Tingting Fang1
Linghua Kong- 1School of Nursing and Rehabilitation, Shandong University, Jinan, China
- 2Marine Engineering College of Dalian Maritime University, Dalian, China
- 3Department of Gynecology, Reproductive Hospital affiliated to Shandong University, Jinan, China
Aims: To develop and validate a multi-feature machine learning (ML) model for early diabetic nephropathy (DN) prediction in elderly living with type 2 diabetes mellitus (T2DM), incorporating clinical indicators, symptoms of traditional Chinese medicine (TCM), and ultrasonic imaging features.
Methods: The valid data (including clinical indicators, TCM symptoms, and ultrasonic imaging features) of 786 patients was retained, and the data were divided into training and validation set. Three models were constructed to examine the model’s performance. The optimal indicators were selected for seven ML. Performance was assessed using accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve (AUC). The subgroup analysis was conducted based on age.
Results: The multi-feature model, combining clinical data, TCM symptoms, and ultrasound imaging, demonstrated the best performance. Among the ML algorithms, RF exhibited superior performance with an AUC of 0.894, sensitivity of 0.667, specificity of 0.877, precision of 0.769, recall of 0.667, and F1 score of 0.714 in the validation set. Subgroup analysis revealed that the AUC values exceed 0.7 in each group.
Conclusion: This study is the first to incorporate TCM symptoms and ultrasound imaging features into a predictive model for early DN in elderly living with T2DM. The models demonstrated strong predictive performance across different age groups. These findings underscore the potential of early screening, prevention, and intervention in improving outcomes for elderly living with T2DM, offering a novel approach to managing diabetic nephropathy.
1 Introduction
The prevalence of diabetes has grown significantly with aging populations, posing major global health challenges. Older adults are disproportionately affected, and this trend is particularly evident in China, which, according to the 2019 International Diabetes Federation (IDF), is home to approximately 35.5 million individuals aged 65 and elderly living with diabetes—accounting for nearly a quarter of the global elderly diabetic population (1, 2). Type 2 diabetes mellitus (T2DM) constitutes the majority of these cases, representing 90–95% of all diabetes diagnoses (3). Among elderly living with T2DM, the risk of diabetic nephropathy (DN), a severe complication, is alarmingly high, affecting 21.8% of this population in China (4). Furthermore, DN prevalence in individuals over 60 years of age is estimated to be between 20% and 40%, making it the leading cause of end-stage renal disease (ESRD) (4).
The burden of DN continues to rise, with projections indicating over 24.3 million T2DM-related DN cases in China alone (5). Early DN is characterized by subtle and often atypical symptoms, leading to delayed detection. Without timely intervention, DN can progress to significant proteinuria and ESRD, the latter occurring at a rate 14 times higher than other kidney diseases once DN advances to its later stages (4). As such, the early stage of DN represents a critical window for intervention, where timely screening and preventive strategies have the potential to alter the disease trajectory (4, 6, 7).
Although several predictive models, such as the RECODe model (8), UKPDS outcomes model 2 (9), and the Renal DCS Risk Score (10), have been developed, these are predominantly designed for patients with advanced renal disease. Models specifically addressing early DN are rare and often rely on diagnosis markers, such as estimated glomerular filtration rate (eGFR) and urinary albumin-to-creatinine ratio (UACR) (7, 11–16).
Emerging evidence suggests that incorporating TCM symptoms into prediction models offers unique advantages. Unlike conventional biochemical indicators, TCM symptomology provides a holistic view of the patient’s health status, offering insights into subtle pathophysiological changes that might precede biochemical abnormalities (17, 18). Similarly, ultrasonography is increasingly recognized for its potential in stratifying the risk of early DN by assessing both renal and systemic vascular health. Beyond emerging renal techniques (e.g., elastography for stiffness and Doppler for intrarenal hemodynamics), carotid ultrasound findings—such as increased carotid intima-media thickness (cIMT) and the presence of carotid artery plaque—have been shown to be independent risk factors for the development and progression of DN in T2DM patients. This underscores the value of ultrasound in providing a non-invasive, integrative evaluation of the cardiorenal system (19–24). The integration of these multidimensional data sources presents an opportunity to enhance the predictive accuracy and clinical utility of DN models.
This study aims to fill these critical gaps by developing a comprehensive, multi-feature machine learning (ML) prediction model for early DN in elderly living with T2DM. By combining clinical indicators, TCM symptoms, and ultrasound imaging features, the study seeks to identify the most predictive variables and the optimal ML algorithm for early DN detection. This innovative approach offers a timely and significant contribution to advancing early screening, diagnosis, and management of DN, addressing a pressing need in the care of aging populations at high risk for kidney disease.
2 Methods
This study was approved by the Ethics Committee of The Affiliated Hospital of Hangzhou Normal University (Approval No. 2022KS034) and adhered to the principles outlined in the Declaration of Helsinki. The study followed the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) guidelines. Informed consent was submitted by all subjects when they were enrolled.
2.1 Study design and patient selection
Elderly living with T2DM were recruited from The Affiliated Hospital of Hangzhou Normal University between May 2021 and October 2022. The inclusion criteria were (1): age ≥ 60 years, (2) diagnosis of T2DM, and (3) urinary albumin-to-creatinine ratio (UACR) < 300 mg/g. Patients were excluded if they: (1) were under 60 years of age, (2) had non-T2DM diagnoses, (3) had UACR ≥ 300 mg/g, uremia, or renal failure, (4) had severe infections, systemic immune diseases, organ failure, or malignancies, or (5) lacked essential clinical information. After applying these criteria, 786 patients were included in the study (Figure 1).
Figure 1. Research flow chart.
2.2 Diagnostic criteria
T2DM and early DN were diagnosed according to the 1999 World Health Organization criteria and Kidney Disease: Improving Global Outcomes (KDIGO) guidelines (25, 26). Early DN was defined as a UACR between 30–300 mg/g, confirmed by at least two of three tests conducted over 3–6 months.
2.3 Data collection
Patient data were obtained from the hospital’s electronic medical records and a questionnaire survey. The data were categorized into three domains:
2.3.1 Clinical information
Variables included gender, age, smoking, drinking, comorbidities (hypertension, coronary heart disease, cerebral infarction, hyperlipidemia), family history, diabetic retinopathy, diabetes duration, systolic and diastolic blood pressure, body mass index (BMI), and laboratory parameters such as bilirubin (total, direct, and indirect), calcium, blood urea nitrogen, serum creatinine, uric acid, retinol-binding protein, cholesterol (total, triglycerides, HDL-c, LDL-c), C-reactive protein (CRP), red cell distribution width, platelet distribution width, platelet-to-lymphocyte ratio, high-sensitivity CRP (hs_CRP), glycated hemoglobin (HbA1c), and UACR.
2.3.2 Traditional Chinese medicine symptoms
A TCM symptom questionnaire was designed based on diagnostic and syndrome differentiation criteria (27–29).Ten variables commonly associated with DN were assessed, including fatigue, night sweats, cold extremities, face and feet edema, lumbar and knee weakness, tinnitus and deafness, insomnia and dreaminess, blurred vision, nocturnal polyuria, limb numbness. Responses were scored as “Yes” (1) or “No” (0) (30, 31).
2.3.3 Ultrasound imaging indicators
Variables included left ventricular diastolic dysfunction decreased, valvular regurgitation, renal cysts, nephrolithiasis, renal parenchymal calcification, carotid intima thickening, and carotid artery plaque.
2.4 Data cleaning
Data were subjected to an extensive cleaning process to ensure quality and completeness. Records with missing values exceeding 15% were excluded (32, 33), while missing values under 15% were addressed using simple interpolation. We used SPSS 22.0 for simple interpolation (< 15% missing): imputation methods (1): continuous: series mean imputation; (2) categorical: mode imputation. Duplicate and extreme outliers were removed.
2.5 Statistical analysis
Statistical analyses were conducted using SPSS 22.0 and R software (v4.2.0). Continuous variables with normal distributions were compared using t-tests or ANOVA and reported as mean ± standard deviation (SD). Non-normally distributed data were analyzed with non-parametric tests (Wilcoxon rank-sum or Kruskal-Wallis H test) and reported as medians with interquartile ranges (P25, P75). Categorical variables were compared using chi-square or Fisher’s exact tests and expressed as counts and percentages. A two-tailed p-value < 0.05 was considered statistically significant.
2.6 Feature selection and model evaluation
Least absolute shrinkage and selection operator (LASSO) regression was performed to identify key predictors, followed by multivariate logistic regression (34). A stepwise backward elimination method was used to finalize the model variables. Model discrimination was evaluated using receiver operating characteristic (ROC) curves, with the area under the curve (AUC) calculated using the “pROC” package in R. AUC comparisons between models were conducted with the DeLong test. Calibration and clinical utility were assessed using calibration curves and decision curve analysis (DCA), with the “rms” and “nricens” packages, respectively. Nomograms were constructed for visualization.
2.7 Machine learning algorithms
The final model variables were used to develop predictive models using seven machine learning algorithms: logistic regression (LR), decision tree (DT), random forest (RF), k-nearest neighbors (KNN), light gradient boosting machine (Light GBM), support vector machine (SVM), and XGBoost (XGB). The performance of each algorithm was evaluated using accuracy, precision, recall, F1 score, and AUC.
3 Results
3.1 Baseline characteristics of participants
A total of 786 participants were included in this study, with 550 allocated to the training set and 236 to the validation set in a 7:3 ratio. Baseline comparisons revealed significant differences in the variables “cold extremities”, diabetes duration, total bilirubin (TB), and indirect bilirubin (IB) between the training and validation sets (P < 0.05). No significant differences were observed for other variables (P > 0.05), confirming the comparability between the training and validation sets (Table 1).
Table 1. Comparison of baseline data between training and validation sets.
3.2 Variable selection using LASSO and logistic regression
LASSO regression was applied to identify relevant predictors, using early DN as the dependent variable and 48 candidate variables as independent variables. The optimal model was determined through ten-fold cross-validation (Figure 2). LASSO analysis identified 21 significant factors, including cold extremities, lumbar and knee weakness, blurred vision, nocturnal polyuria, limb numbness, hypertension, cerebral infarction, hyperlipidemia, diabetic retinopathy (DR), diabetes duration, systolic blood pressure (SBP), indirect bilirubin (IB), blood calcium (Ca), blood urea nitrogen (BUN), uric acid (UA), retinol-binding protein (RBP), triglycerides (TG), C-reactive protein (CRP), renal parenchymal calcification, carotid intima thickening, and carotid artery plaque.
Figure 2. Best match factor screening by lasso regression. (A) The Lasso regression path diagram; (B) The plot of the best matching factors screened by the ten-fold cross validation method, and the best matching factors were selected using lambda.1se as the criterion.
Through backward stepwise logistic regression, 15 independent risk factors were identified: lumbar and knee weakness, blurred vision, nocturnal polyuria, hypertension, cerebral infarction, hyperlipidemia, DR, SBP, IB, Ca, UA, RBP, CRP, carotid intima thickening, and carotid artery plaque (Supplementary Figure S1).
3.3 Comparison of predictive models
Three prediction models were developed:
● Mod A: Clinical indicators only (hypertension, cerebral infarction, hyperlipidemia, DR, SBP, IB, Ca, UA, RBP, CRP).
● Mod B: Clinical indicators and TCM symptoms (Mod A variables + lumbar and knee weakness, blurred vision, nocturnal polyuria).
● Mod C: Clinical indicators, TCM symptoms, and ultrasound imaging (Mod B variables + carotid intima thickening, carotid artery plaque).
Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). In the training set, AUCs were 0.852 (95% CI: 0.819–0.884) for Mod A, 0.881 (95% CI: 0.852–0.910) for Mod B, and 0.902 (95% CI: 0.876–0.928) for Mod C. In the validation set, AUCs were 0.801 (95% CI: 0.741–0.860), 0.832 (95% CI: 0.781–0.883), and 0.855 (95% CI: 0.808–0.902) for Mod A, Mod B, and Mod C, respectively. Calibration and decision curve analyses further confirm that Mod C exhibited the best predictive performance (Figure 3). Based on these findings, Mod C was selected to construct a nomogram for clinical application (Figure 4).
Figure 3. The ROC curve, calibration curve, and the decision curve analysis of three models in the training and validation sets. (A1, A2) The ROC curve in the training and validation sets, respectively; (B1, B2) The calibration curve in the training and validation sets, respectively; (C1, C2) The decision curve analysis in the training and validation sets, respectively.
Figure 4. Nomogram of the prediction model for early nephropathy in elderly living with T2DM.
3.4 Performance of machine learning models
Using the multi-feature data from Mod C, seven machine learning algorithms were evaluated: logistic regression (LR), decision tree (DT), random forest (RF), k-nearest neighbors (KNN), light gradient boosting machine (Light GBM), support vector machine (SVM), and XGBoost (XGB). Among these, RF demonstrated the highest performance. In the training set, RF achieved an AUC, sensitivity, specificity, precision, recall, and F1 score of 1.000. In the validation set, RF yielded an AUC of 0.894, sensitivity of 0.667, specificity of 0.877, precision of 0.769, recall of 0.667, and F1 score of 0.714 (Supplementary Figure S2, Figure 5, Table 2). SHAP analysis identified DR, UA, and carotid artery plaque as the top three predictors influencing early DN in elderly T2DM patients (Supplementary Figure S3).
Figure 5. Performance of seven machine learning models between training and validation sets. (A, B) Training and validation sets, respectively.
Table 2. Performance of seven machine learning models between training and validation sets.
3.5 Subgroup analysis by age
To account for potential age-related differences in DN, subgroup analyses were performed by stratifying participants into three age groups: 60–69 years, 70–79 years, and ≥ 80 years. In the training set, AUCs were 0.933 (95% CI: 0.902–0.964) for ages 60–69, 0.935 (95% CI: 0.900–0.970) for ages 70–79, and 0.837 (95% CI: 0.756–0.917) for ages ≥ 80. In the validation set, AUCs were 0.879 (95% CI: 0.814–0.944), 0.923 (95% CI: 0.861–0.985), and 0.718 (95% CI: 0.559–0.878), respectively (Supplementary Figure S4). Forest plots and age-specific nomograms were generated to visualize risk factors for each age group and to facilitate clinical decision-making (Supplementary Figures S5, S6).
4 Discussion
Numerous established models for predicting diabetic nephropathy (DN) primarily focus on patients with end-stage renal disease or renal failure (8–10). Early DN prediction models, while incorporating diagnostic markers such as estimated glomerular filtration rate (eGFR) and urinary albumin-to-creatinine ratio (UACR), are generally based on demographic, anthropometric, and biochemical indicators (7, 11, 14, 35). In this study, we constructed a novel predictive model integrating clinical data, traditional Chinese medicine (TCM) symptoms, and ultrasound imaging indicators to predict early DN in elderly living with type 2 diabetes mellitus (T2DM).
Among the three models developed, the combined model (Mod C) demonstrated the highest predictive value, with an area under the curve (AUC) of 0.902. This performance highlights the synergistic value of combining clinical data, TCM symptoms, and ultrasound imaging features, surpassing the predictive ability of models based solely on clinical or single-domain data. Our findings align with recent studies emphasizing the importance of integrating TCM symptoms and imaging features in disease prediction (16, 36). Consequently, Mod C was utilized to construct a nomogram, and its performance was further validated using machine learning (ML) algorithms, demonstrating strong discrimination and calibration. Our nomogram-based prediction model can be implemented clinically through the following standardized procedures (1): assess TCM syndromes (using standardized diagnostic scale); (2) obtain ultrasound parameters; (3) input routine metrics (e.g., hypertension, cerebral infarction, hyperlipidemia, DR, SBP, IB); (4) plot scores on corresponding nomogram axes; (5) sum total points to read predicted probability.
4.1 Clinical relevance of predictors
The predictive model identified several key factors related to early DN in older patients. TCM symptoms such as lumbar and knee weakness, blurred vision, and nocturnal polyuria emerged as critical predictors. These symptoms reflect the underlying deficiencies in kidney Yin and Yang, which are central to TCM pathophysiology (37, 38). TCM classifies DN based on syndrome differentiation (e.g., Qi-Yin deficiency), which reflects systemic pathological changes even in early-stage DN when conventional biomarkers (e.g., microalbuminuria) may still be within normal ranges (39). Lumbar and knee weakness, blurred vision, and nocturnal polyuria may serve as early warning signs, aiding in the identification of high-risk patients before structural kidney damage becomes evident. Age-related declines in kidney function further exacerbate these deficiencies, as documented in prior studies (40, 41).
Ultrasound imaging indicators, particularly carotid intima thickening and carotid artery plaque, were also identified as significant predictors. These markers are commonly associated with diabetic macroangiopathy and atherosclerosis, which are closely linked to DN progression (42–48). Although not a gold standard, ultrasound provides valuable structural and hemodynamic insights, such as: carotid intima thickening and carotid artery plaque (suggesting diabetic macroangiopathy and atherosclerosis) (49). These findings, combined with laboratory tests, enhance early DN detection sensitivity. While the relationship between carotid intima-media thickness (IMT) and DN remains controversial, our study reinforces its role as an independent risk factor for early DN. TCM syndrome progression (e.g., from Qi-Yin deficiency to Yang deficiency) correlates with ultrasound-documented structural decline (e.g., carotid intima thickening and carotid artery plaque), offering a holistic view of disease progression. We acknowledge the need for further research on correlations between specific TCM syndromes (e.g., Spleen-Kidney Qi deficiency) and ultrasound parameters (e.g., carotid intima thickening and carotid artery plaque). Prospective studies validating a combined TCM-ultrasound predictive model would strengthen clinical utility.
Clinical factors such as hypertension, cerebral infarction, hyperlipidemia, diabetic retinopathy (DR), systolic blood pressure (SBP), indirect bilirubin (IB), calcium (Ca), uric acid (UA), retinol-binding protein (RBP), and C-reactive protein (CRP) were also significant predictors. Known risk factors, including DR, hypertension, and hyperlipidemia, align with established evidence (7, 11, 50). Notably, UA, an oxidative stress marker, is strongly associated with proteinuria, glomerular filtration rate decline, and DN progression (51–54). RBP, an early diagnostic marker of proximal tubular dysfunction, also emerged as a significant predictor (55). Interestingly, IB, with its antioxidant properties, was identified as a protective factor against DN, consistent with emerging research on its role in mitigating oxidative stress (56). Further studies are warranted to explore the mechanisms underlying these associations.
4.2 Subgroup analysis
Given the known epidemiological and physiological differences in DN risk across age groups, subgroup analyses were conducted. Predictive models showed robust performance across all age groups, with AUC values exceeding 0.7 in both training and validation datasets. The performance was particularly strong for patients aged 60–79 years, with slightly lower predictive accuracy for those aged ≥ 80 years, potentially due to smaller sample sizes. These findings emphasize the adaptability and applicability of the model for various age cohorts, providing a practical tool for early DN risk stratification in older populations.
4.3 Machine learning model comparison
The integration of clinical, TCM, and ultrasound imaging data was further validated through ML approaches. Among the seven algorithms evaluated, the random forest (RF) model exhibited the best predictive performance, with an AUC of 0.894, sensitivity of 0.667, specificity of 0.877, precision of 0.769, recall of 0.667, and F1 score of 0.714 in the validation set. These results confirm RF’s robustness, aligning with prior research that highlighted its superiority in predicting progression to end-stage renal disease (ESRD) (35, 57, 58). Notably, few existing ML models incorporate TCM and imaging data, underscoring the novelty and clinical relevance of our approach. Risk Equations for Complications Of type 2 Diabetes (RECODe) were derived from the Action to Control Cardiovascular Risk in Diabetes (ACCORD) study (59, 60). Compared with established DN prediction tools like RECODe, our model incorporates TCM syndromes (e.g., lumbar and knee weakness, blurred vision, and nocturnal polyuria) and ultrasound parameters (e.g., carotid intima thickening and carotid artery plaque). This multimodal design targets earlier prediction windows than RECODe. At the same time, the RECODe predicts 3–5 year renal function decline, our model identifies pre-clinical risks (TCM manifestations precede lab abnormalities).
4.4 Implications and limitations
This study provides a comprehensive predictive framework for early DN in elderly living with T2DM, incorporating multidimensional data to improve accuracy. The integration of TCM symptoms and ultrasound imaging data represents a novel and clinically valuable approach, facilitating early detection and targeted management. However, studying has several limitations.
4.4.1 Single-center and internal validation design
The participants were recruited from a single hospital with internal validation, introducing potential selection bias. Future studies should include multicenter cohorts and external validation to enhance generalizability.
4.4.2 Subjectivity of TCM assessments
Although standardized questionnaires were used, the inherent subjectivity and lack of uniform standards in TCM symptom evaluation remain a challenge. Future work will involve multicenter collaboration and AI-assisted tools (e.g., CNN) to enhance objectivity.
4.4.3 Sample size constraints
The subgroup of patients aged ≥ 80 years was relatively small (n=146 vs. 421 in 60-69y and 219 in 70-79y groups), which may have influenced the predictive performance in this group. Larger studies are needed to validate these findings.
4.4.4 Ultrasound imaging variability
Differences in equipment and operator expertise were not accounted for, potentially affecting the consistency of imaging data. Standardized imaging protocols should be adopted in future studies.
4.4.5 Non-albuminuric nephropathy was not considered
Studies documented that non-albuminuric DKD (eGFR < 60 mL/min/1.73 m2 in the absence of albuminuria) occurs relatively frequently in patients with diabetes and its prevalence is increasing. In this study, the diagnosis of early kidney disease is based on UACR. We did not consider non-albuminuric DKD. In future studies, we will focus on the construction of non-albuminuric DKD prediction model.
5 Conclusions
This study successfully developed and validated predictive models for early DN in elderly living with T2DM, incorporating clinical, TCM, and ultrasound imaging data. The RF model demonstrated superior predictive performance, and subgroup analyses confirmed its applicability across different age groups. These findings have significant implications for early DN screening, prevention, and management, particularly in aging populations. Further research is needed to address the study’s limitations and to validate the model in diverse clinical settings.
Data availability statement
The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation.
Ethics statement
This study was approved by the ethics committee of The Affiliated Hospital of Hangzhou Normal University (Approval No. 2022KS034) and adhered to the principles outlined in the Declaration of Helsinki. Informed consent was submitted by all subjects when they were enrolled.
Author contributions
TF: Investigation, Software, Methodology, Writing – original draft, Data curation. YY: Writing – original draft, Investigation, Methodology. FZ: Investigation, Data curation, Writing – original draft, Methodology. XX: Methodology, Writing – original draft, Data curation. JS: Conceptualization, Writing – review & editing, Supervision. LK: Writing – review & editing, Supervision, Conceptualization, Resources.
Funding
The author(s) declared that financial support was received for this work and/or its publication. This work was supported by the Shandong Excellent Young Scientists Fund Program (Overseas) (No. 2024HWYQ-010) and The Special Foundation for Taishan Scholars (No. tsqn202211034).
Acknowledgments
We gratefully acknowledge all the participants in the study and the Affiliated Hospital of Hangzhou Normal University for participating in this study.
Conflict of interest
The authors declared that this work was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Generative AI statement
The author(s) declared that generative AI was not used in the creation of this manuscript.
Any alternative text (alt text) provided alongside figures in this article has been generated by Frontiers with the support of artificial intelligence and reasonable efforts have been made to ensure accuracy, including review by the authors wherever possible. If you identify any issues, please contact us.
Publisher’s note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
Supplementary material
The Supplementary Material for this article can be found online at: https://www.frontiersin.org/articles/10.3389/fendo.2025.1660903/full#supplementary-material
References
1. Wang L, Peng W, Zhao Z, Zhang M, Shi Z, Song Z, et al. Prevalence and treatment of diabetes in China, 2013-2018. JAMA: J Am Med Assoc. (2021) 24):326. doi: 10.1001/jama.2021.22208
2. Sinclair A, Saeedi P, Kaundal A, Karuranga S, Malanda B, and Williams R. Diabetes and global ageing among 65-99-year-old adults: Findings from the International Diabetes Federation Diabetes Atlas, 9(th) edition. Diabetes Res Clin Pract. (2020) 162:108078. doi: 10.1016/j.diabres.2020.108078
3. Addendum. 2. Classification and diagnosis of diabetes: standards of medical care in diabetes-2021. Diabetes Care. (2021) 44:S15–33. doi: 10.2337/dc21-S002
4. Society CD. Chinese guidelines for the prevention and treatment of type 2 diabetes (2020 edition) (I). Chin J Pract Internal Med. (2021) 41:668–95.
5. Zhang L, Long J, Jiang W, Shi Y, He X, Zhou Z, et al. Trends in chronic kidney disease in China. N Engl J Med. (2016) 375:905–6. doi: 10.1056/NEJMc1602469
6. Ahn HS, Kim JH, Jeong H, Yu J, Yeom J, Song SH, et al. Differential urinary proteome analysis for predicting prognosis in type 2 diabetes patients with and without renal dysfunction. Int J Mol Sci. (2020) 21:4236. doi: 10.3390/ijms21124236
7. Slieker RC, van der Heijden A, Siddiqui MK, Langendoen-Gort M, Nijpels G, Herings R, et al. Performance of prediction models for nephropathy in people with type 2 diabetes: systematic review and external validation study. Bmj. (2021) 374:n2134. doi: 10.1136/bmj.n2134
8. Basu S, Sussman JB, Berkowitz SA, Hayward RA, and Yudkin JS. Development and validation of Risk Equations for Complications Of type 2 Diabetes (RECODe) using individual participant data from randomised trials. Lancet Diabetes Endocrinol. (2017) 5:788–98. doi: 10.1016/S2213-8587(17)30221-8
9. Hayes AJ, Leal J, Gray AM, Holman RR, and Clarke PM. UKPDS outcomes model 2: a new version of a model to simulate lifetime health outcomes of patients with type 2 diabetes mellitus using data from the 30 year United Kingdom Prospective Diabetes Study: UKPDS 82. Diabetologia. (2013) 56:1925–33. doi: 10.1007/s00125-013-2940-y
10. 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. (2013) 36:3113–20. doi: 10.2337/dc13-0190
11. Jiang W, Wang J, Shen X, Lu W, Wang Y, Li W, et al. Establishment and validation of a risk prediction model for early diabetic kidney disease based on a systematic review and meta-analysis of 20 cohorts. Diabetes Care. (2020) 43:925–33. doi: 10.2337/dc19-1897
12. Yin JM, Li Y, Xue JT, Zong GW, Fang ZZ, and Zou L. Explainable machine learning-based prediction model for diabetic nephropathy. J Diabetes Res. (2024) 2024:8857453. doi: 10.1155/2024/8857453
13. Xu W, Zhou Y, Jiang Q, Fang Y, and Yang Q. Risk prediction models for diabetic nephropathy among type 2 diabetes patients in China: a systematic review and meta-analysis. Front Endocrinol (Lausanne). (2024) 15:1407348. doi: 10.3389/fendo.2024.1407348
14. Yun C, Tang F, Gao Z, Wang W, Bai F, Miller JD, et al. Construction of risk prediction model of type 2 diabetic kidney disease based on deep learning. Diabetes Metab J. (2024) 48:771–9. doi: 10.4093/dmj.2023.0033
15. Wang G, Wang B, Qiao G, Lou H, Xu F, Chen Z, et al. Screening tools based on nomogram for diabetic kidney diseases in chinese type 2 diabetes mellitus patients. Diabetes Metab J. (2021) 45:708–18. doi: 10.4093/dmj.2020.0117
16. Ma J, An S, Cao M, Zhang L, and Lu J. Integrated machine learning and deep learning for predicting diabetic nephropathy model construction, validation, and interpretability. Endocrine. (2024) 85:615–25. doi: 10.1007/s12020-024-03735-1
17. Shuang LI, Shuwei D, Zheyi D, Yilun QU, Yayong L, Jianghua KE, et al. Distribution of Traditional Chinese Medicine syndromes in diabetic kidney disease chronic kidney disease 1-5: a correlation study. J Tradit Chin Med. (2024) 44:572–80. doi: 10.19852/j.cnki.jtcm.20230802.007
18. Zhang GD, Liu XX, Liang JL, and Hu QM. The distribution pattern of traditional chinese medicine syndromes in 549 patients with type 2 diabetes. Diabetes Metab Syndr Obes. (2021) 14:2209–16. doi: 10.2147/DMSO.S295351
19. Garofolo M, Napoli V, Lucchesi D, Accogli S, Mazzeo ML, Rossi P, et al. Type 2 diabetes albuminuric and non-albuminuric phenotypes have different morphological and functional ultrasound features of diabetic kidney disease. Diabetes Metab Res Rev. (2023) 39:e3585. doi: 10.1002/dmrr.3585
20. Di Marco M, Scilletta S, Miano N, Marrano N, Natalicchio A, Giorgino F, et al. Cardiovascular risk and renal injury profile in subjects with type 2 diabetes and non-albuminuric diabetic kidney disease. Cardiovasc Diabetol. (2023) 22:344. doi: 10.1186/s12933-023-02065-2
21. Masulli M, Mancini M, Liuzzi R, Daniele S, Mainenti PP, Vergara E, et al. Measurement of the intrarenal arterial resistance index for the identification and prediction of diabetic nephropathy. Nutr Metab Cardiovasc Dis. (2009) 19:358–64. doi: 10.1016/j.numecd.2008.07.003
22. Nosadini R, Velussi M, Brocco E, Abaterusso C, Carraro A, Piarulli F, et al. Increased renal arterial resistance predicts the course of renal function in type 2 diabetes with microalbuminuria. Diabetes. (2006) 55:234–9. doi: 10.2337/diabetes.55.01.06.db05-0881
23. Keech AC, Grieve SM, Patel A, Griffiths K, Skilton M, Watts GF, et al. Urinary albumin levels in the normal range determine arterial wall thickness in adults with Type 2 diabetes: a FIELD substudy. Diabetes Med. (2005) 22:1558–65. doi: 10.1111/j.1464-5491.2005.01688.x
24. Cardoso CRL, Salles GC, Leite NC, and Salles GF. Prognostic impact of carotid intima-media thickness and carotid plaques on the development of micro- and macrovascular complications in individuals with type 2 diabetes: the Rio de Janeiro type 2 diabetes cohort study. Cardiovasc Diabetol. (2019) 18:2. doi: 10.1186/s12933-019-0809-1
25. Zhu D and Society CD. Guideline for the prevention and treatment of type 2 diabetes mellitus in China, 2020 edition. (2021).
26. de Boer IH, Khunti K, Sadusky T, Tuttle KR, Neumiller JJ, Rhee CM, et al. Diabetes management in chronic kidney disease: A consensus report by the american diabetes association (ADA) and kidney disease: improving global outcomes (KDIGO). Diabetes Care. (2022) 45:3075–90. doi: 10.2337/dci22-0027
27. Zhihua F, Xiaoting W, Yun C, and Xiaodong X. Nephropathy. Diabetic nephropathy TCM symptoms distribution characteristics and traditional chinese medicine intervention. China Health Standard Management. (2016) 7:140–1.
28. Branch CMAN. Diabetic nephropathy diagnosis, syndrome differentiation and curative effect evaluation standard (trial scheme). Shanghai J Traditional Chin Med. (2007) 41:7–8.
29. Mou X, Zhou D, Zhuang A, Liu Y, Chen H, Hu Y, et al. Evolution rules of TCM syndrome of patients with type 2 diabetes and diabetic nephropathy. China J Traditional Chin Med Pharmacy. (2016) 31:4.
30. Jian-Feng Z, Jia-Tuo XU, Li-Ping TU, Zhi-Feng Z, Xiao-Juan HU, Ji C, et al. Study on the characteristics of sub-health symptoms and TCM syndrome patterns distribution in 1754 non-disease population. Chin J Integrated Traditional Western Med. (2017) 37:934–8.
31. Tian Z, Fan Y, Sun X, Wang D, Guan Y, Zhang Y, et al. Predictive value of TCM clinical index for diabetic peripheral neuropathy among the type 2 diabetes mellitus population: A new observation and insight. Heliyon. (2023) 9:e17339. doi: 10.1016/j.heliyon.2023.e17339
32. Zou Y, Zhao L, Zhang J, Wang Y, Wu Y, Ren H, et al. 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. Ren Fail. (2022) 44:562–70. doi: 10.1080/0886022X.2022.2056053
33. Tan J, Zhang Z, He Y, Xu X, Yang Y, Xu Q, et al. Development and validation of a risk prediction model for osteoporosis in elderly patients with type 2 diabetes mellitus: a retrospective and multicenter study. BMC Geriatr. (2023) 23:698. doi: 10.1186/s12877-023-04306-1
34. Dai P, Chang W, Xin Z, Cheng H, Ouyang W, and Luo A. Retrospective study on the influencing factors and prediction of hospitalization expenses for chronic renal failure in China based on random forest and LASSO regression. Front Public Health. (2021) 9:678276. doi: 10.3389/fpubh.2021.678276
35. Chan L, Nadkarni GN, Fleming F, McCullough JR, Connolly P, Mosoyan G, et al. Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease. Diabetologia. (2021) 64:1504–15. doi: 10.1007/s00125-021-05444-0
36. Jiang A, Li J, Wang L, Zha W, Lin Y, Zhao J, et al. Multi-feature, Chinese-Western medicine-integrated prediction model for diabetic peripheral neuropathy based on machine learning and SHAP. Diabetes Metab Res Rev. (2024) 40:e3801. doi: 10.1002/dmrr.3801
37. Ying-Jun D, Yong-Hua X, Qiang FU, Li P, and Jin-Xi Z. Explanation and analysis on TCM pathology hypothesis micro-zhengjia of diabetic nephropathy. China J Traditional Chin Med Pharmacy. (2009) 24:27–30.
38. Xiao-Lin T, Qiang Z, Lin-Hua Z, Jia-Xing T, and Hospital G. Experience on TCM syndrome differentiation and treatment of diabetic nephropathy. China J Traditional Chin Med Pharmacy. (2014) 29:144–6.
39. Liu XJ, Hu XK, Yang H, Gui LM, Cai ZX, Qi MS, et al. A review of traditional chinese medicine on treatment of diabetic nephropathy and the involved mechanisms. Am J Chin Med. (2022) 50:1739–79. doi: 10.1142/S0192415X22500744
40. Wei J, Wu R, and Zhao D. Analysis on traditional Chinese medicine syndrome elements and relevant factors for senile diabetes. J Tradit Chin Med. (2013) 33:473–8. doi: 10.1016/S0254-6272(13)60151-X
41. Jiang M, Lou XE, Zhang X, Nan Q, Gao X, and Liu H. Development and validation of the diagnostic scale of traditional Chinese medicine syndrome elements for diabetic kidney disease. Ann Palliat Med. (2021) 10:12291–9. doi: 10.21037/apm-21-3147
42. Su X, Lin S, and Huang Y. Value of radiomics-based two-dimensional ultrasound for diagnosing early diabetic nephropathy. Sci Rep. (2023) 13:20427. doi: 10.1038/s41598-023-47449-2
43. Ghadirpour A, Tarzamni MK, Naghavi-Behzad M, Abedi-Azar S, Koushavar H, and Nezami N. Renal vascular Doppler ultrasonographic indices and carotid artery intima-media thickness in diabetic nephropathy. Med Ultrason. (2014) 16:95–9. doi: 10.11152/mu.2013.2066.162.ag1mkt2
44. Zhang L, Zhao F, Yang Y, Qi L, Zhang B, Wang F, et al. Association between carotid artery intima-media thickness and early-stage CKD in a Chinese population. Am J Kidney Dis. (2007) 49:786–92. doi: 10.1053/j.ajkd.2007.03.011
45. Yokoyama H, Aoki T, Imahori M, and Kuramitsu M. Subclinical atherosclerosis is increased in type 2 diabetic patients with microalbuminuria evaluated by intima-media thickness and pulse wave velocity. Kidney Int. (2004) 66:448–54. doi: 10.1111/j.1523-1755.2004.00752.x
46. Furtner M, Kiechl S, Mair A, Seppi K, Weger S, Oberhollenzer F, et al. Urinary albumin excretion is independently associated with carotid and femoral artery atherosclerosis in the general population. Eur Heart J. (2005) 26:279–87. doi: 10.1093/eurheartj/ehi014
47. Fleg JL, Mete M, Howard BV, Umans JG, Roman MJ, Ratner RE, et al. Effect of statins alone versus statins plus ezetimibe on carotid atherosclerosis in type 2 diabetes: the SANDS (Stop Atherosclerosis in Native Diabetics Study) trial. J Am Coll Cardiol. (2008) 52:2198–205. doi: 10.1016/j.jacc.2008.10.031
48. Chen J, Li W, Cao J, Lu Y, Wang C, and Lu J. Risk factors for carotid plaque formation in type 2 diabetes mellitus. J Transl Med. (2024) 22:18. doi: 10.1186/s12967-023-04836-7
49. Ito H, Komatsu Y, Mifune M, Antoku S, Ishida H, Takeuchi Y, et al. but not the stage of diabetic nephropathy graded by the urinary albumin excretion, is associated with the carotid intima-media thickness in patients with type 2 diabetes mellitus: a cross-sectional study. Cardiovasc Diabetol. (2010) 9:18. doi: 10.1186/1475-2840-9-18
50. Tziomalos K and Athyros VG. Diabetic nephropathy: new risk factors and improvements in diagnosis. Rev Diabetes Stud. (2015) 12:110–8. doi: 10.1900/RDS.2015.12.110
51. Bjornstad P, Lanaspa MA, Ishimoto T, Kosugi T, Kume S, Jalal D, et al. Fructose and uric acid in diabetic nephropathy. Diabetologia. (2015) 58:1993–2002. doi: 10.1007/s00125-015-3650-4
52. Tseng CH. Correlation of uric acid and urinary albumin excretion rate in patients with type 2 diabetes mellitus in Taiwan. Kidney Int. (2005) 68:796–801. doi: 10.1111/j.1523-1755.2005.00459.x
53. Feng B, Lu Y, Ye L, Yin L, Zhou Y, and Chen A. Mendelian randomization study supports the causal association between serum cystatin C and risk of diabetic nephropathy. Front Endocrinol (Lausanne). (2022) 13:1043174. doi: 10.3389/fendo.2022.1043174
54. Kuwabara M, Fukuuchi T, Aoki Y, Mizuta E, Ouchi M, Kurajoh M, et al. Exploring the multifaceted nexus of uric acid and health: A review of recent studies on diverse diseases. Biomolecules. (2023) 13:1519. doi: 10.3390/biom13101519
55. Lin ZH, Dai SF, Zhao JN, and Jiang Y. Application of urinary N-acetyl-on.glucosaminidase combined with serum retinol-binding protein in early detection of diabetic nephropathy. World J Diabetes. (2023) 14:883–91. doi: 10.4239/wjd.v14.i6.883
56. Wang J, Li Y, Han X, Hu H, Wang F, Yu C, et al. Association between serum bilirubin levels and decline in estimated glomerular filtration rate among patients with type 2 diabetes. J Diabetes Complications. (2016) 30:1255–60. doi: 10.1016/j.jdiacomp.2016.05.013
57. Sabanayagam C, He F, Nusinovici S, Li J, Lim C, Tan G, et al. Prediction of diabetic kidney disease risk using machine learning models: A population-based cohort study of Asian adults. . Elife. (2023) 12:e81878. doi: 10.7554/eLife.81878
58. Chen L, Shao X, and Yu P. Machine learning prediction models for diabetic kidney disease: systematic review and meta-analysis. Endocrine. (2024) 84:890–902. doi: 10.1007/s12020-023-03637-8
59. Ginsberg HN, Elam MB, Lovato LC, Crouse JR, Leiter L, Linz P, et al. Effects of combination lipid therapy in type 2 diabetes mellitus. N Engl J Med. (2010) 362:1563–74. doi: 10.1056/NEJMoa1001282
Keywords: machine learning, prediction model, early nephropathy, type 2 diabetes mellitus, elderly
Citation: Fang T, Yang Y, Zhuo F, Xie X, Song J and Kong L (2026) Multi-feature integrated machine learning prediction model for early nephropathy in elderly living with type 2 diabetes mellitus. Front. Endocrinol. 16:1660903. doi: 10.3389/fendo.2025.1660903
Received: 07 July 2025; Accepted: 29 December 2025; Revised: 15 September 2025;
Published: 21 January 2026.
Edited by:
Sanad Aburass, Luther College, United StatesReviewed by:
Nouran Salah, Ain Shams University, EgyptHua Zhou, First People’s Hospital of Changzhou, China
Copyright © 2026 Fang, Yang, Zhuo, Xie, Song and Kong. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Jialun Song, bWVpaml1MEAxNjMuY29t; Linghua Kong, a29uZ2xpbmdodWFAc2R1LmVkdS5jbg==
†ORCID: Linghua Kong, orcid.org.0000-0001-8289-4180