1
|
Lin X, Liu C, Wang H, Fan X, Li L, Xu J, Li C, Wang Y, Cai X, Peng X. A SuperLearner approach for predicting diabetic kidney disease upon the initial diagnosis of T2DM in hospital. BMC Med Inform Decis Mak 2025; 25:148. [PMID: 40140809 PMCID: PMC11948915 DOI: 10.1186/s12911-025-02977-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2024] [Accepted: 03/17/2025] [Indexed: 03/28/2025] Open
Abstract
BACKGROUND Diabetic kidney disease (DKD) is a serious complication of diabetes mellitus (DM), with patients typically remaining asymptomatic until reaching an advanced stage. We aimed to develop and validate a predictive model for DKD in patients with an initial diagnosis of type 2 diabetes mellitus (T2DM) using real-world data. METHODS We retrospectively examined data from 3,291 patients (1740 men, 1551 women) newly diagnosed with T2DM at Ningbo Municipal Hospital of Traditional Chinese Medicine (2011-2023). The dataset was randomly divided into training and validation cohorts. Forty-six readily available medical characteristics at initial diagnosis of T2DM from the electronic medical records were used to develop prediction models based on linear, non-linear, and SuperLearner approaches. Model performance was evaluated using the area under the curve (AUC). SHapley Additive exPlanation (SHAP) was used to interpret the best-performing models. RESULTS Among 3291 participants, 563 (17.1%) were diagnosed with DKD during median follow-up of 2.53 years. The SuperLearner model exhibited the highest AUC (0.7138, 95% confidence interval: [0.673, 0.7546]) for the holdout internal validation set in predicting any DKD stage. Top-ranked features were WBC_Cnt*, Neut_Cnt, Hct, and Hb. High WBC_Cnt, low Neut_Cnt, high Hct, and low Hb levels were associated with an increased risk of DKD. CONCLUSIONS We developed and validated a DKD risk prediction model for patients with newly diagnosed T2DM. Using routinely available clinical measurements, the SuperLearner model could predict DKD during hospital visits. Prediction accuracy and SHAP-based model interpretability may help improve early detection, targeted interventions, and prognosis of patients with DM.
Collapse
Affiliation(s)
- Xiaomeng Lin
- Ningbo Institute of Chinese Medicine Research, Ningbo Municipal Hospital of Traditional Chinese Medicine (TCM), Affiliated Hospital of Zhejiang Chinese Medical University, No. 819, Liyuan North Road, Haishu District, Ningbo, 315010, China
| | - Chao Liu
- Yidu Cloud Technology Inc., Beijing, 100083, China
- Nanjing YiGenCloud Institute, Nanjing, 211899, China
| | - Huaiyu Wang
- National Institute of Traditional Chinese Medicine Constitution and Preventive Treatment of Diseases, Beijing University of Chinese Medicine, Beijing, 100029, China
| | - Xiaohui Fan
- Pharmaceutical Informatics Institute, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, 310058, China
| | - Linfeng Li
- Yidu Cloud Technology Inc., Beijing, 100083, China
| | - Jiming Xu
- Yidu Cloud Technology Inc., Beijing, 100083, China
| | - Changlin Li
- Department of Nephrology, Ningbo Municipal Hospital of Traditional Chinese Medicine (TCM), Affiliated Hospital of Zhejiang Chinese Medical University, Ningbo, 315010, China
| | - Yao Wang
- Yidu Cloud Technology Inc., Beijing, 100083, China
| | - Xudong Cai
- Department of Nephrology, Ningbo Municipal Hospital of Traditional Chinese Medicine (TCM), Affiliated Hospital of Zhejiang Chinese Medical University, Ningbo, 315010, China
| | - Xin Peng
- Ningbo Institute of Chinese Medicine Research, Ningbo Municipal Hospital of Traditional Chinese Medicine (TCM), Affiliated Hospital of Zhejiang Chinese Medical University, No. 819, Liyuan North Road, Haishu District, Ningbo, 315010, China.
| |
Collapse
|
2
|
Song H, Liao Y, Hu H, Wan Q. Nonlinear association between proteinuria levels and the risk of cardiovascular disease events and all-cause mortality among chronic kidney disease patients. Ren Fail 2024; 46:2310727. [PMID: 38345084 PMCID: PMC10863521 DOI: 10.1080/0886022x.2024.2310727] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2023] [Accepted: 01/22/2024] [Indexed: 02/15/2024] Open
Abstract
BACKGROUND The association between proteinuria levels and cardiovascular disease (CVD) development and all-cause mortality in chronic kidney disease (CKD) patients remains controversial. METHODS In this investigation, we conducted a retrospective analysis involving 1138 patients who were registered in the CKD-Research of Outcomes in Treatment and Epidemiology (ROUTE) study. The primary outcome of this study was the composite of cardiovascular events or all-cause death. Cox proportional hazards regression, smooth curve fitting, piecewise linear regression, and subgroup analyses were used. RESULTS The mean age of the included individuals was 67.3 ± 13.6 years old. Adjusted hazard ratios (HRs) for UPCR in middle and high groups, compared to the low group, were 1.93 (95% CI: 1.28-2.91) and 4.12 (95% CI: 2.87-5.92), respectively, after multivariable adjustment. Further adjustments maintained significant associations; HRs for middle and high groups were 1.71 (95% CI: 1.12-2.61) and 3.07 (95% CI: 2.08-4.54). A nonlinear UPCR-primary outcome relationship was observed, with an inflection point at 3.93 g/gCr. CONCLUSION Among non-dialyzed patients with stage G2-G5 CKD, a nonlinear association between UPCR and the primary outcome was observed. A higher UPCR (when UPCR < 3.93 g/gCr) was an independent predictor of the primary outcome. Importantly, our study predates SGLT2 inhibitor use, showcasing outcomes achievable without these medications. Future research considerations will involve factors like SGLT-2 inhibitor utilization.
Collapse
Affiliation(s)
- Haiying Song
- Department of Nephrology, The First Affiliated Hospital of Shenzhen University, Shenzhen Second People’s Hospital, Shenzhen, PRChina
- Department of Nephrology, Shenzhen University Health Science Center, Shenzhen, PR China
| | - Yuheng Liao
- Department of Nephrology, The First Affiliated Hospital of Shenzhen University, Shenzhen Second People’s Hospital, Shenzhen, PRChina
- Department of Nephrology, Shenzhen University Health Science Center, Shenzhen, PR China
| | - Haofei Hu
- Department of Nephrology, The First Affiliated Hospital of Shenzhen University, Shenzhen Second People’s Hospital, Shenzhen, PRChina
- Department of Nephrology, Shenzhen University Health Science Center, Shenzhen, PR China
| | - Qijun Wan
- Department of Nephrology, The First Affiliated Hospital of Shenzhen University, Shenzhen Second People’s Hospital, Shenzhen, PRChina
- Department of Nephrology, Shenzhen University Health Science Center, Shenzhen, PR China
| |
Collapse
|
3
|
Ou SM, Tsai MT, Lee KH, Tseng WC, Yang CY, Chen TH, Bin PJ, Chen TJ, Lin YP, Sheu WHH, Chu YC, Tarng DC. Prediction of the risk of developing end-stage renal diseases in newly diagnosed type 2 diabetes mellitus using artificial intelligence algorithms. BioData Min 2023; 16:8. [PMID: 36899426 PMCID: PMC10007785 DOI: 10.1186/s13040-023-00324-2] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/04/2022] [Accepted: 02/17/2023] [Indexed: 03/12/2023] Open
Abstract
OBJECTIVES Type 2 diabetes mellitus (T2DM) imposes a great burden on healthcare systems, and these patients experience higher long-term risks for developing end-stage renal disease (ESRD). Managing diabetic nephropathy becomes more challenging when kidney function starts declining. Therefore, developing predictive models for the risk of developing ESRD in newly diagnosed T2DM patients may be helpful in clinical settings. METHODS We established machine learning models constructed from a subset of clinical features collected from 53,477 newly diagnosed T2DM patients from January 2008 to December 2018 and then selected the best model. The cohort was divided, with 70% and 30% of patients randomly assigned to the training and testing sets, respectively. RESULTS The discriminative ability of our machine learning models, including logistic regression, extra tree classifier, random forest, gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and light gradient boosting machine were evaluated across the cohort. XGBoost yielded the highest area under the receiver operating characteristic curve (AUC) of 0.953, followed by extra tree and GBDT, with AUC values of 0.952 and 0.938 on the testing dataset. The SHapley Additive explanation summary plot in the XGBoost model illustrated that the top five important features included baseline serum creatinine, mean serum creatine within 1 year before the diagnosis of T2DM, high-sensitivity C-reactive protein, spot urine protein-to-creatinine ratio and female gender. CONCLUSIONS Because our machine learning prediction models were based on routinely collected clinical features, they can be used as risk assessment tools for developing ESRD. By identifying high-risk patients, intervention strategies may be provided at an early stage.
Collapse
Affiliation(s)
- Shuo-Ming Ou
- Division of Nephrology, Department of Medicine, Taipei Veterans General Hospital, 201, Section 2, Shih-Pai Road, Taipei, 11217, Taiwan.,School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.,Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Ming-Tsun Tsai
- Division of Nephrology, Department of Medicine, Taipei Veterans General Hospital, 201, Section 2, Shih-Pai Road, Taipei, 11217, Taiwan.,School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.,Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Kuo-Hua Lee
- Division of Nephrology, Department of Medicine, Taipei Veterans General Hospital, 201, Section 2, Shih-Pai Road, Taipei, 11217, Taiwan.,School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.,Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Wei-Cheng Tseng
- Division of Nephrology, Department of Medicine, Taipei Veterans General Hospital, 201, Section 2, Shih-Pai Road, Taipei, 11217, Taiwan.,School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.,Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Chih-Yu Yang
- Division of Nephrology, Department of Medicine, Taipei Veterans General Hospital, 201, Section 2, Shih-Pai Road, Taipei, 11217, Taiwan.,School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.,Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Tz-Heng Chen
- Division of Nephrology, Department of Medicine, Taipei Veterans General Hospital, 201, Section 2, Shih-Pai Road, Taipei, 11217, Taiwan.,School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Pin-Jie Bin
- Graduate Institute of Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan
| | - Tzeng-Ji Chen
- School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.,Department of Family Medicine, Taipei Veterans General Hospital, Taipei, Taiwan.,Department of Family Medicine, Taipei Veterans General Hospital, Hsinchu Branch, Hsinchu, Taiwan.,Institute of Hospital and Health Care Administration, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Yao-Ping Lin
- Division of Nephrology, Department of Medicine, Taipei Veterans General Hospital, 201, Section 2, Shih-Pai Road, Taipei, 11217, Taiwan.,School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.,Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Wayne Huey-Herng Sheu
- School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.,Division of Endocrinology and Metabolism, Department of Internal Medicine, Taipei Veterans General Hospital, Taipei, Taiwan.,Institute of Molecular and Genetic Medicine, National Health Research Institute, Miaoli, Taiwan
| | - Yuan-Chia Chu
- Information Management Office, Taipei Veterans General Hospital, 201, Section 2, Shih-Pai Road, Taipei, 11217, Taiwan. .,Big Data Center, Taipei Veterans General Hospital, Taipei, Taiwan. .,Department of Information Management, National Taipei University of Nursing and Health Sciences, Taipei, Taiwan.
| | - Der-Cherng Tarng
- Division of Nephrology, Department of Medicine, Taipei Veterans General Hospital, 201, Section 2, Shih-Pai Road, Taipei, 11217, Taiwan. .,School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan. .,Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan. .,Department and Institute of Physiology, National Yang Ming Chiao Tung University, Taipei, Taiwan.
| |
Collapse
|