Diabetic Polyneuropathy Early in Type 2 Diabetes Is Associated With Higher Incidence Rate of Cardiovascular Disease: Results From Two Danish Cohort Studies

Diabetic peripheral neuropathy detection of type 2 diabetes using machine learning from TCM features: a cross-sectional study

AIMS

Diabetic peripheral neuropathy (DPN) is the most common complication of diabetes mellitus. Early identification of individuals at high risk of DPN is essential for successful early intervention. Traditional Chinese medicine (TCM) tongue diagnosis, one of the four diagnostic methods, lacks specific algorithms for TCM symptoms and tongue features. This study aims to develop machine learning (ML) models based on TCM to predict the risk of diabetic peripheral neuropathy (DPN) in patients with type 2 diabetes mellitus (T2DM).

METHODS

A total of 4723 patients were included in the analysis (4430 with T2DM and 293 with DPN). TFDA-1 was used to obtain tongue images during a questionnaire survey. LASSO (least absolute shrinkage and selection operator) logistic regression model with fivefold cross-validation was used to select imaging features, which were then screened using best subset selection. The synthetic minority oversampling technique (SMOTE) algorithm was applied to address the class imbalance and eliminate possible bias. The area under the receiver operating characteristic curve (AUC) was used to evaluate the model's performance. Four ML algorithms, namely logistic regression (LR), random forest (RF), support vector classifier (SVC), and light gradient boosting machine (LGBM), were used to build predictive models for DPN. The importance of covariates in DPN was ranked using classifiers with better performance.

RESULTS

The RF model performed the best, with an accuracy of 0.767, precision of 0.718, recall of 0.874, F-1 score of 0.789, and AUC of 0.77. With a value of 0.879, the LGBM model appeared to be the best regarding recall Age, sweating, dark red tongue, insomnia, and smoking were the five most significant RF features. Age, yellow coating, loose teeth, smoking, and insomnia were the five most significant features of the LGBM model.

CONCLUSIONS

This cross-sectional study demonstrates that the RF and LGBM models can screen for high-risk DPN in T2DM patients using TCM symptoms and tongue features. The identified key TCM-related features, such as age, tongue coating, and other symptoms, may be advantageous in developing preventative measures for T2DM patients.

Effect of the glucagon-like peptide-1 receptor agonists on diabetic peripheral neuropathy: A meta-analysis

Previous researches found that glucagon-like peptide 1 receptor agonists (GLP-1RA) offer benefits beyond their anti-diabetic properties, including weight loss and cardiovascular disease prevention. However, the effects of GLP-1RA on diabetic peripheral neuropathy (DPN) remain unclear. This meta-analysis aims to assess the potential benefits of GLP-1RA treatment in DPN patients by evaluating peripheral neural function. Following the Cochrane Collaboration and Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we conducted a meta-analysis of the clinical trials investigating the impact of GLP-1RA treatment on peripheral neural function in patients with DPN. Outcomes were measured using electrophysiological tests, including nerve conduction velocity (NCV) and action potential amplitude. Our meta-analysis included six studies with 271 participants. Following GLP-1RA treatment, NCV significantly improved compared to the control group (MD 1.74; 95% CI 1.16 to 2.33; p < 0.001) and before treatment (MD 2.16; 95% CI 1.04 to 3.27; p < 0.001). Despite the improvement in NCV, blood glucose levels did not change significantly (MD -0.20 95% CI -0.87 to 0.46, p = 0.55) indicating that GLP-1RA enhances NCV through mechanisms other than glucose lowering. Nonetheless, as a result of the limited population studied, further research is needed to strengthen the reliability of these findings.

Unravelling the cardio-renal-metabolic-foot connection in people with diabetes-related foot ulceration: a narrative review

Diabetes-related foot ulceration (DFU), a serious but preventable complication of diabetes, is a leading cause of hospitalisation, lower extremity amputation and disability worldwide. People with DFU have a greater burden of cardiovascular risk factors, heart failure and chronic kidney disease, resulting in over two-fold higher risk of cardiovascular death compared with people with diabetes without DFU. Here, we propose a "cardio-renal-metabolic-foot" connection in people with diabetes based on shared pathophysiological mechanisms linking DFU with cardiovascular and renal disease. Whilst these mechanistic links remain to be fully elucidated, systemic inflammation and infection in the context of DFU are postulated as key mediators in the development, and progression of, cardiovascular and renal disease. However, cardiovascular and renal disease are also implicated in the pathogenesis of DFU, highlighting the multi-directional interplay between conditions. The impact of screening, prevention, and early management of cardiovascular complications associated with DFU requires further research. Multi-modality cardiac imaging could play a role in unravelling disease mechanisms leading to novel therapeutic strategies, as well as facilitating personalised risk assessment and management. Recent clinical trials have transformed the therapeutic landscape for people with type 2 diabetes, by demonstrating that sodium glucose co-transporter 2 inhibitors, glucagon-like peptide-1 agonists and non-steroidal mineralocorticoid receptor antagonists improve cardiovascular and renal outcomes. Although dedicated research in people with DFU is warranted, these therapies could target multiple facets of the "cardio-renal-metabolic-foot" connection. The holistic, person-centred approach to managing DFU should incorporate new multidisciplinary models of care focusing on the prevention and management of cardiovascular and kidney disease.

The Danish Centre for Strategic Research in Type 2 Diabetes (DD2) Project Cohort and Biobank from 2010 Through 2023-A Cohort Profile Update

Purpose

This paper provides an overview of the Danish Centre for Strategic Research in Type 2 Diabetes (DD2) cohort and biobank, including baseline characteristics of participants enrolled up to 2023, and post-enrollment rates of cardiovascular disease outcomes and mortality.

Methods

Since 2010, the DD2 project has enrolled individuals with type 2 diabetes mellitus (T2DM) recently diagnosed by general practitioners and by hospital-based clinicians across Denmark. Data from questionnaires, clinical examinations, and biological samples are collected at enrollment. Additional baseline and longitudinal follow-up data are accessed via linkage to health registries.

Results

Between 2010 and 2023, the DD2 project enrolled 11,369 participants (41.3% women, median age 61.4 years). Median T2DM duration at enrollment was 1.3 years, and median BMI was 31.6 kg/m2 for women and 30.5 kg/m2 for men. 18.3% were smokers, 5.7% consumed more than 14/21 units of alcohol weekly (women/men), and 17.9% reported leisure-time physical inactivity. Original midwife records dating back >80 years revealed that 20.2% of cohort participants had birth weights <3000 g. Based on complete hospital contact history 10 years before enrollment, 20.7% of cohort participants had macrovascular complications, 17.0% had microvascular complications, and 21.7% had kidney disease based on eGFR or urine albumin-creatinine measurements. At enrollment, statins were used by 68.2%, antihypertensive drugs by 69.9%, and glucose-lowering drugs by 86.5% of individuals. Median HbA1c was 48 mmol/mol and median LDL cholesterol 2.2 mmol/L. Genome-wide genotyping and biomarker data have been analyzed for over 9000 individuals. During the current follow-up time from the enrollment date (median 7.9 years), incident cardiovascular disease rate has been 13.8 per 1000 person-years and the mortality rate has been 17.6 per 1000 person-years.

Conclusion

The DD2 cohort, with its detailed information and long-term follow up, can improve our understanding of the progression and prevention of complications among individuals with newly diagnosed T2DM.

Risk Factors for Subclinical Diabetic Peripheral Neuropathy in Type 2 Diabetes Mellitus

Purpose

To investigate the risk factors associated with subclinical diabetic peripheral neuropathy (sDPN) in patients with type 2 diabetes mellitus (T2DM).

Patients and Methods

This cross-sectional, retrospective study involved 311 patients with T2DM who were successively admitted from January 2018 to December 2021 without any neurological symptoms. All participants underwent a nerve conduction study (NCS), and those asymptomatic patients with abnormal nerve conduction were diagnosed with sDPN. Differences between groups were evaluated by the chi-squared, Wilcoxon, or Fisher's exact test. Binary logistic regression analysis was performed to determine the independent risk factors for sDPN. Receiver operating characteristic (ROC) curves were constructed, and the areas under curves (AUCs) were detected.

Results

Among 311 asymptomatic patients with T2DM, 142 (45.7%) with abnormal nerve conduction were diagnosed with sDPN. Patients with sDPN significantly differed from those without diabetic peripheral neuropathy (DPN) in age, history of hypertension, duration of diabetes, anemia, neutrophil-to-lymphocyte ratio, fasting C-peptide level, serum creatinine level, and albuminuria (all p<0.05). Furthermore, the duration of diabetes (odds ratio [OR]: 1.062, 95% confidence interval [CI]: 1.016-1.110), fasting C-peptide level (OR: 2.427, 95% CI: 1.126-5.231), and presence of albuminuria (OR: 2.481, 95% CI: 1.406-4.380) were independently associated with the development of sDPN (all p<0.05). The AUCs for fasting C-peptide level, duration of diabetes, and the two factors combined were 0.6229 (95% CI: 0.5603-0.6855, p=0.0002), 0.6738 (95% CI: 0.6142-0.7333, p<0.0001), and 0.6808 (95% CI: 0.6212-0.7404, p<0.0001), respectively.

Conclusion

For patients with T2DM and longer duration of diabetes, lower fasting C-peptide levels, and presence with albuminuria, the risk for developing DPN is higher even if they have no clinical signs or symptoms. Identifying potential risk factors for the development of sDPN and effectively controlling them early are critical for the successful management of DPN.

Advances in cardiovascular-related biomarkers to predict diabetic peripheral neuropathy

Diabetic peripheral neuropathy (DPN) is a common chronic complication of diabetes mellitus. One of the most common types is distal symmetric poly-neuropathy, which begins as bilateral symmetry pain and hyperesthesia and gradually progresses into hypoesthesia with nerve fibre disorder and is frequently accompanied by depression and anxiety. Notably, more than half of patients with DPN can be asymptomatic, which tends to delay early detection. Furthermore, the study of adverse outcomes showed that DPN is a prominent risk factor for foot ulceration, gangrene and nontraumatic amputation, which decreases quality of life. Thus, it is essential to develop convenient diagnostic biomarkers with high sensitivity for screening and early intervention. It has been reported that there may be common pathways for microvascular and macrovascular complications of diabetes. The pathogenesis of both disorders involves vascular endothelial dys-function. Emerging evidence indicates that traditional and novel cardiovascular-related biomarkers have the potential to characterize patients by subclinical disease status and improve risk prediction. Additionally, beyond traditional cardiovascular-related biomarkers, novel cardiovascular-related biomarkers have been linked to diabetes and its complications. In this review, we evaluate the association between major traditional and nontraditional car-diovascular-related biomarkers of DPN, such as cardiac troponin T, B-type natriuretic peptide, C-reactive protein, myeloperoxidase, and homocysteine, and assess the evidence for early risk factor-based management strategies to reduce the incidence and slow the progression of DPN.

Morbidity and mortality of patients with diabetic neuropathy treated with pathogenetically oriented alpha-lipoic acid versus symptomatic pharmacotherapies - a nationwide database analysis from Hungary

AIMS

Diabetic neuropathy is associated with increased risk of morbidity and all-cause mortality. It is unclear whether these outcomes differ in patients with diabetic neuropathy treated with pathogenetically oriented vs symptomatic pharmacotherapies.

METHODS

We performed a retrospective (2009-2019) database analysis of patients treated with pathogenetically oriented alpha-lipoic acid (ALA) or symptomatic pharmacotherapies for diabetic neuropathy. We investigated clinical outcomes in propensity score matched patients in Hungary. Changes in hazard ratios and annualized event rates were assessed and sensitivity analyses performed.

RESULTS

Hazard ratios favored treatment with ALA vs symptomatic pharmacotherapies regarding acute myocardial infarction (HR 0.73, 95%CI: 0.60-0.89, p = 0.0016), stroke (HR 0.71, 95%CI: 0.62-0.82, p<0.0001), hospitalization for heart failure (HR 0.72, 95%CI: 0.66-0.78, p<0.0001), cancer events (HR 0.83, 95% CI: 0.76-0.92, p = 0.0002) and all-cause mortality (HR 0.55, 95% CI: 0.49-0.61, p<0.0001), but not for lower limb amputation (HR 1.05, 95%CI: 0.89-1.25, p = 0.5455). This association was supported by results of evaluating annual event rates and sensitivity analyses.

CONCLUSIONS

This retrospective database analysis revealed a lower occurrence of cardio- and cerebrovascular morbidity, cancer events and all-cause mortality in patients with diabetic neuropathy treated with pathogenetically oriented ALA vs symptomatic pharmacotherapies. This hypothesis-generating result requires further investigations.

Diabetic peripheral neuropathy is associated with diabetic kidney disease and cardiovascular disease – The Silesia Diabetes-Heart Project

Microvascular complications of diabetes seem to be clustered and put patients at higher risk of developing cardiovascular disease (CVD). This was a questionnaire-based study designed to screen for the presence of diabetic peripheral neuropathy (DPN), defined as the score in the Michigan Neuropathy Screening Instrument (MNSI) above 2, and to evaluate its association with other complication of diabetes, including CVD. There were 184 patients included into the study. The prevalence of DPN in the study group was 37.5%. The regression model analysis revealed that the presence of DPN was significantly associated with the presence of diabetic kidney disease (DKD) (P = 0.0034;) and patient's age (P < 0.0001). Thirty-four patients (49.3%) with MNSI score >2 were diagnosed with CVD in comparison to 24 (20.1%) subjects with MNSI score ≤ 2 (P = 0.00006). In case of having one diabetes complication diagnosed, it is important to screen for others, including macrovascular ones.

The association between distal symmetric polyneuropathy in diabetes with all-cause mortality - a meta-analysis

BACKGROUND

Distal symmetric polyneuropathy (DSPN) is a common microvascular complication of both type 1 and 2 diabetes with substantial morbidity burden and reduced quality of life. Its association with mortality is equivocal.

PURPOSE

To describe the association between DSPN and all-cause mortality in people with diabetes and further stratify by the type of diabetes based on a meta-analysis of published observational studies.

DATA SOURCES

We searched Medline from inception to May 2021.

STUDY SELECTION

Original data were collected from case-control and cohort studies that reported on diabetes and DSPN status at baseline and all-cause mortality during follow-up.

DATA EXTRACTION

was completed by diabetes specialists with clinical experience in neuropathy assessment.

DATA SYNTHESIS

Data was synthesized using random-effects meta-analysis. The difference between type 1 and 2 diabetes was investigated using meta-regression.

RESULTS

A total of 31 cohorts (n=155,934 participants, median 27.4% with DSPN at baseline, all-cause mortality 12.3%) were included. Diabetes patients with DSPN had an almost twofold mortality (HR: 1.96, 95%CI: 1.68-2.27, I2 = 91.7%), I^{2 =} 91.7%) compared to those without DSPN that was partly explained by baseline risk factors (adjusted HR: 1.60, 95%CI: 1.37-1.87, I^{2 =} 78.86%). The association was stronger in type 1 compared to type 2 diabetes (HR: 2.22, 95%CI: 1.43-3.45). Findings were robust in sensitivity analyses without significant publication bias.

LIMITATIONS

Not all papers reported multiple adjusted estimates. The definition of DSPN was heterogeneous.

CONCLUSIONS

DSPN is associated with an almost twofold risk of death. If this association is causal, targeted therapy for DSPN could improve life expectancy of diabetic patients.

Scores of peripheral neuropathic pain predicting long-term mortality in patients with type 2 diabetes: A retrospective cohort study

OBJECTIVES

Diabetic peripheral neuropathic pain (DPNP) is a prevalent chronic complication in patients with diabetes. Using a questionnaire is helpful for DPNP screening in outpatients. In this retrospective cohort, we aimed to examine whether DPNP diagnosed based on scoring questionnaires could predict long-term mortality in outpatients with type 2 diabetes.

METHODS

We enrolled 2318 patients who had joined the diabetes pay-for-performance program and completed the annual assessments, including both the identification pain questionnaire (ID pain) and Douleur Neuropathique en 4 questionnaire (DN4), between January 2013 and October 2013. Information on registered deaths was collected up to August 2019.

RESULTS

There was high consistency in the scores between the ID pain and DN4 (r = 0.935, P < 0.001). During the median follow-up of 6.2 years (interquartile range: 5.9-6.4 years), 312 patients deceased. Patients with an ID pain score of ≥ 2 had a higher mortality risk than those with a score of < 2 (hazard ratio [HR] = 1.394, 95%CI: 1.090-1.782), and patients with a DN4 score of ≥ 4 had a higher mortality risk than those with a score of < 4 (HR = 1.668, 95% confidence interval [CI]: 1.211-2.297). Patients consistently diagnosed with DPNP by the ID pain and DN4 had a significantly higher mortality risk (HR = 1.713, 95% CI: 1.223-2.398, P = 0.002), but not those discrepantly diagnosed with DPNP (P = 0.107), as compared with those without DPNP.

CONCLUSIONS

Both the ID pain and DN4 for DPNP screening were predictive of long-term mortality in patients with type 2 diabetes. However, a discrepancy in the diagnosis of DPNP weakened the power of mortality prediction.