Risk Factors for Diabetic Peripheral Neuropathy, Peripheral Artery Disease, and Foot Deformity Among the Population With Diabetes in Beijing, China: A Multicenter, Cross-Sectional Study

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.

The global and regional burden of diabetic peripheral neuropathy

Diabetic peripheral neuropathy (DPN) is length-dependent peripheral nerve damage arising as a complication of type 1 or type 2 diabetes in up to 50% of patients. DPN poses a substantial burden on patients, who can experience impaired gait and loss of balance, predisposing them to falls and fractures, and neuropathic pain, which is frequently difficult to treat and reduces quality of life. Advanced DPN can lead to diabetic foot ulcers and non-healing wounds that often necessitate lower-limb amputation. From a socioeconomic perspective, DPN increases both direct health-care costs and indirect costs from loss of productivity owing to neuropathy-related disability. In this Review, we highlight the importance of understanding country-specific and region-specific variations in DPN prevalence to inform public health policy and allocate resources appropriately. We also explore how identification of DPN risk factors can guide treatment and prevention strategies and aid the development of health-care infrastructure for populations at risk. We review evidence that metabolic factors beyond hyperglycaemia contribute to DPN development, necessitating a shift from pure glycaemic control to multi-targeted metabolic control, including weight loss and improvements in lipid profiles.

A Review of Peripheral Artery Disease in Diabetic Patients in Sub-Saharan Africa

Peripheral artery disease (PAD) is an atherosclerotic occlusive disease of the lower extremities and is associated with an increased risk of amputation and cardiovascular events. The interplay between diabetes and PAD is complex, influenced by shared risk factors such as hypertension, dyslipidemia, and smoking. High rates of undiagnosed diabetes, coupled with barriers to accessing care, contribute to the complexity of managing PAD. Unique to the Sub-Sahara region is associations with communicable diseases such as human immunodeficiency virus and tuberculosis which further complicates the epidemiological landscape. Comprehensive management strategies, including lifestyle modifications, pharmacological interventions, and revascularization procedures, are essential. However, the region faces challenges such as inadequate healthcare infrastructure and high costs of treatment. This narrative review highlights the epidemiology of PAD in people with diabetes, the risk factors associated with PAD, the impact of PAD on the morbidity and mortality of individuals with diabetes, as well as the management of PAD in individuals with diabetes, with attention geared toward Sub-Saharan Africa These insights are critical for developing effective strategies to mitigate the burden of PAD in diabetes, especially in Sub-Saharan Africa. Further research is essential to understand the associations between diabetes and other diseases in the region.

Global hotspots and trends in diabetic peripheral neuropathy research from 2011 to 2023

Diabetic peripheral neuropathy (DPN) is a prevalent disease, and the relevant literature has been increasingly investigated over the past years. Consequently, it is imperative to conduct a scientific and comprehensive DPN research field bibliometric analysis. This study aims to summarize and visualize the literature distribution laws, the research hotspots, and the development trends in DPN using bibliometric methods. We searched all relevant documents published from 2011 to 2023 in the Web of Science Core Collection. Bibliometric analysis and network visualization were performed using VOSviewer, R-bibliometrix, and CiteSpace tools, focusing on countries, institutions, authors, journals, highly cited papers, references, and keywords. This study included a total of 2708 documents. The annual number of publications in the field has notably increased. China, the USA, and the UK take on critical significance in DPN research. The University of Manchester in the UK has the highest number of publications (109). Malik has the most publications (86). Tesfaye literature has been most frequently cited by scholars of DPN research. The Journal of Diabetes and its Complications and Frontiers in Endocrinology have the most publications (45 each). Diabetes Care stands out with the highest impact factor (16.200), number of citations (2516), and H-index (27) among the number of publications top 10 journals. The paper "Colloca, L. et al Neuropathic pain. Nature Reviews Disease Primers. 2017, 3 (1):1-19" has the highest number of citations (1224 times). The most critical co-cited reference is "Tesfaye S, 2010, DIABETES CARE, V33, P2285" (cited 408 times). Keywords like "type 2 diabetes," "diagnosis," "association," "retinopathy," "risk factors," "progression," "corneal confocal microscopy," "nephropathy," "balance," "microvascular complications," "inflammation," "disease," and "insulin resistance" represent the recent research hotspots. The development, research hotspots, and future trends of the global DPN domain from 2011 to 2023 were summarized and visualized in this study. This study can present more insights into the general situation of DPN research and provide a useful reference for clinical decision-making and directions of subsequent research.

Muscle Network Connectivity Study in Diabetic Peripheral Neuropathy Patients

Diabetic peripheral neuropathy (DPN) is a prevalent complication of chronic diabetes mellitus and has a significant impact on quality of life. DPN typically manifests itself as a symmetrical, length-dependent sensorimotor polyneuropathy with severe effects on gait. Surface electromyography (sEMG) is a valuable low-cost tool for assessing muscle activation patterns and precise identification of abnormalities. For the present study, we used information theory methods, such as cross-correlation (CC), normalized mutual information (NMI), conditional granger causality (CG-Causality), and transfer entropy (TE), to evaluate muscle network connectivity in three population groups: 33 controls (healthy volunteers, CT), 10 diabetic patients with a low risk of DPN (LW), and 17 moderate/high risk patients (MH). The results obtained indicated significant alterations in the intermuscular coupling mechanisms due to diabetes and DPN, with the TE group showing the best performance in detecting differences. The data revealed a significant increase in information transfer and muscle connectivity in the LW group over the CT group, while the MH group obtained significantly lower values for these metrics than the other two groups. These findings highlight the sEMG coupling metrics' potential to reveal neuromuscular mechanisms that could aid the development of targeted rehabilitation strategies and help monitor DPN patients.

Role of Decreased Expression of miR-155 and miR-146a in Peripheral Blood of Type 2 Diabetes Mellitus Patients with Diabetic Peripheral Neuropathy

Objective

To Study the Correlations of microRNA-155 (miR-155) and microRNA-146a (miR-146a) Expression in Peripheral Blood of Type 2 Diabetes Mellitus (T2DM) Patients with Diabetic Peripheral Neuropathy (DPN), and Explore the Clinical Value of miR-155 and miR-146a in the Diagnosis and Treatment Outcomes of DPN.

Methods

The study included 51 T2DM patients without DPN (T2DM group), 49 T2DM patients with DPN (DPN group), and 50 normal controls (NC group). Quantitative real-time PCR was utilized to determine the expression levels of miR-155 and miR-146a. Clinical features and risk factors for DPN were assessed. Multivariate stepwise logistic regression analysis was conducted to confirm whether the expressions of miR-155 and miR-146a could independently predict the risk of DPN. ROC curve analysis evaluated their diagnostic value.

Results

The T2DM group exhibited significantly lower expression levels of miR-155 and miR-146a compared to the NC group (P < 0.05). Moreover, the DPN group exhibited a significantly decreased expression level of miR-155 and miR-146a compared to the T2DM group (P < 0.01). Multivariate logistic regression analysis indicated that higher levels of miR-155 and miR-146a might serve as protective factors against DPN development. ROC curve analysis revealed that miR-155 (sensitivity 91.8%, specificity 37.3%, AUC 0.641,) and miR-146a (sensitivity 57.1%, specificity 84.3%, AUC 0.722) possess a strong ability to discriminate between T2DM and DPN. Their combined use further enhanced the diagnostic potential of DPN (sensitivity 83.7%, specificity 60.8%, AUC 0.775). A multi-index combination can improve DPN diagnostic efficiency.

Conclusion

The decreased expression of miR-155 and miR-146a in the peripheral blood of T2DM patients is closely related to the occurrence of DPN, highlighting their potential as valuable biomarkers for diagnosing and prognosticating DPN.

Interpretable machine learning models for detecting peripheral neuropathy and lower extremity arterial disease in diabetics: an analysis of critical shared and unique risk factors

BACKGROUND

Diabetic peripheral neuropathy (DPN) and lower extremity arterial disease (LEAD) are significant contributors to diabetic foot ulcers (DFUs), which severely affect patients' quality of life. This study aimed to develop machine learning (ML) predictive models for DPN and LEAD and to identify both shared and distinct risk factors.

METHODS

This retrospective study included 479 diabetic inpatients, of whom 215 were diagnosed with DPN and 69 with LEAD. Clinical data and laboratory results were collected for each patient. Feature selection was performed using three methods: mutual information (MI), random forest recursive feature elimination (RF-RFE), and the Boruta algorithm to identify the most important features. Predictive models were developed using logistic regression (LR), random forest (RF), and eXtreme Gradient Boosting (XGBoost), with particle swarm optimization (PSO) used to optimize their hyperparameters. The SHapley Additive exPlanation (SHAP) method was applied to determine the importance of risk factors in the top-performing models.

RESULTS

For diagnosing DPN, the XGBoost model was most effective, achieving a recall of 83.7%, specificity of 86.8%, accuracy of 85.4%, and an F1 score of 83.7%. On the other hand, the RF model excelled in diagnosing LEAD, with a recall of 85.7%, specificity of 92.9%, accuracy of 91.9%, and an F1 score of 82.8%. SHAP analysis revealed top five critical risk factors shared by DPN and LEAD, including increased urinary albumin-to-creatinine ratio (UACR), glycosylated hemoglobin (HbA1c), serum creatinine (Scr), older age, and carotid stenosis. Additionally, distinct risk factors were pinpointed: decreased serum albumin and lower lymphocyte count were linked to DPN, while elevated neutrophil-to-lymphocyte ratio (NLR) and higher D-dimer levels were associated with LEAD.

CONCLUSIONS

This study demonstrated the effectiveness of ML models in predicting DPN and LEAD in diabetic patients and identified significant risk factors. Focusing on shared risk factors may greatly reduce the prevalence of both conditions, thereby mitigating the risk of developing DFUs.

Glucagon-like peptide-1 receptor agonists for the management of diabetic peripheral neuropathy

Diabetes mellitus is a prevalent chronic disease characterized by hyperglycemia. Diabetic peripheral neuropathy (DPN) is one of the complications of diabetes mellitus and is caused by neuron injury induced by hyperglycemic circumstances. The incidence of DPN varies among different countries and regions, ranging from nearly 20% to over 70%. Patients with DPN may encounter symmetric pain or discomfort of the extremes, leading to reduced quality of life and even amputation. The pharmacological management for painful DPN mainly includes antidepressants due to their analgesic effects. Nevertheless, effective therapies to impact the pathogenesis and progression of DPN are lacking. Glucagon-like peptide-1 receptor (GLP-1R) agonists show efficacy in controlling blood glucose and serve as a treatment modality for diabetes mellitus. In recent years, evidence has been proposed that GLP-1R agonists exert neuroprotective effects through modulating inflammation, oxidative stress, and mitochondrial dysfunction. On the other hand, clinical evidence on the potential of GLP-1R agonists for treating DPN is still controversial and limited. This narrative review summarizes the preclinical and clinical studies investigating the capacity of GLP-1R agonists as therapeutic agents for DPN.

Association of HbA1c Variability with Vibrating Perception Threshold in Middle-Aged and Elderly Patients with Type 2 Diabetes Mellitus: A Retrospective Cohort Study

Purpose

To investigate the relationship between HbA1c variability and vibrating perception threshold (VPT) in middle-aged and elderly patients with type 2 diabetes mellitus (T2DM).

Patients and Methods

A total of 367 middle-aged and elderly patients with T2DM were enrolled. All patients were categorized into the control and vibration sensation deficiency group (VSD) based on VPT. Clinical data were collected. The coefficient of variation of glycated hemoglobin A1c (HbA1c-CV) and the mean glycated hemoglobin A1c(HbA1c-Mean) are considered as indexes of HbA1c variability. Multivariate logistic regression analysis, the generalized linear model and ROC curve correlation analysis were used to analyze the correlation of various factors and VPT.

Results

The multivariate logistic regression analysis revealed that age, systolic blood pressure (SBP), and HbA1c-CV were identified as risk factors for vibration sensation deficiency in middle-aged and elderly patients with T2DM, while estimated glomerular filtration rate (eGFR), triiodothyronine (T3), and alanine aminotransferase (ALT) were considered as protective factors. In the unadjusted generalized linear model, a significant association was observed between HbA1c-CV and VPT values. After adjusting for age, diabetic duration, SBP, homeostatic model assessment for beta-cell function (HOMA-β), ALT, eGFR, T3, 24-hour urinary protein excretion levels, and HbA1c-Mean, HbA1c-CV remained significantly correlated with VPT values on both sides. (left side, B=2.560, 95% CI 1.298~3.823; P<0.001; right side, B=2.608, 95% CI 1.498~3.718, P<0.001). The area under the curve (AUC) for HbA1c-CV and VSD prevalence was 0.723, with a sensitivity of 79.85%, specificity of 56.22%.

Conclusion

The risk of developing VSD increases proportionally with higher HbA1c-CV levels in middle-aged and elderly patients with T2DM. Reaching and maintaining blood glucose stability is essential to the mitigation of diabetes peripheral neuropathy occurrence.

Diabetes-Related Microvascular Complications in Primary Health Care Settings in the West Bank, Palestine

BACKGROUND

Worldwide, retinopathy, nephropathy, and neuropathy are the major diabetes-related microvascular complications. In Palestine, a low-middle-income country, diabetes is the fourth reason for death. However, a few studies examined diabetes microvascular consequences and its management. Therefore, we carried out a national study that aims to investigate the factors associated with diabetes-related microvascular complications among individuals seeking care in primary healthcare settings of the West Bank of Palestine.

METHOD

Using a cluster systematic sampling technique, 882 participants with diabetes patients were chosen for a cross-sectional study from primary healthcare facilities operated by the Ministry of Health (PMoH), the United Nations Relief and Works Agency (UNRWA), and the Palestinian Medical Relief Society (PMRS). Data about patients related to diabetes-related complications, medication use, and other diseases were extracted from patients' medical records. In addition, an interview face-to-face questionnaire was used to collect information about patients' sociodemographic variables, medical history, smoking habits, duration of the disease, presence of concurrent conditions previous referrals, and hospital admissions, as well as their level of knowledge regarding diabetes, complications, and treatments.

RESULTS

Approximately 34.4% of persons with diabetes patients in Palestine encounter at least one microvascular complication associated with diabetes. The most prevalent diabetes-related microvascular complication was retinopathy (17.3%), 23.4% of participants had more than one microvascular complication, and 29% of male patients had erectile dysfunction. A higher probability of having any microvascular complications was associated with older age (over 60 years). Participants with diabetes patients with fundoscopy or ophthalmology reports, according to diabetes follow-up guidelines, were less likely to develop retinopathy. Also, those who performed regular kidney function testing were less likely to have nephropathy, and those who performed a regular foot exam were less likely to develop diabetic foot.

CONCLUSIONS

Diabetes-related microvascular complications were associated with patient age, low education level, residency location, and adherence to diabetes follow-up guidelines of diabetes management; i.e., having been tested for HbA1c, consulting with specialists, regular kidney function, and foot examination. These factors can be utilized in setting up proper management protocols to prevent or delay microvascular complications in many patients.

How does diabetic peripheral neuropathy impact patients' burden of illness and the economy? A retrospective study in Beijing, China

Objective

Diabetic peripheral neuropathy (DPN) causes significant illness in patients and has a negative impact on the economy. The objective of this study is to evaluate the cost and quantity of anti-diabetic drugs needed by patients with or without DPN, as well as their variation trends in Beijing between 2016 and 2018.

Methods

This observational cross-sectional study used data on diabetic patients with outpatient medication records obtained from Beijing Medical Insurance from 2016 to 2018. The medications, comorbidities, diabetes-related complications, treatment strategies, and costs of drug treatment were compared between DPN patients and non-DPN patients.

Results

Of the 28,53,036 diabetic patients included in the study, 3,75,216 (13.15%) had DPN and 1,87,710 (50.03%) of the DPN patients were women. Compared with non-DPN patients, DPN patients used more mediations (4.7 ± 2.47 vs. 3.77 ± 2.32, p < 0.0001, in 2018) to treat related complications and comorbidities (2.03 ± 1.2 vs. 1.71 ± 1.05; 2.68 ± 1.93 vs. 2.06 ± 1.86, p < 0.0001, respectively, in 2018). The total annual costs of drug treatment were higher in DPN patients than in non-DPN patients (¥12583.25 ± 10671.48 vs. ¥9810.91 ± 9234.14, p < 0.0001, in 2018). The usage of DDP4i increased from 2.55 to 6.63% in non-DPN patients and from 4.45 to 10.09% in DPN patients from 2017 to 2018.

Conclusions

The number of comorbidities, diabetic complications, medications, and annual drug treatment costs were greater in DPN patients than in non-DPN patients.

Immunological profile of diabetic foot ulcers: update review

The most frequent consequence of diabetes mellitus, diabetic foot ulcers frequently do not heal and necessitate lower limb amputation. According to estimates, DFU accounts for 50% to 70% of all lower limb amputations, and 50% of patients with DFU have peripheral artery disease (PAD), which is occasionally brought on by atherosclerosis. Deformity of foot, peripheral artery disease (PAD), loss protective sensation (LOPS), and a history of foot ulcers. Global prevalence for DFUs varies by region. One of the frequent complications of diabetes in poor nations, such as Iraq, is diabetic foot; approximately two-thirds of the patients with diabetes have Diabetic Foot disorder (DFD) in Iraq and this health issue had significant negative social and economic effects. The Saudi Arabia and Bahrain have the highest prevalence rates of DFU; the reported yearly incidence of diabetic foot ulcers ranges from "2.1% to 7.4%". There are three types of diabetic foot ulcers: neuropathic, neuroischaemic, and ischemic. An infected DFU often contains three to five different types of bacteria, including gram-positive aerobes, such as "Staphylococcus sp.", gram-positive anaerobes, gram negative aerobes, gram negative anaerobes, and fungi (Candida spp.). Numerous studies have demonstrated that effective management of DFU can significantly decrease, postpone, or even completely avoid consequences like infection, gangrene, amputation, and death.

Mechanism underlying linezolid-induced peripheral neuropathy in multidrug-resistant tuberculosis

Multidrug-resistant tuberculosis (MDR-TB) remains a main global health concern as there is no comprehensive therapeutic intervention yet and numerous adverse effects follow the therapeutic process. In recent years, linezolid has been frequently used for treating MDR-TB. However, peripheral neuropathy associated with linezolid has reduced patient compliance. The current study explored the mechanism underlying linezolid-induced peripheral neuropathy in MDR-TB. Autophagy plays a neuroprotective role against peripheral nerve injury. We hypothesized that autophagy might also play a neuroprotective role against linezolid-induced peripheral neuropathy. In this study, we collected 12 questionnaires from MDR-TB patients in our hospital, and 10 of them developed linezolid-induced pain. The pain is mainly concentrated in the feet and accompanied by numbness. Subsequently, we used Sprague-Dawley (SD) rats and Schwann cells (SCs) to explore the mechanism. We found that linezolid causes a sparse arrangement of sciatic nerve tissue with associated loss of neurons, myelin sheaths, and down-regulation of LC3B expression. These results were also confirmed by in vitro experiments, showing that linezolid inhibited the proliferation of SCs. And the expression of P-AKT and P62 was elevated, and the expression of LC3B declined compared with the control group. Moreover, chloroquine (CQ), an autophagy inhibitor, also exhibited experimental results similar to linezolid. In summary, we conclude that linezolid-induced peripheral neuropathy is associated with the inhibition of autophagy flux.