Two-Dimensional Ultrasound-Based Radiomics Nomogram for Diabetic Kidney Disease: A Pilot Study DOI Creative Commons
Xingyue Huang,

Yugang Hu,

Yao Zhang

и другие.

International Journal of General Medicine, Год журнала: 2024, Номер Volume 17, С. 1877 - 1885

Опубликована: Май 1, 2024

Objective: To establish a radiomics nomogram based on two-dimensional ultrasound for risk assessment of diabetic kidney disease (DKD) in patients with type 2 diabetes mellitus (T2DM). Methods: This study retrospectively collected images and clinical data from 52 T2DM who underwent renal biopsy our hospital January 2023 to August 2023. Based the pathological results, all were categorized into two groups: DKD (n=33) non-DKD (n=19). The radiomic features segmented pictures retrieved selected calculate each patient's rad-score. A predictive rad-score was then constructed validated calibration curve. Results: computed five imaging characteristics extracted images. developed rad-score, retinopathy, duration diabetes, glycosylated hemoglobin. Moreover, showed outstanding capability, discrimination as well therapeutic usefulness. Conclusion: We patientsThe model has been proven have good performance, showing its potential identifying assisting making appropriate early interventions. Keywords: disease, ultrasound, machine learning,

Язык: Английский

Gender Differences in the Incidence of Nephropathy and Changes in Renal Function in Patients with Type 2 Diabetes Mellitus: A Retrospective Cohort Study DOI Creative Commons
Fan Zhang, Yan Han, Guojun Zheng

и другие.

Diabetes Metabolic Syndrome and Obesity, Год журнала: 2024, Номер Volume 17, С. 943 - 957

Опубликована: Фев. 1, 2024

This research aims to examine and scrutinize gender variations in the incidence of diabetic nephropathy (DN) trajectory renal function type 2 diabetes mellitus (T2DM) patients.

Язык: Английский

Процитировано

5

The threshold effect of triglyceride glucose index on diabetic kidney disease risk in patients with type 2 diabetes: unveiling a non-linear association DOI Creative Commons
Huabin Wang, Guangming Chen, Dongmei Sun

и другие.

Frontiers in Endocrinology, Год журнала: 2024, Номер 15

Опубликована: Июнь 13, 2024

Background Previous studies have confirmed that the triglyceride glucose (TyG) index, recognized as a reliable marker of insulin resistance, is an important risk factor for diabetic kidney disease (DKD). However, it still unclear whether DKD continues to increase linearly with elevation TyG index. This study aimed thoroughly investigated intrinsic relationship between index and in type 2 diabetes (T2D). Methods cross-sectional included 933 patients T2D China, who were categorized into non-DKD groups stratified by levels. Logistic regression analysis identified independent factors DKD. The association was evaluated using restricted cubic spline (RCS) curves analysis. R package ‘CatPredi’ utilized determine optimal cut-off point followed threshold effect Results prevalence 33.01%. After adjusting confounding factors, prominent clinical DKD, showing highest odds ratio (OR 1.57 (1.26 - 1.94), P<0.001). RCS revealed non-linear interval risk. When ≤ 9.35, plateaued at low level; however, when > increased gradually rising Among each 1-unit associated 1.94-fold (OR=1.94 (1.10 3.43), P=0.022). Conclusion presented initially stable level, then above 9.35.

Язык: Английский

Процитировано

4

A SuperLearner approach for predicting diabetic kidney disease upon the initial diagnosis of T2DM in hospital DOI Creative Commons
Xiaomeng Lin,

Chao Liu,

Huaiyu Wang

и другие.

BMC Medical Informatics and Decision Making, Год журнала: 2025, Номер 25(1)

Опубликована: Март 26, 2025

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 predictive model for DKD in initial diagnosis type 2 (T2DM) using real-world data. Methods retrospectively examined data from 3,291 (1740 men, 1551 women) newly diagnosed T2DM at Ningbo Municipal Hospital Traditional Chinese Medicine (2011–2023). The dataset was randomly divided into training validation cohorts. Forty-six readily available medical characteristics the electronic records were used prediction models based on linear, non-linear, SuperLearner approaches. Model performance evaluated area under curve (AUC). SHapley Additive exPlanation (SHAP) interpret best-performing models. Results Among 3291 participants, 563 (17.1%) during median follow-up 2.53 years. exhibited highest AUC (0.7138, 95% confidence interval: [0.673, 0.7546]) holdout internal set predicting any Top-ranked features WBC_Cnt*, Neut_Cnt, Hct, Hb. High WBC_Cnt, low high Hb levels associated increased risk DKD. Conclusions developed validated T2DM. Using routinely clinical measurements, could predict hospital visits. Prediction accuracy SHAP-based interpretability may help improve early detection, targeted interventions, prognosis DM.

Язык: Английский

Процитировано

0

Risk prediction models for diabetic nephropathy among type 2 diabetes patients in China: a systematic review and meta-analysis DOI Creative Commons
Wenbin Xu, Yanfei Zhou,

Qian Jiang

и другие.

Frontiers in Endocrinology, Год журнала: 2024, Номер 15

Опубликована: Июль 3, 2024

Objective This study systematically reviews and meta-analyzes existing risk prediction models for diabetic kidney disease (DKD) among patients with type 2 diabetes, aiming to provide references scholars in China develop higher-quality models. Methods We searched databases including National Knowledge Infrastructure (CNKI), Wanfang Data, VIP Chinese Science Technology Journal Database, Biomedical Literature Database (CBM), PubMed, Web of Science, Embase, the Cochrane Library studies on construction DKD diabetes patients, up until 28 December 2023. Two researchers independently screened literature extracted evaluated information according a data extraction form bias assessment tool model studies. The area under curve (AUC) values were meta-analyzed using STATA 14.0 software. Results A total 32 included, 31 performing internal validation 22 reporting calibration. incidence rate ranged from 6.0% 62.3%. AUC 0.713 0.949, indicating have fair excellent accuracy. overall applicability included was good; however, there high bias, mainly due retrospective nature most studies, unreasonable sample sizes, conducted single center. Meta-analysis yielded combined 0.810 (95% CI: 0.780–0.840), good predictive performance. Conclusion Research is still its initial stages, lack clinical application. Future efforts could focus constructing high-performance, easy-to-use based interpretable machine learning methods applying them settings. Registration systematic review meta-analysis following Preferred Reporting Items Systematic Reviews Meta-Analyses (PRISMA) statement, recognized guideline such research. registration https://www.crd.york.ac.uk/prospero/ , identifier CRD42024498015.

Язык: Английский

Процитировано

2

A New Potent Inhibitor against α-Glucosidase Based on an In Vitro Enzymatic Synthesis Approach DOI Creative Commons
Huanyu Zhang,

Xiance Che,

Hongyan Jing

и другие.

Molecules, Год журнала: 2024, Номер 29(4), С. 878 - 878

Опубликована: Фев. 16, 2024

Inhibiting the activity of intestinal α-glucosidase is considered an effective approach for treating type II diabetes mellitus (T2DM). In this study, we employed in vitro enzymatic synthesis to synthesize four derivatives natural products (NPs) discovery therapeutic drugs T2DM. Network pharmacology analysis revealed that betulinic acid derivative P3 exerted its effects treatment T2DM through multiple targets. Neuroactive ligand–receptor interaction and calcium signaling pathway were identified as key pathways involved action compound The results molecular docking, dynamics (MD) simulations, binding free energy calculations indicate exhibits a more stable lower (−41.237 kcal/mol) with compared acarbose. addition, demonstrates excellent characteristics various pharmacokinetic prediction models. Therefore, holds promise lead development warrants further exploration. Finally, performed site-directed mutagenesis achieve targeted derivative. This work practical strategy discovering novel anti-hyperglycemic from NPs synthesized technology, providing potential insights into drug development.

Язык: Английский

Процитировано

1

Unveiling the utility of artificial intelligence for prediction, diagnosis, and progression of diabetic kidney disease: an evidence-based systematic review and meta-analysis DOI
Sagar Dholariya, Siddhartha Dutta, Amit Sonagra

и другие.

Current Medical Research and Opinion, Год журнала: 2024, Номер unknown, С. 1 - 31

Опубликована: Окт. 30, 2024

The purpose of this study was to conduct a systematic investigation the potential artificial intelligence (AI) models in prediction, detection diagnostic biomarkers, and progression diabetic kidney disease (DKD). In addition, we compared performance non-logistic regression (LR) machine learning (ML) conventional LR prediction models.

Язык: Английский

Процитировано

1

Two-Dimensional Ultrasound-Based Radiomics Nomogram for Diabetic Kidney Disease: A Pilot Study DOI Creative Commons
Xingyue Huang,

Yugang Hu,

Yao Zhang

и другие.

International Journal of General Medicine, Год журнала: 2024, Номер Volume 17, С. 1877 - 1885

Опубликована: Май 1, 2024

Objective: To establish a radiomics nomogram based on two-dimensional ultrasound for risk assessment of diabetic kidney disease (DKD) in patients with type 2 diabetes mellitus (T2DM). Methods: This study retrospectively collected images and clinical data from 52 T2DM who underwent renal biopsy our hospital January 2023 to August 2023. Based the pathological results, all were categorized into two groups: DKD (n=33) non-DKD (n=19). The radiomic features segmented pictures retrieved selected calculate each patient's rad-score. A predictive rad-score was then constructed validated calibration curve. Results: computed five imaging characteristics extracted images. developed rad-score, retinopathy, duration diabetes, glycosylated hemoglobin. Moreover, showed outstanding capability, discrimination as well therapeutic usefulness. Conclusion: We patientsThe model has been proven have good performance, showing its potential identifying assisting making appropriate early interventions. Keywords: disease, ultrasound, machine learning,

Язык: Английский

Процитировано

0