Correction: Multi-feature integrated machine learning prediction model for early nephropathy in elderly living with type 2 diabetes mellitus

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)(12)(13)(14)(15)(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)(20)(21)(22)(23)(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, multifeature 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.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.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) 0.05), confirming the comparability between the training and validation sets (Table 1).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 (Fig. 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.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 (Fig. S1).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 (Fig. 3). Based on these findings, Mod C was selected to construct a nomogram for clinical application (Fig. 4).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 (Fig. S2; Fig. 5; Table 2). SHAP analysis identified DR, UA, and carotid artery plaque as the top three predictors influencing early DN in elderly T2DM patients (Fig. S3).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 (Fig. S4).Forest plots and age-specific nomograms were generated to visualize risk factors for each age group and to facilitate clinical decision-making (Fig. S5 andS6).Numerous established models for predicting diabetic nephropathy (DN) primarily focus on patients with end-stage renal disease or renal failure (8)(9)(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.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 earlystage 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)(43)(44)(45)(46)(47)(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.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.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).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 early detection and has several (2) of TCM Although standardized were the and of in TCM symptom evaluation a and tools (e.g., to enhance The subgroup of patients aged ≥80 years was in and in which may have the predictive performance in this studies are to these Ultrasound imaging in and operator were not potentially affecting the of imaging data. imaging be in nephropathy was not documented that < 60 2 in the of in patients with diabetes and its prevalence is In this study, the diagnosis of early kidney disease is based on We not In we focus on the of prediction study and validated predictive models for early DN in elderly living with T2DM, incorporating clinical, TCM, and ultrasound imaging RF model demonstrated predictive performance, and subgroup analyses confirmed its applicability across age These findings have significant for early DN screening, and particularly in aging Further research is to the and to the model in clinical