Development and internal validation of machine learning algorithms for end-stage renal disease risk prediction model of people with type 2 diabetes mellitus and diabetic kidney disease. Issue 1 (31st December 2022)

• Record Type: Journal Article
• Authors: Zou, Yutong; Zhao, Lijun; Zhang, Junlin; Wang, Yiting; Wu, Yucheng; Ren, Honghong; Wang, Tingli; Zhang, Rui; Wang, Jiali; Zhao, Yuancheng; Qin, Chunmei; Xu, Huan; Li, Lin; Chai, Zhonglin; Cooper, Mark E.; Tong, Nanwei; Liu, Fang
• Is Part Of: Renal failure. Volume 44:Issue 1(2022)
• Page Start: 562
• Page End: 570
• Publication Date: 2022-12-31
• Subjects: Type 2 diabetes mellitus -- diabetic kidney disease -- end-stage renal disease -- risk prediction model -- machine learning; Chronic renal failure -- Periodicals; Acute renal failure -- Periodicals; Uremia -- Periodicals; 616.614005
• DOI: 10.1080/0886022X.2022.2056053
• Languages: English
• ISSNs: 0886-022X

Abstract

Abstract: Aims: Diabetic kidney disease (DKD) is the most common cause of end-stage renal disease (ESRD) and is associated with increased morbidity and mortality in patients with diabetes. Identification of risk factors involved in the progression of DKD to ESRD is expected to result in early detection and appropriate intervention and improve prognosis. Therefore, this study aimed to establish a risk prediction model for ESRD resulting from DKD in patients with type 2 diabetes mellitus (T2DM). Methods: Between January 2008 and July 2019, a total of 390 Chinese patients with T2DM and DKD confirmed by percutaneous renal biopsy were enrolled and followed up for at least 1 year. Four machine learning algorithms (gradient boosting machine, support vector machine, logistic regression, and random forest (RF)) were used to identify the critical clinical and pathological features and to build a risk prediction model for ESRD. Results: There were 158 renal outcome events (ESRD) (40.51%) during the 3-year median follow up. The RF algorithm showed the best performance at predicting progression to ESRD, showing the highest AUC (0.90) and ACC (82.65%). The RF algorithm identified five major factors: Cystatin-C, serum albumin (sAlb), hemoglobin (Hb), 24-hour urine urinary total protein, and estimated glomerular filtration rate. A nomogram according to the aforementioned five predictive factors was constructed to predict the incidence of ESRD. Conclusion: Machine learning algorithms can efficiently predict the incident ESRD in DKD participants. Compared with the previous models, the importance of sAlb and Hb were highlighted in the current model. Highlights: What is already known? Identification of risk factors for the progression of DKD to ESRD is expected to improve the prognosis by early detection and appropriate intervention. What this study has found? Machine learning algorithms were used to construct a risk prediction model of ESRD in patients with T2DM and DKD. The major predictive factors were found to be CysC, sAlb, Hb, eGFR, and UTP. What are the implications of the study? In contrast with the treatment of participants with early-phase T2DM with or without mild kidney damage, major emphasis should be placed on indicators of kidney function, nutrition, anemia, and proteinuria for participants with T2DM and advanced DKD to delay ESRD, rather than age, sex, and control of hypertension and glycemia.