Long-term HbA1c variability and the development and progression of diabetic retinopathy in subjects with type 2 diabetes

Dynamic observation and analysis of factors influencing the progression of diabetic retinopathy

OBJECTIVE

To actively monitor and analyze the factors that affect the advancement of diabetic retinopathy (DR).

METHOD

In this study, we prospectively recruited patients diagnosed with non-proliferative diabetic retinopathy (NPDR) for concurrent monitoring. A total of 75 patients who transitioned from NPDR to proliferative diabetic retinopathy (PDR) comprised the progression group, while 112 NPDR patients who did not develop PDR formed the stable group in a prospective cohort study. Follow-up assessments occurred every six months, and patients were observed continuously over an eight-year period. Clinical parameters from both NPDR and PDR groups were collected to assess the stability of these indicators (with a coefficient of variation [CV] > 5 % indicating instability and CV < 5 % indicating stability).

RESULTS

In the NPDR cohort, 80.4 % Control the stability ratio regulation of glycosylated hemoglobin (HbA1c), whereas in the PDR cohort, 80.0 % Control the proportion of instability (P = 0.001); for blood creatinine (Cr), 64.3 % of NPDR patients maintained stable levels, contrasting with 77.3 % of PDR patients with fluctuating levels (P = 0.001). Blood urea nitrogen (BUN) and homocysteine (HCY) control demonstrated instability in both NPDR and PDR groups. Instability in regulating HbA1c, Cr, BUN, and HCY served as independent risk factors for DR progression, with significant associations found between HbA1c CV (HR: 15.586; 95 % CI: 14.205-15.988; p = 0.001), Cr CV (HR: 9.231; 95 % CI: 9.088-10.235; p = 0.005), BUN CV (HR: 3.568; 95 % CI: 3.183-4.367; p = 0.01), and HCY CV (HR: 8.678; 95 % CI: 7.754-8.998；p = 0.003).

CONCLUSION

Inadequate regulation of HbA1c, Cr, BUN, and HCY independently impact the advancement of DR.

Prevalence and Progression of Diabetic Retinopathy in a Tertiary Care Setting: An Initial Review With Recommended Screening Protocols

INTRODUCTION

The objective of this study is to evaluate diabetic patients with either normal fundus or non-proliferative diabetic retinopathy (NPDR) changes, examine retinal alterations during follow-up, and propose follow-up guidelines within a tertiary eye care setting.

METHODS

A five-year prospective longitudinal study is being conducted at the Diabetic Clinic of Al Ibrahim Eye Hospital/Isra Postgraduate Institute of Ophthalmology, Karachi. Induction for the research took place from October 2021 to March 2022, and a two-year preliminary report is presented here. Newly diagnosed type II diabetic patients with normal fundus or NPDR of any stage, irrespective of age, gender, or glycemic status, who were willing to participate and agreed to follow-ups, were included. Patients with proliferative diabetic retinopathy (PDR), diabetic macular edema (DME), fundus non-visibility, or systemic complications of diabetes were excluded.

RESULTS

A total of 251 patients were enrolled, consisting of 80 individuals with a normal fundus and 171 with different stages of NPDR, including mild (N=59), moderate (N=91), and severe (N=21) retinopathy. The incidence of progression from mild to moderate NPDR was noted to be 52.5%, with a median time of 3.5 months. Progression from moderate to severe NPDR occurred in 37.1% of cases, with a median time of 4.5 months. Similarly, DME developed in 5% of patients with mild NPDR over eight months, in 22.2% with moderate NPDR over seven months, and in 37.5% with severe NPDR over 4.4 months.

CONCLUSION

This study emphasizes the urgent need to revise diabetic retinopathy (DR) monitoring protocols for our Pakistani (Southeast Asian) population. The rapid progression of NPDR and the high rates of DME development demand more frequent screenings. Current guidelines recommending annual screenings are inadequate. Biannual screenings for patients with a normal fundus or mild NPDR, and quarterly assessments for those with moderate or severe NPDR, are necessary.

Cut-off value of glycated hemoglobin A1c for detecting diabetic retinopathy in the Chinese population

BACKGROUND

Glycated hemoglobin A1c (HbA1c) is considered the most suitable for diabetes mellitus diagnosis due to its accuracy and convenience. However, the effect of HbA1c on diabetic retinopathy (DR) in the Han and Korean populations in Jilin, China, remains inconclusive.

AIM

To determine the best cut-off of HbA1c for diagnosing DR among the Chinese.

METHODS

This cross-sectional study included 1933 participants from the Yanbian area of Jilin Province, China. Trained investigators employed a questionnaire-based survey, physical examination, laboratory tests, and fundus photography for the investigation. The best cut-off value for HbA1c was established via the receiver operating characteristic curve. The factors associated with HbA1c-associated risk factors were determined via linear regression.

RESULTS

The analysis included 887 eligible Chinese Han and Korean participants, 591 of whom were assigned randomly to the training set and 296 to the validation set. The prevalence of DR was 3.27% in the total population. HbA1c of 6.2% was the best cut-off value in the training set, while it was 5.9% in the validation set. In both Chinese Han and Korean populations, an HbA1c level of 6.2% was the best cut-off value. The optimal cut-off values of fasting blood glucose (FBG) ≥ 7 mmol/L and < 7 mmol/L were 8.1% and 6.2% respectively in Han populations, while those in Korean populations were 6.9% and 5.3%, respectively. Age, body mass index, and FBG were determined as the risk factors impacting HbA1c levels.

CONCLUSION

HbA1c may serve as a useful diagnostic indicator for DR. An HbA1c level of 6.2% may be an appropriate cut-off value for DR detection in the Chinese population.

Assessing the importance of risk factors for diabetic retinopathy in patients with type 2 diabetes mellitus: Results from the classification and regression tree models

BACKGROUND

Diabetic retinopathy (DR) is one of the serious complications of diabetes mellitus (DM). Many studies have identified the risk factors associated with DR, but there is not much evidence on the importance of these factors for DR. This study aimed to investigate the associated factors for patients with type 2 DM (T2DM) and calculate the importance of the identified factors.

MATERIALS AND METHODS

Using probability proportionate to size sampling method in this community-based cross-sectional study, 22 community health service centers were selected from 10 administrative districts in Shenzhen, China. Approximately 60 T2DM patients were recruited from each center. The participants completed a structural questionnaire, had their venous blood collected, and underwent medical examinations and fundus photography. Logistic regression models were used to identify the risk factors of DR. The classification and regression tree (CART) model was used to calculate the importance of the identified risk factors.

RESULTS

This study recruited 1097 T2DM patients, 266 of whom were identified as having DR, yielding a prevalence rate of 24.3% (95% confidence interval [CI]: 21.7%-26.9%). Results showed that a longer duration of DM, indoor-type lifestyle, and higher levels of hemoglobin A1c (HbA1c) or urea increased the risk of DR. Patients with HbA1c values ≥7% were about 2.45 times (odds ratio: 2.45; 95% CI: 1.83-3.29) more likely to have DR than their counterparts. The CART model found that the values of variable importance for HbA1c, DM duration, lifestyle (i.e., indoor type), and urea were 48%, 37%, 10%, and 4%, respectively.

CONCLUSION

The prevalence of DR is high for T2DM patients who receive DM health management services from the primary healthcare system. HbA1c is the most important risk factor for DR. Integration of DR screening and HbA1c testing into the healthcare services for T2DM to reduce vision impairment and blindness is urgently warranted.

An interpretable predictive deep learning platform for pediatric metabolic diseases

OBJECTIVES

Metabolic disease in children is increasing worldwide and predisposes a wide array of chronic comorbid conditions with severe impacts on quality of life. Tools for early detection are needed to promptly intervene to prevent or slow the development of these long-term complications.

MATERIALS AND METHODS

No clinically available tools are currently in widespread use that can predict the onset of metabolic diseases in pediatric patients. Here, we use interpretable deep learning, leveraging longitudinal clinical measurements, demographical data, and diagnosis codes from electronic health record data from a large integrated health system to predict the onset of prediabetes, type 2 diabetes (T2D), and metabolic syndrome in pediatric cohorts.

RESULTS

The cohort included 49 517 children with overweight or obesity aged 2-18 (54.9% male, 73% Caucasian), with a median follow-up time of 7.5 years and mean body mass index (BMI) percentile of 88.6%. Our model demonstrated area under receiver operating characteristic curve (AUC) accuracies up to 0.87, 0.79, and 0.79 for predicting T2D, metabolic syndrome, and prediabetes, respectively. Whereas most risk calculators use only recently available data, incorporating longitudinal data improved AUCs by 13.04%, 11.48%, and 11.67% for T2D, syndrome, and prediabetes, respectively, versus models using the most recent BMI (P < 2.2 × 10-16).

DISCUSSION

Despite most risk calculators using only the most recent data, incorporating longitudinal data improved the model accuracies because utilizing trajectories provides a more comprehensive characterization of the patient's health history. Our interpretable model indicated that BMI trajectories were consistently identified as one of the most influential features for prediction, highlighting the advantages of incorporating longitudinal data when available.

Comparative Analysis of Biomarkers in Type 2 Diabetes Patients With and Without Comorbidities: Insights Into the Role of Hypertension and Cardiovascular Disease

Background

Type 2 diabetes mellitus (T2DM) are 90% of diabetes cases, and its prevalence and incidence, including comorbidities, are rising worldwide. Clinically, diabetes and associated comorbidities are identified by biochemical and physical characteristics including glycemia, glycated hemoglobin (HbA1c), and tests for cardiovascular, eye and kidney disease.

Objectives

Diabetes may have a common etiology based on inflammation and oxidative stress that may provide additional information about disease progression and treatment options. Thus, identifying high-risk individuals can delay or prevent diabetes and its complications.

Design

In patients with or without hypertension and cardiovascular disease, as part of progression from no diabetes to T2DM, this research studied the changes in biomarkers between control and prediabetes, prediabetes to T2DM, and control to T2DM, and classified patients based on first-attendance data. Control patients and patients with hypertension, cardiovascular, and with both hypertension and cardiovascular diseases are 156, 148, 61, and 216, respectively.

Methods

Linear discriminant analysis is used for classification method and feature importance, This study examined the relationship between Humanin and mitochondrial protein (MOTSc), mitochondrial peptides associated with oxidative stress, diabetes progression, and associated complications.

Results

MOTSc, reduced glutathione and glutathione disulfide ratio (GSH/GSSG), interleukin-1β (IL-1β), and 8-isoprostane were significant (P < .05) for the transition from prediabetes to t2dm, highlighting importance of mitochondrial involvement. complement component 5a (c5a) is a biomarker associated with disease progression and comorbidities, gsh gssg, monocyte chemoattractant protein-1 (mcp-1), 8-isoprostane being most important biomarkers.

Conclusions

Comorbidities affect the hypothesized biomarkers as diabetes progresses. Mitochondrial oxidative stress indicators, coagulation, and inflammatory markers help assess diabetes disease development and provide appropriate medications. Future studies will examine longitudinal biomarker evolution.

What else can we do to prevent diabetic retinopathy?

The classical modifiable factors associated with the onset and progression of diabetic retinopathy are the suboptimal control of blood glucose levels and hypertension, as well as dyslipidaemia. However, there are other less recognised modifiable factors that can play a relevant role, such as the presence of obesity or the abnormal distribution of adipose tissue, and others related to lifestyle such as the type of diet, vitamin intake, exercise, smoking and sunlight exposure. In this article we revisit the prevention of diabetic retinopathy based on modulating the modifiable risk factors, as well as commenting on the potential impact of glucose-lowering drugs on the condition. The emerging concept that neurodegeneration is an early event in the development of diabetic retinopathy points to neuroprotection as a potential therapeutic strategy to prevent the advanced stages of the disease. In this regard, the better phenotyping of very early stages of diabetic retinopathy and the opportunity of arresting its progression using treatments targeting the neurovascular unit (NVU) are discussed.

Association Between the Variability of Glycated Hemoglobin and Retinopathy in Patients with Type 2 Diabetes Mellitus: A Meta-Analysis

Visit-to-visit variability of glycated hemoglobin (HbA1c) is a marker of long-term glycemic fluctuation, which has been related to increased risk of macrovascular complications in patients with type 2 diabetes mellitus (T2DM). The association between HbA1c variability and retinopathy in patients with T2DM, however, has been inconsistent in previous studies. In order to fully evaluate the above association, we conducted a meta-analysis. Observational studies related to the aim of the meta-analysis were identified by search of PubMed, Web of Science, and Embase databases. Studies with HbA1c variability evaluated as the standard deviation (SD) and/or the coefficients of variation (CV) of HbA1c were included. The results were analyzed using a random-effects model that incorporated potential heterogeneity between studies. Twelve observational studies involving 44 662 T2DM patients contributed to the meta-analysis. Overall, 5150 (11.5%) patients developed retinopathy. Pooled results showed that compared to patients with lower HbA1c variability, T2DM patients with higher HbA1c-SD (relative risk [RR]: 1.48, 95% confidence interval [CI]: 1.24 to 1.78, p<0.001, I2=34%) and higher HbA1c-CV (RR: 1.29, 95% CI: 1.05 to 1.59, p=0.02, I2=0%) were both associated with higher risk of DR. For studies with HbA1c-SD, the association was not significantly affected by study characteristics such as country, study design, mean age, disease duration, adjustment of mean HbA1c, or quality scores (p for subgroup difference all>0.05). In conclusion, higher HbA1c variability may be associated with an increased risk of retinopathy in patients with T2DM.

Long-term HbA1c variability and macro-/micro-vascular complications in type 2 diabetes mellitus: a meta-analysis update

AIMS

The aim of the present study was to evaluate, by means of a meta-analysis approach, whether new available data, appeared on qualified literature, can support the effectiveness of an association of HbA1c variability with the risk of macro- and/or micro-vascular complications in type 2 diabetes mellitus (T2DM).

METHODS

The meta-analysis was conducted according to PRISMA Statement guidelines and considered published studies on T2DM, presenting HbA1c variability as standard deviation (SD) or its derived coefficient of variation (CV). Literature search was performed on PubMed in the time range 2015-July 2022, with no restrictions of language.

RESULTS

Twenty-three selected studies fulfilled the aims of the present investigation. Overall, the analysis of the risk as hazard ratios (HR) indicated a significant association between the HbA1c variability, expressed either as SD or CV, and the complications, except for neuropathy. Macro-vascular complications were all significantly associated with HbA1c variability, with HR 1.40 (95%CI 1.31-1.50, p < 0.0001) for stroke, 1.30 (95%CI 1.25-1.36, p < 0.0001) for transient ischaemic attack/coronary heart disease/myocardial infarction, and 1.32 (95%CI 1.13-1.56, p = 0.0007) for peripheral arterial disease. Micro-vascular complications yielded HR 1.29 (95%CI 1.22-1.36, p < 0.0001) for nephropathy, 1.03 (95%CI 0.99-1.08, p = 0.14) for neuropathy, and 1.15 (95%CI 1.08-1.24, p < 0.0001) for retinopathy. For all-cause mortality, HR was 1.33 (95%CI 1.27-1.39, p < 0.0001), and for cardiovascular mortality 1.25 (95%CI 1.17-1.34, p < 0.0001).

CONCLUSIONS

Our meta-analysis on HbA1c variability performed on the most recent published data since 2015 indicates positive association between HbA1c variability and macro-/micro-vascular complications, as well as mortality events, in T2DM, suggesting that this long-term glycaemic parameter merits further attention as a predictive, independent risk factor for T2DM population.

HbA1c Variability and Cardiovascular Events in Patients with Prostate Cancer Receiving Androgen Deprivation Therapy

Background

Androgen deprivation therapy (ADT) worsens glycaemic control and cardiovascular outcomes. The prognostic value of visit-to-visit HbA1c variability (VVHV) has been unexplored in prostate cancer (PCa) patients receiving ADT.

Objective

To explore the effect of ADT on VVHV and the cardiovascular prognostic value of VVHV.

Design setting and participants

PCa patients receiving ADT in Hong Kong between January 1, 1993 and March 31, 2021 were included in this retrospective cohort study. Those with fewer than three HbA1c results available within 3 yr after ADT initiation, <6 mo of ADT, missing baseline HbA1c, prior diagnosis of any component of major adverse cardiovascular events (MACEs), and MACEs occurring within 3 yr were excluded. Patients were followed up until September 31, 2021.

Outcome measurements and statistical analysis

The outcome was MACEs (composite of heart failure, myocardial infarction, stroke, and cardiovascular mortality). VVHV was calculated from HbA1c levels within 3 yr after and, separately where available, before ADT initiation using coefficient of variation (CV; standard deviation [SD] divided by mean) and average real variability (ARV; average difference between consecutive measurements).

Results and limitations

Altogether, 1065 patients were analysed (median age 74.4 yr old [interquartile range 68.3-79.5 yr]). In 709 patients with VVHV available before and after ADT initiation, VVHV increased after ADT initiation (p < 0.001), with 473 (66.2%) and 474 (66.9%) having increased CV and ARV, respectively. Over a median follow-up of 4.3 yr (2.8-6.7 yr), higher VVHV was associated with a higher risk of MACEs (adjusted hazard ratio [per SD] for CV 1.21 [95% confidence interval: 1.02, 1.43], p = 0.029; ARV 1.25 [1.06, 1.48], p = 0.008). Limitations included residual confounding and selection bias.

Conclusions

In PCa patients receiving ADT, VVHV increased after ADT initiation. Higher VVHV was associated with an increased risk of MACEs.

Patient summary

In prostate cancer patients receiving androgen deprivation therapy (ADT), glycaemic control is less stable after initiating ADT, which was associated with an increased cardiovascular risk.

Glycemic Control after Initiation of Anti-VEGF Treatment for Diabetic Macular Edema

Diabetic macular edema (DME) induces visual disturbance, and intravitreal injections of anti-vascular endothelial growth factor (VEGF) drugs are the accepted first-line treatment. We investigate its impact on glycemic control after starting VEGF treatment for DME on the basis of a questionnaire and changes in hemoglobin A1c (HbA1c). We conducted a retrospective multicenter study analyzing 112 patients with DME who underwent anti-VEGF therapy and their changes in HbA1c over two years. Central retinal thickness and visual acuity significantly improved at three months and throughout the period after initiating therapy (p < 0.0001); a significant change in HbA1c was not found. A total of 59.8% of patients became more active in glycemic control through exercise and diet therapy after initiating therapy, resulting in a significantly lower HbA1c at 6 (p = 0.0047), 12 (p = 0.0003), and 18 (p = 0.0117) months compared to patients who did not. HbA1c was significantly lower after 18 months in patients who stated that anti-VEGF drugs were expensive (p = 0.0354). The initiation of anti-VEGF therapy for DME affects HbA1c levels in relation to more aggressive glycemic control.

Identification of robust deep neural network models of longitudinal clinical measurements

Deep learning (DL) from electronic health records holds promise for disease prediction, but systematic methods for learning from simulated longitudinal clinical measurements have yet to be reported. We compared nine DL frameworks using simulated body mass index (BMI), glucose, and systolic blood pressure trajectories, independently isolated shape and magnitude changes, and evaluated model performance across various parameters (e.g., irregularity, missingness). Overall, discrimination based on variation in shape was more challenging than magnitude. Time-series forest-convolutional neural networks (TSF-CNN) and Gramian angular field(GAF)-CNN outperformed other approaches (P < 0.05) with overall area-under-the-curve (AUCs) of 0.93 for both models, and 0.92 and 0.89 for variation in magnitude and shape with up to 50% missing data. Furthermore, in a real-world assessment, the TSF-CNN model predicted T2D with AUCs reaching 0.72 using only BMI trajectories. In conclusion, we performed an extensive evaluation of DL approaches and identified robust modeling frameworks for disease prediction based on longitudinal clinical measurements.

Correlation of Glucose and Lipid Metabolism Levels and Serum Uric Acid Levels with Diabetic Retinopathy in Type 2 Diabetic Mellitus Patients

Objective. The aim of this study was to observe the association between the development of diabetic retinopathy (DR) in type 2 diabetes mellitus (T2DM) and the levels of glucose and lipid metabolism and serum uric acid (SUA) levels. Methods. A retrospective analysis was performed on 97 patients with T2DM who were admitted to our endocrinology department from June 2019 to April 2021 with complete data; the patients were divided into DR and no DR groups (NDR) according to the presence or absence of DR. Their clinical history and biochemical test indexes were collected, and the fundus was examined by fundus photography and the fundoscopic examination method, and the vascular diameter was measured by using a computer software. All clinical data, medical history, and biochemical test indexes were compared between the two groups, and logistic regression was used to analyze the risk factors of DR. Results. The duration of DM disease, fasting blood glucose (FBG), glycosylated hemoglobin, type A1C (HbA1c) levels, cholesterol (TC), triacylglycerol (TG), low-density lipoprotein cholesterol (LDL-C), and SUA levels were higher in the DR group than those in the NDR group, and the differences were significant ( $P<0.05$ ). The difference between the NDR group and the DR group in terms of gender, age, BMI, DBP, SBP, family history of DM, FINS, and HDL-C levels was not significant ( $P>0.05$ ). The results of multifactorial analysis showed that the four variables of DM duration, HbA1c, TG, and SUA were still risk factors for the development of DR ( $P<0.05$ ). Further receiver operating characteristic (ROC) analysis showed that the areas under the curves (AUCs) for the duration of DM disease, HbA1c, TG, and SUA to predict the occurrence of DR were 0.740 (95% CI 0.639–0.841), 0.767 (95% 0.672–0.862), 0.721 (95% CI 0.617–0.826), and 0.693 (95% CI 0.588∼0.797), respectively. Conclusion. The lesions of DR in T2DM patients have a close relationship with the course of DM, HbA1c, TG, and SUA, and the course of DM, HbA1c, TG, and SUA has a good predictive value for the occurrence of DR.

Reduced Serum Magnesium Levels Are Associated with the Occurrence of Retinopathy in Patients with Type 2 Diabetes Mellitus: a Retrospective Study

The aim of this study is to explore the relationship between serum magnesium (Mg²⁺) level and diabetic retinopathy (DR) in patients with type 2 diabetes mellitus (T2DM). The clinical data of 2222 patients with T2DM, including 713 patients with DR and 1509 patients without DR, between September 2016 and August 2020 in our hospital, were analyzed retrospectively. Further, the role and predictive value of serum Mg²⁺ on the prevalence of DR were determined through logistic regression and the receiver operating characteristic (ROC) curve respectively. The level of serum Mg²⁺ was lower in DR group than that in non-DR group (0.92 vs 0.88 mmol/L, P < 0.001). Stratified serum Mg²⁺ levels into quartiles (Q1-Q4), the first (Q1, Mg²⁺ ≤ 0.85 mmol/L) and fourth quartile (Q4, ≥ 0.96 mmol/L) represented the lowest and highest quartile, respectively. And the incidence of DR was obviously higher in Q1 and Q2 than that in Q3 and Q4 (50.9% and 30.2% vs 23.5% and 21%, respectively). Logistic regression demonstrated that there remained an independent association between lower serum Mg²⁺ levels and the occurrence of DR (OR were 3.907 and 1.709 in Q1 and Q2, respectively) no matter whether the interference of confounding variables. ROC curve showed the best cut-off value of serum Mg²⁺ level in predicting the occurrence of DR was 0.875 mmol/L. Lower Mg²⁺ levels are related with an increased risk of developing DR. Serum Mg²⁺ level can be a potential clinical indicator to help identify DR in patients with T2DM.

Diagnostic circulating biomarkers to detect vision-threatening diabetic retinopathy: Potential screening tool of the future?

With the increasing prevalence of diabetes in developing and developed countries, the socio-economic burden of diabetic retinopathy (DR), the leading complication of diabetes, is growing. Diabetic retinopathy (DR) is currently one of the leading causes of blindness in working-age adults worldwide. Robust methodologies exist to detect and monitor DR; however, these rely on specialist imaging techniques and qualified practitioners. This makes detecting and monitoring DR expensive and time-consuming, which is particularly problematic in developing countries where many patients will be remote and have little contact with specialist medical centres. Diabetic retinopathy (DR) is largely asymptomatic until late in the pathology. Therefore, early identification and stratification of vision-threatening DR (VTDR) is highly desirable and will ameliorate the global impact of this disease. A simple, reliable and more cost-effective test would greatly assist in decreasing the burden of DR around the world. Here, we evaluate and review data on circulating protein biomarkers, which have been verified in the context of DR. We also discuss the challenges and developments necessary to translate these promising data into clinically useful assays, to detect VTDR, and their potential integration into simple point-of-care testing devices.

Diabetic retinopathy risk prediction in patients with type 2 diabetes mellitus using a nomogram model

BACKGROUND

This study aims to develop a diabetic retinopathy (DR) hazard nomogram for a Chinese population of patients with type 2 diabetes mellitus (T2DM).

METHODS

We constructed a nomogram model by including data from 213 patients with T2DM between January 2019 and May 2021 in the Affiliated Hospital of Zunyi Medical University. We used basic statistics and biochemical indicator tests to assess the risk of DR in patients with T2DM. The patient data were used to evaluate the DR risk using R software and a least absolute shrinkage and selection operator (LASSO) predictive model. Using multivariable Cox regression, we examined the risk factors of DR to reduce the LASSO penalty. The validation model, decision curve analysis, and C-index were tested on the calibration plot. The bootstrapping methodology was used to internally validate the accuracy of the nomogram.

RESULTS

The LASSO algorithm identified the following eight predictive variables from the 16 independent variables: disease duration, body mass index (BMI), fasting blood glucose (FPG), glycated hemoglobin (HbA1c), homeostatic model assessment-insulin resistance (HOMA-IR), triglyceride (TG), total cholesterol (TC), and vitamin D (VitD)-T3. The C-index was 0.848 (95% CI: 0.798-0.898), indicating the accuracy of the model. In the interval validation, high scores (0.816) are possible from an analysis of a DR nomogram's decision curve to predict DR.

CONCLUSION

We developed a non-parametric technique to predict the risk of DR based on disease duration, BMI, FPG, HbA1c, HOMA-IR, TG, TC, and VitD.