Diabetic Retinopathy, Classified Using the Lesion-Aware Deep Learning System, Predicts Diabetic End-Stage Renal Disease in Chinese Patients

Zhao, Lijun; Ren, Honghong; Zhang, Junlin; Cao, Yana; Wang, Yiting; Meng, Dan; Wu, Yucheng; Zhang, Rui; Zou, Yutong; Xu, Hong‐Xi; Li, Lin; Zhang, Jie; Cooper, Mark E.; Tong, Nanwei; Liu, Fang

doi:10.4158/ep-2019-0512

Cited by 31 publications

(37 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In patients with differing ALP level, differences in continuous variables were analyzed using one-way ANOVA, followed by the Bonferroni or Tukey methods for multiple comparisons, or the Kruskal–Wallis H test, as appropriate. Categorical variables were analyzed by Chi-square test or Fisher’s exact test [ 24 ].…”

Section: Methodsmentioning

confidence: 99%

“…We conducted a retrospective study of patients with T2DM and DN who underwent percutaneous renal biopsy between 2004 and 2018 at the West China Hospital of Sichuan University. Renal biopsy was performed in T2DM patients with renal damage who lacked absolute contraindications [22][23][24]. The diagnosis of T2DM was made according to the American Diabetes Association criteria [25].…”

Section: Setting and Populationmentioning

confidence: 99%

“…Baseline complete clinical data at the time of renal biopsy were abstracted from electronic medical records. The eGFR was evaluated using the Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) formula [24]. Serum ALP was measured using a colorimetric assay in accordance with a standardized method (Roche Modular Analyzer) [12].…”

Section: Clinical Information and Pathological Classificationmentioning

confidence: 99%

“…All patients were followed until March 2019. [24]. Survival cures for four quartiles of serum ALP levels were obtained using the Kaplan-Meier method and log-rank tests.…”

Section: Renal Outcomementioning

confidence: 99%

See 3 more Smart Citations

Association between serum alkaline phosphatase and renal outcome in patients with type 2 diabetes mellitus

Zhao

Ren

et al. 2020

Renal Failure

Self Cite

View full text Add to dashboard Cite

This retrospective study included 299 patients with type 2 diabetes mellitus and biopsy-confirmed diabetic nephropathy (DN) to investigate the prognostic value of alkaline phosphatase (ALP) for renal outcome. Cox proportional hazards models were used to estimate the hazard ratios (HRs) for the serum ALP level on renal outcome, which was defined as end-stage renal disease (ESRD) or a 50% decline in estimated glomerular filtration rate (eGFR) from baseline. The median baseline ALP was 80 IU/L with an interquartile range of 64-97 IU/L. Serum ALP was negatively associated with eGFR but positively associated with proteinuria and renal interstitial fibrosis. During a median follow-up period of 23 months, ESRD or a 50% declined in the eGFR occurred in 156 (52.2%) patients. The highest quartile of ALP was significantly associated with poor renal outcome, as defined above (HR 2.38, 95% confidence interval [CI] 1.09-5.17), when adjusted for sociodemographics, baseline eGFR, proteinuria, liver function parameters, parathyroid hormone levels, and renal pathological findings. Each standard deviation higher in the natural log-transformed ALP was associated with a 25% increased risk for poor renal outcome. Additionally, there was a graded increase in the risk for poor renal outcome with higher ALP in patients with nephrotic-range proteinuria. However, no significant associations were observed between serum ALP levels and renal outcome in patients with non-nephrotic-range proteinuria. In conclusion, an elevated ALP level was independently associated with poor renal outcome in patients with type 2 diabetes mellitus and nephrotic-range proteinuria after multivariate adjustment.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Setting and Populationmentioning

confidence: 99%

Section: Clinical Information and Pathological Classificationmentioning

confidence: 99%

“…All patients were followed until March 2019. [24]. Survival cures for four quartiles of serum ALP levels were obtained using the Kaplan-Meier method and log-rank tests.…”

Section: Renal Outcomementioning

confidence: 99%

See 2 more Smart Citations

Association between serum alkaline phosphatase and renal outcome in patients with type 2 diabetes mellitus

Zhao

Ren

et al. 2020

Renal Failure

Self Cite

View full text Add to dashboard Cite

show abstract

“…The indications for renal biopsy have been detailed described previously. 12 They were type 2 diabetes mellitus (T2DM) patients with renal damage who lacked absolute contraindications. Especially T2DM patients with obvious glomerular hematuria and/or short diabetic duration, or with sudden onset overt proteinuria met the requirement of renal biopsy.…”

Section: Patient Selection and Study Designmentioning

confidence: 99%

Combining glomerular basement membrane and tubular basement membrane assessment improves the prediction of diabetic end‐stage renal disease

Zhao

Zhang

Song

et al. 2021

Journal of Diabetes

Self Cite

View full text Add to dashboard Cite

Background: To address the prognostic value of combining tubular basement membrane (TBM) and glomerular basement membrane (GBM) thickness in diabetic nephropathy (DN).Methods: This retrospective study enrolled 110 patients with type 2 diabetes and biopsy-proven DN from 2011 to 2018. The pathological findings were confirmed according to the Renal Pathology Society classifications. GBM and TBM thicknesses were determined using the Haas' direct measurement/arithmetic mean method and orthogonal intercept method, respectively. Cox proportional hazard models were used to investigate the hazard ratios (HRs) for the influence of combined GBM and TBM thickness for predicting end-stage renal disease (ESRD). Results: Patients were assigned to three groups according to the median GBM and TBM thickness: GBM lo TBM lo (GBM < 681 nm and TBM < 1200 nm), GBM hi TBM lo /GBM lo TBM hi (GBM ≥ 681 nm and TBM < 1200 nm, or GBM < 681 nm and TBM ≥ 1200 nm), and GBM hi TBM hi (GBM ≥ 681 nm and TBM ≥ 1200 nm). The GBM hi TBM lo /GBM lo TBM hi and GBM hi TBM hi groups displayed poorer renal function, a more severe glomerular classification and interstitial inflammation, and poorer renal survival rates than the GBM lo TBM lo group The GBM hi TBM lo /GBM lo TBM hi and GBM hi TBM hi groups had adjusted HRs of 1.49 (95% confidence interval [CI], 1.21-9.75) and 3.07 (95% CI, 2.87-12.78), respectively, compared with the GBM lo TBM lo group.Conclusions: TBM thickness enhanced GBM thickness for renal prognosis in patients with type 2 diabetes.

show abstract

Retinal image‐based artificial intelligence in detecting and predicting kidney diseases: Current advances and future perspectives

Wen

Liu

et al. 2023

VIEW

View full text Add to dashboard Cite

Artificial intelligence (AI) has reformed the healthcare system with its compelling capabilities of processing biomedical data for disease diagnosis, prediction, and individualized management. The eye, as a non-invasive observation window for many systemic diseases, can be used to detect the signs of chronic kidney diseases, and other diseases like hypertension and type 2 diabetes mellitus, based on specific manifestations of retinal images. Recent advances using AI technology have posed a great potential of using retinal images for rapid mass screening and prognosis prediction of kidney diseases. Herein, we outlined the key applications of AI in ophthalmology and the detection of systemic diseases based on retinal imaging, especially the current progress of retinal image-based AI models for the detection and prediction of kidney diseases. We hope to shed light on the current opportunities and future challenges in this field to provide suggestions for further improvement and applications.

show abstract

Diabetic Retinopathy, Classified Using the Lesion-Aware Deep Learning System, Predicts Diabetic End-Stage Renal Disease in Chinese Patients

Cited by 31 publications

References 32 publications

Association between serum alkaline phosphatase and renal outcome in patients with type 2 diabetes mellitus

Association between serum alkaline phosphatase and renal outcome in patients with type 2 diabetes mellitus

Combining glomerular basement membrane and tubular basement membrane assessment improves the prediction of diabetic end‐stage renal disease

Retinal image‐based artificial intelligence in detecting and predicting kidney diseases: Current advances and future perspectives

Contact Info

Product

Resources

About