E, Kausz AT, et al. National Kidney Foundation practice guidelines for chronic kidney disease: evaluation, classification, and stratification. Ann Intern Med. 2003; 139(2): 137-147. doi: 10.7326/0003-4819-139-2-200307150-00013.
5. Kolsanov AV, Sedashkina OA, Postnikov MA, Makoveczkaya GA, et al. Skrining xronicheskoj bolezni pochek u detej s pomoshh`yu algoritmov mashinnogo obucheniya. Menedzher zdravooxraneniya. 2024; 5: 75-83. (In Russ.) doi: 10.21045/1811-0185-2024-5-75-84.
6. Ng DK, Pierce CB. Kidney Disease Progression in Children and Young Adults With Pediatric CKD: Epidemiologic Perspectives and Clinical Applications. Semin Nephrol. 2021; 41(5): 405-15. doi: 10.1016/j.semnephrol.2021.09.002.
7. Kaggle. Kidney Disease Prediction. Available at: https://www.kaggle.com/code/niteshyadav3103/chronic-kidney-disease-prediction-98-accuracy. Accessed May 12, 2024.
8. KDIGO 2024 Clinical Practice Guideline for the Evaluation and Management of Chronic Kidney Disease. doi: 10.1016/j.kint.2023.10.018.
9. Ketlinskij SA, Simbircev AS. Citokiny. SPb.: Foliant; 2008. (In Russ.)
10. Miromanov AM, Mironova OB, Miromanova NA. Interleukin-4-589C>T gene polymorphism and interleukin-4 expression in patients with the development of chronic traumatic osteomyelitis. Medical Immunology (Russia). 2018; 20(6): 889-894. (In Russ.) doi: 10.15789/1563-0625-2018-6-889-894.
11. Dyatlov SP. The use of digital technologies as one of the directions of solving the problem of the quality of Russian health care. Biznes-obrazovanie v ekonomike znanij. 2023; 2(25). (In Russ.)
12. Kanda E, Epureanu BI, Adachi T, Kashihara N. Machine-learning-based Web system for the prediction of chronic kidney disease progression and mortality. PLOS Digit Health. 2023; 2(1): e0000188. doi: 10.1371/journal.pdig.0000188.
13. Steyerberg EW, Vickers AJ, Cook NR, Gerds T, Gonen M, Obuchowski N., et al. Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiol Camb Mass. 2010; 21(1): 128-38. doi: 10.1097/EDE.0b013e3181c30fb2.
14. Schlattmann P. Tutorial: statistical methods for the meta-analysis of diagnostic test accuracy studies. Clin Chem Lab Med. 2023; 61(5): 777-794. doi: 10.1515/cclm-2022-1256.
15. Zhang Z, Rousson V, Lee WC, Ferdynus C, Chen M, Qian X, Guo Y; written on behalf of AME Big-Data Clinical Trial Collaborative Group. Decision curve analysis: a technical note. Ann Transl Med. 2018; 6(15): 308. doi: 10.21037/atm.2018.07.02.
16. Jiang J, Liu X, Cheng Z, Liu Q, Xing W. Interpretable machine learning models for early prediction of acute kidney injury after cardiac surgery. BMC Nephrol. 2023; 24(1): 326. doi: 10.1186/s12882-023-03324-w.
17. Reed BY, Masoumi A, Elhassan E, McFann K, Cadnapaphornchai MA, Maahs DM, et al. Angiogenic growth factors correlate with disease severity in young patients with autosomal dominant polycystic kidney disease. Kidney Int. 2011; 79(1): 128-34. doi: 10.1038/ki.2010.355.
18. Urbina E. Noninvasive assessment of target organ injury in children with the metabolic syndrome. J Cardiometab Syndr. 2006; 1(4): 277-81. doi: 10.1111/j.1559-4564.2006.05799.x.
19. Kashtan CE, Adam MP, Feldman J, Mirzaa GM, et al. Alport Syndrome. Seattle (WA): University of Washington, Seattle; 1993. Available at: http://www.ncbi.nlm.nih.gov/books/NBK1207/. Accessed May 12, 2024.
20. Marques C, Carvelli J, Biard L, Faguer S, et al. Prognostic Factors in Anti-glomerular Basement Membrane Disease: A Multicenter Study of 119 Patients. Front Immunol. 2019; 10: 1665. doi: 10.3389/fimmu.2019.01665.
Review
For citations:
Sedashkina O.A., Kolsanov A.V. Nomogram for predicting chronic kidney disease in children developed using artificial intelligence methods. Medical Doctor and Information Technologies. 2025;(1):82-89. (In Russ.) https://doi.org/10.25881/18110193_2025_1_82
Views:
504
Email this article 