Acta Diabetologica最新文献

{"title":"Association between the triglyceride glucose-body roundness index and the incidence of cardiovascular disease among Chinese middle and old-aged adults: a nationwide prospective cohort study.","authors":"Wangyang Bai, Hangqi Chen, Huiqin Wan, Xiaofei Ye, Yi Ling, Jinfang Xu, Xiaojing Guo, Jia He","doi":"10.1007/s00592-025-02499-y","DOIUrl":"https://doi.org/10.1007/s00592-025-02499-y","url":null,"abstract":"<p><strong>Aim: </strong>Previous studies have suggested that the triglyceride glucose (TyG) index and body roundness index (BRI) are indicators of insulin resistance (IR) and are associated with the incidence of cardiovascular disease (CVD) among middle and old-aged adults. BRI is considered a more accurate indicator of the proportion of body fat and visceral fat than body mass index (BMI). However, it remains unclear whether the combined use of the TyG index and BRI, specifically the triglyceride glucose-body roundness index (TyG-BRI), is associated with the incidence of CVD among Chinese middle and old-aged adults.</p><p><strong>Methods: </strong>Data were obtained from the China Health and Retirement Longitudinal Study (CHARLS). The TyG-BRI index was computed using baseline measurements of triglycerides, fasting blood glucose, waist circumference, and height. Cox proportional hazards regression and restricted cubic spline (RCS) regression analyses were applied to assess the association between the TyG-BRI index and incident CVD (defined as cardiac events or stroke).</p><p><strong>Results: </strong>A total of 8,113 Chinese adults participated in this study, with a median age of 58 years, including 56.3% males. The fully adjusted Cox regression analysis revealed that individuals in the highest quartile (Q4) of the TyG-BRI index had a 59.1% increased risk of developing incident CVD compared to those in the lowest quartile (HR, 1.591 [95% CI, 1.330-1.902]). The TyG-BRI index showed a significant linear association with CVD incidence (P for nonlinearity = 0.447, P < 0.001). This association persisted after conducting subgroup and sensitivity analyses.</p><p><strong>Conclusions: </strong>This study introduced a novel TyG-BRI index, which integrated IR and body roundness as a comprehensive indicator, demonstrating its strong and independent association with increased CVD risk in a Chinese nationwide cohort. Our findings provide new insights into the interaction between metabolic dysfunction and cardiovascular risk, suggesting that the TyG-BRI index could serve as a practical tool for targeted preventive interventions.</p>","PeriodicalId":6921,"journal":{"name":"Acta Diabetologica","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143750224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Early prediction of gestational diabetes mellitus: the role of the pregnancy-specific triglycerides-glucose index and other fasting parameters in combination with dynamic testing.","authors":"Christian S Göbl, Tina Linder, Daniel Eppel, Grammata Kotzaeridi, Laura Weidinger, Sophie Zarotti, Thorsten Fischer, Monya Todesco Bernasconi, Mirjam Kunze, Nicole Ochsenbein-Koelble, Bettina Winzeler, Irene Hoesli, Evelyn A Huhn, Andrea Tura","doi":"10.1007/s00592-025-02490-7","DOIUrl":"https://doi.org/10.1007/s00592-025-02490-7","url":null,"abstract":"<p><p>The identification of mothers at risk for gestational diabetes mellitus (GDM) at start of pregnancy may be beneficial to improve perinatal outcomes. This study aims evaluating the predictive performance of fasting and dynamic indices of glucose metabolism at first trimester and their association with later GDM development. A cohort of 198 women received detailed metabolic assessment at median gestational age (13 weeks) including 75-g oral glucose tolerance test (OGTT) with assessment of glucose, insulin and C-peptide, and biochemical markers (including triglycerides) to calculate different indices of insulin sensitivity either at fasting and in the OGTT dynamic conditions. Moreover, parameters of β-cell function were assessed. A second OGTT was performed between 24 and 28 gestational weeks (GW) to identify women with GDM. We found that 28 women developed GDM, and, in univariable analysis, this was fairly predicted by several first trimester indices, both at fasting and in dynamic conditions. However, fasting indices containing maternal triglycerides showed better accuracy as compared to traditional indices (even the dynamic ones). In multivariable analysis, the best predictive model of GDM development included fasting and OGTT glucose values, HbA1c, and an insulin sensitivity marker that includes triglycerides (e.g. the improved triglyceride-glucose index, TyGIS). β-Cell function was not included in such predictive model, but at 24-28 GW it showed remarkable impairment in women with GDM. In conclusion, both fasting and dynamic parameters of glucose homeostasis at early pregnancy showed fair predictive accuracy for later GDM, with TyGIS showing excellent performance. β-Cell dysfunction role needs being further elucidated.</p>","PeriodicalId":6921,"journal":{"name":"Acta Diabetologica","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143750405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning-based models to predict type 2 diabetes combined with coronary heart disease and feature analysis-based on interpretable SHAP.","authors":"Yijian Ji, Hongyan Shang, Jing Yi, Wenhui Zang, Wenjun Cao","doi":"10.1007/s00592-025-02496-1","DOIUrl":"https://doi.org/10.1007/s00592-025-02496-1","url":null,"abstract":"<p><strong>Background: </strong>Type 2 diabetes and coronary heart disease exhibit heightened prevalence in the Chinese population, posing as leading causes of mortality. The combination of diabetes and coronary heart disease, due to its challenging diagnosis and poor prognosis, imposes a significant disease burden. In recent years, machine learning has frequently been employed in diagnostic applications within medical fields; however, predictive models for type 2 diabetes complicated by coronary heart disease have been confronted with issues such as lower predictive performance and interference from other comorbidities during prediction.</p><p><strong>Methods: </strong>This study enhances the predictive accuracy, sensitivity, specificity, F1 score, and AUC of models forecasting the coexistence of diabetes and coronary heart disease. We developed an advanced prediction model using XGBoost combined with SHAP for feature analysis. Through comparative feature selection, hyperparameter optimization, and computational efficiency analysis, we identified optimal conditions for model performance. External validation with independent datasets confirmed the model's robustness and generalizability, supporting its potential implementation in clinical practice.</p><p><strong>Results: </strong>This study compared three models-Random Forest, LightGBM, and XGBoost-and found that XGBoost exhibited superior performance in both efficacy and computational efficiency. The accuracy (Acc) of the XGBoost model was 0.8910, which improved to 0.8942 after hyperparameter tuning. External validation using datasets from Pingyang Hospital and Heji Hospital in Shanxi Province, China, yielded an AUC of 0.7897, demonstrating robust generalizability. By integrating SHAP (SHapley Additive exPlanations) for interpretability, our study identified bilirubin levels, basophil count, cholesterol levels, and age as key features for predicting the coexistence of type 2 diabetes mellitus (T2DM) and coronary heart disease (CHD). These findings are seamlessly consistent with the feature importance rankings determined by the XGBoost algorithm. The model demonstrates moderate predictive performance (AUC = 0.7879 in external validation) with practical interpretability, offering potential utility in improving diagnostic efficiency for T2DM-CHD comorbidity in resource-limited settings. However, its clinical implementation requires further validation in diverse populations.</p>","PeriodicalId":6921,"journal":{"name":"Acta Diabetologica","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143750481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Triglyceride-glucose index is a significant predictor of hospital mortality in non-diabetic critically ill patients with ischemic stroke: a retrospective cohort study of the MIMIC-IV database.","authors":"Ronghui Zhu, Qian He, Rui Wang, Yaoyong Tai, Chi Peng, Cheng Wu","doi":"10.1007/s00592-025-02502-6","DOIUrl":"https://doi.org/10.1007/s00592-025-02502-6","url":null,"abstract":"<p><strong>Background and aims: </strong>The relationship between the TyG index and outcomes in non-diabetic patients with ischemic stroke admitted to intensive care unit (ICU) has not been validated. This study aims to investigate the correlation between the TyG index and mortality in non-diabetic ICU patients with ischemic stroke.</p><p><strong>Methods: </strong>We collected data from ICU patients (≥ 18 years) with ischemic stroke and no diabetes. The primary outcome was hospital mortality, and the secondary outcomes were 30-day mortality following admission, hospital length of stay (LOS) and ICU LOS. Cox proportional hazards models and generalized linear models were employed to evaluate association between the TyG index and mortality and LOS, respectively. Nonlinear associations between the TyG index and outcomes were assessed using restricted cubic spline regression models.</p><p><strong>Results: </strong>A total of 1122 eligible patients were included in this study. The hospital mortality was 10.61%, and 30-day mortality was 16.93%. Multivariate Cox proportional hazards models and generalized linear models revealed the higher of TyG was significantly associated with increased hospital mortality [adjusted HR (95% CI) 1.22 (1.02-1.46), P = 0.0264], 30-day mortality [adjusted HR (95% CI) 1.26 (1.10-1.44), P = 0.0011] and prolonged hospital LOS [adjusted difference (95% CI) 0.52 (0.06-0.97), P = 0.0276].</p><p><strong>Conclusions: </strong>TyG index is a significant predictor of hospital mortality, 30-day mortality, and LOS in non-diabetic ICU patients with ischemic stroke, which could aid clinical decision-making in managing ischemic stroke.</p>","PeriodicalId":6921,"journal":{"name":"Acta Diabetologica","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143750615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of postprandial time trends and influencing factors of blood glucose and insulin in type 2 diabetes mellitus (T2DM) with metabolic dysfunction-associated steatotic liver disease (MASLD): a retrospective study based on propensity score matching (PSM).","authors":"Ge-Yao Qi, Fei Wang, Yuan-Bo Shi, Juan Feng, Jin Xu","doi":"10.1007/s00592-025-02503-5","DOIUrl":"https://doi.org/10.1007/s00592-025-02503-5","url":null,"abstract":"<p><strong>Background: </strong>Metabolic dysfunction-associated steatotic liver disease (MASLD) and type 2 diabetes mellitus (T2DM) are increasingly prevalent metabolic disorders worldwide, with a complex bidirectional relationship between them. Currently, there is a lack of research on the trajectories of blood glucose and insulin concentration over time after eating in patients with MASLD and T2DM.</p><p><strong>Methods: </strong>This clinical cohort included diagnosed T2DM patients in a large hospital over the past five years, was divided into an observation group (with MASLD) and a control group (without MASLD). The postprandial time trends of blood glucose and insulin concentration were analysed within two hours after eating. A strategy of backward iterative feature elimination combined with propensity score matching (PSM) was employed to screen for potential associated factors that might influence these trends.</p><p><strong>Results: </strong>In total, there were 521 in the observation group and 373 in the control group. In terms of blood glucose, the postprandial time-concentration trajectories for both groups shown a significant time main effect (F = 1145.567, P < 0.001), a significant group main effect (F = 15.340, P < 0.001), and a significant time*group interaction effect (F = 2.873, P = 0.035); After matching all the factors, the time*group interaction effect of blood glucose was not significant, but the differences from group main effect still existed. In terms of insulin, the postprandial time-concentration trajectories for both groups shown a significant time main effect (F = 309.429, P < 0.001), a significant group main effect (F = 6.319, P < 0.012), and a significant time*group interaction effect (F = 20.057, P < 0.001), but the trajectories crossed; After matching 4 factors such as Smoking, Essential Hypertension (EH), Body Mass Index (BMI), Triglyceride (TG) and Ca²⁺, neither the group main effect nor the time*group interaction effect on insulin was significant any more.</p><p><strong>Conclusion: </strong>The postprandial trends of blood glucose and insulin concentration over time shown significant differences between T2DM patients with and without MASLD. IL-6 might be associated with the insulin resistance, while EH and Ca²⁺ might be related to the islet β-cell function. Smoking and TG might participate in both of the above processes. The strategy of backward iterative with PSM had demonstrated a relatively satisfactory effect in feature screening.</p>","PeriodicalId":6921,"journal":{"name":"Acta Diabetologica","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143750042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FTZ alleviates lipid deposition in diabetic kidney disease by AMPK/ACC/SREBP signaling pathway.","authors":"Jie Tao, Xiao-Yu Zhang, Hai-Bo Tan, Min-Yi Huang, Yi-Qi Yang, Jiao Guo","doi":"10.1007/s00592-025-02492-5","DOIUrl":"https://doi.org/10.1007/s00592-025-02492-5","url":null,"abstract":"<p><p>Fufang Zhenzhu Tiaozhi capsule (FTZ) is a patented traditional Chinese medicine preparation that has been used clinically for nearly 10 years to treat hyperglycemia, hyperlipidemia, and other glucolipid metabolic diseases. Previous studies have shown that FTZ can improve diabetic kidney disease (DKD). However, the role and mechanism of FTZ in reducing renal lipid accumulation in DKD remain unclear. Phosphorylation of Adenosine 5'-Monophosphate-Activated Protein Kinase (AMPK), a key regulator of energy homeostasis, inhibits Acetyl-CoA Carboxylase (ACC) signaling, thereby reducing fatty acid synthesis and promoting fatty acid oxidation via carnitine palmitoyltransferase-1 (CPT-1). Sterol regulatory element-binding protein 1 (SREBP-1), a transcription factor, regulates lipid metabolism through fatty acid synthesis. This study investigated the anti-lipid accumulation effect and mechanism of FTZ in vitro and in vivo. Streptozotocin (40 mg/kg/d, i.p. for 5 days, consecutively) combined with a high-fat diet (HFD) were used to induce a DKD model in C57BL/6J mice, followed by FTZ (1, 2 g/kg/d, i.g.) or Losartan (30 mg/kg/d, i.g.) treatments for 12 weeks. High glucose (HG, 30 mM) combined with palmitic-acid (PA, 250 µM) were used to induce HK-2 cells injury, followed by FTZ (25, 50, or 100 µg/ml) or Compound C (an AMPK inhibitor, 10 µM) treatments for 24 h. Results showed that FTZ reduced blood lipids and improved renal function in DKD mice. In addition, compared with the control group, DKD mice and cells exhibited significantly increased lipid deposition. However, the effect of FTZ in alleviating lipid accumulation was reversed by Compound C. Furthermore, FTZ increased p-AMPK, p-ACC and CPT-1 protein expression while decreasing SREBP-1. These results indicate that FTZ effectively protects against lipid accumulation in DKD by regulating the AMPK/ACC/SREBP pathway, inhibiting de novo lipogenesis, providing a novel therapeutic strategy for DKD.</p>","PeriodicalId":6921,"journal":{"name":"Acta Diabetologica","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143750347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gestational diabetes severity stratification during pregnancy: role of plasma oleic acid as a possible early marker.","authors":"Chiara M Soldavini, Gabriele Piuri, Paola A Corsetto, Irma Colombo, Veronica Resi, Stefania Zava, Gabriele Rossi, Enrico Ferrazzi, Angela M Rizzo","doi":"10.1007/s00592-025-02487-2","DOIUrl":"https://doi.org/10.1007/s00592-025-02487-2","url":null,"abstract":"<p><p>Normal pregnancy is characterized by changes in lipid metabolism with significant implications for the health of both mother and offspring. When these changes develop into maternal dyslipidemia, a significant association with adverse pregnancy outcomes has been observed, including the development of gestational diabetes (GD), modulation of the inflammatory response, and excessive fetal growth. In the present study, we performed a lipidomic assessment of patients at GD diagnosis (24-28 weeks of gestation) and 12 weeks after diagnosis. We found higher levels of esterified oleic acid in plasma at the time of GD diagnosis in women who subsequently required pharmacological therapy to control blood glucose levels compared to those who did not require additional treatment, suggesting that the measurement of plasma oleic acid might be an additional tool for the early identification of patients with a more severe form of gestational diabetes. Moreover, plasma oleic acid levels showed a positive correlation with fetal growth in the context of adequate glycemic control, supporting a metabolic dysregulation of other pathways whose identification could help clinicians to discriminate different cases within the spectrum of severity of the disease. Finally, the correlation between plasma oleic acid and circulating BAFF levels at the time of diagnosis and 12 weeks later adds a possible mechanism to support the pro-inflammatory and pro-diabetic state in the metabolic set of GD. Overall, these findings strongly support the role of plasma oleic acid as a possible early marker for GD severity stratification during pregnancy.</p>","PeriodicalId":6921,"journal":{"name":"Acta Diabetologica","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143750471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Identification of FLVCR1 as the iron metabolism-related gene of statin-associated diabetes.","authors":"YiJia Huang, Kai Chen, Xiao Xiao, Shilong Zhong","doi":"10.1007/s00592-025-02491-6","DOIUrl":"https://doi.org/10.1007/s00592-025-02491-6","url":null,"abstract":"<p><strong>Aims: </strong>Long-term statin use has been linked to increased diabetes risk. Iron metabolism disruption may explain this association. The objective of this study was to identify the co-expression gene modules and the iron metabolism-related gene (IMG) linking statin administration and diabetes, making the hunt for novel therapeutic targets necessary.</p><p><strong>Methods: </strong>Weighted gene co-expression network analysis (WGCNA) was applied to the GSE130991 dataset to detect co-expressed gene modules. Enrichment analysis and single sample gene set enrichment analysis (ssGSEA) were conducted to characterize the biological processes and iron metabolism differences, respectively. Candidate IMGs were identified by intersecting WGCNA hub genes, differentially expressed genes (DEGs) from the statin-using and non-using obese individuals within the GSE130991 liver tissue dataset, and IMGs from Molecular Signatures Database Molecular Signatures Database (MisgDB). Mediation analysis was utilized to identify the definitive IMG. Expression validation was conducted through reverse transcription quantitative PCR (RT-qPCR) experiments and cross-referencing with additional datasets.</p><p><strong>Results: </strong>A shared gene module was identified between statin-users and diabetes patients, with functional enrichment analysis indicating involvement in iron ion binding. ssGSEA revealed differentially expressed iron metabolism in both statin-users and diabetes patients. Five IMG genes (CYP51A1, SC5D, MSMO1, SCD, and FLVCR1) were shortlisted, with FLVCR1 emerging as the key intermediary biomarker. FLVCR1 was positively correlated with insulin resistance and demonstrated robust predictive capabilities for diabetes. An increase in FLVCR1 mRNA levels was observed following statin treatment, as confirmed by RT-qPCR experiments and the GSE24188 dataset. Elevated FLVCR1 mRNA was also noted in diabetes patients across datasets GSE130991, GSE23343, and GSE95849.</p><p><strong>Conclusion: </strong>In this study, bioinformatics evidence supporting the association between statin use and diabetes was presented. FLVCR1 was identified as the iron metabolism-related mediator gene implicated in this relationship. Overall, our findings provide a theoretical foundation for new directions for future research exploring the complex interplay between statin treatment, iron metabolism regulation, and diabetes pathogenesis.</p>","PeriodicalId":6921,"journal":{"name":"Acta Diabetologica","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143717661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimized ensemble model for accurate prediction of cardiac vascular calcification in diabetic patients.","authors":"M Suresh, M Maragatharajan","doi":"10.1007/s00592-025-02485-4","DOIUrl":"https://doi.org/10.1007/s00592-025-02485-4","url":null,"abstract":"<p><strong>Aim: </strong>Cardiovascular diseases (CVD) are a major threat to diabetic patients, with cardiac vascular calcification (CVC) as a key predictive factor. This study seeks to improve the prediction of these calcifications using advanced machine learning (ML) algorithms. However, current ML and Artificial Intelligence (AI) methods face challenges such as limited sample sizes, insufficient data, high time complexity, long processing times, and significant implementation costs.</p><p><strong>Method: </strong>To predict CVC in diabetic patients, the Simple linear iterative clustering based Ensemble Artificial Neural Network (SLIC-EANN) model is proposed in this paper. In this research article, certain biochemical, imaging, and clinical data are used that are captured from Coronary computed tomography angiography (CCTA) dataset. The proposed model employs preprocessing techniques such as image normalization, image resizing, and image augmentation to clean and simplify the input images. Then Localization of the cardiac vascular calcification is done using the simple linear iterative clustering (SLIC) algorithm. The ensemble artificial neural network (EANN) classifies calcification severity by integrating outputs from three machine learning techniques Support Vector Machine (SVM), Gradient Boosting (GB), and Decision Tree (DT).</p><p><strong>Results: </strong>This method achieves an accuracy of 98.7% and an error rate of 1.3%, outperforming existing techniques.</p><p><strong>Conclusion: </strong>A comprehensive analysis is conducted in this research article that concludes that the proposed model achieved better prediction performances of calcification in diabetic patients.</p>","PeriodicalId":6921,"journal":{"name":"Acta Diabetologica","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143668623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Different formulations of semaglutide and oxidative stress in subjects with type 2 diabetes and MASLD: an open-label, real-life study.","authors":"Giovanni Petralli, Alice Del Zoppo, Chiara Rovera, Francesco Raggi, Antonio Salvati, Diego Moriconi, Mariarosaria Distaso, Maurizia Rossana Brunetto, Anna Solini","doi":"10.1007/s00592-025-02482-7","DOIUrl":"https://doi.org/10.1007/s00592-025-02482-7","url":null,"abstract":"","PeriodicalId":6921,"journal":{"name":"Acta Diabetologica","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143661920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}