Study on risk factors of diabetic peripheral neuropathy and establishment of a prediction model by machine learning

BACKGROUND

Diabetic peripheral neuropathy (DPN) is a common complication of diabetes. Predicting the risk of developing DPN is important for clinical decision-making and designing clinical trials.

METHODS

We retrospectively reviewed the data of 1278 patients with diabetes treated in two central hospitals from 2020 to 2022. The data included medical history, physical examination, and biochemical index test results. After feature selection and data balancing, the cohort was divided into training and internal validation datasets at a 7:3 ratio. Training was made in logistic regression, k-nearest neighbor, decision tree, naive bayes, random forest, and extreme gradient boosting (XGBoost) based on machine learning. The k-fold cross-validation was used for model assessment, and the accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve (AUC) were adopted to validate the models' discrimination and clinical practicality. The SHapley Additive exPlanation (SHAP) was used to interpret the best-performing model.

RESULTS

The XGBoost model outperformed other models, which had an accuracy of 0·746, precision of 0·765, recall of 0·711, F1-score of 0·736, and AUC of 0·813. The SHAP results indicated that age, disease duration, glycated hemoglobin, insulin resistance index, 24-h urine protein quantification, and urine protein concentration were risk factors for DPN, while the ratio between 2-h postprandial C-peptide and fasting C-peptide(C2/C0), total cholesterol, activated partial thromboplastin time, and creatinine were protective factors.

CONCLUSIONS

The machine learning approach helped established a DPN risk prediction model with good performance. The model identified the factors most closely related to DPN.

Evidence of antidiabetic activity of Spirulina fusiformis against streptozotocin-induced diabetic Wistar albino rats

The aim of our study is to investigate the protective effect of Spirulina fusiformis against streptozotocin-induced diabetes in Wistar albino rats. Rats were divided into five groups: group I was normal control, group II was diabetic control (50 mg/kg b.w. of streptozotocin, i.p.), group III was Spirulina fusiformis (400 mg/kg b.w., p.o.) treated diabetic rats; group IV was Glibenclamide (0. 6 mg/kg b.w., p.o.) treated diabetic rats and group V was treated with Spirulina fusiformis (400 mg/kg b.w., p.o.) alone. There was significant elevation in the levels of blood glucose, serum lipid profile and serum renal markers (total protein, urea, creatinine and uric acid) in the diabetic rats. Also, diabetic rats showed significantly (P < 0.05) reduced antioxidant status (reduced levels of superoxide dismutase, catalase, glutathione peroxidase, glutathione-S-transferase and reduced glutathione; increased levels of TBARS), impaired oral glucose tolerance and elevated HbA1C. Spirulina fusiformis was able to normalize the above mentioned parameters. Significant histopathological changes were found in the pancreas, liver and kidney sections of the diabetic control group while treatment with Spirulina fusiformis was able to minimize the extent of tissue damage. Current study shows that Spirulina fusiformis possesses significant antidiabetic and antihyperlipidemic effects in streptozotocin-induced diabetic rats by effectively reducing the rise in blood glucose levels and lipid profile.

Common medications used by patients with type 2 diabetes mellitus: what are their effects on the lipid profile?

Dyslipidemia is the most fundamental risk factor for atherosclerotic cardiovascular disease (ASCVD). In clinical practice, many commonly prescribed medications can alter the patient's lipid profile and, potentially, the risk for ASCVD-either favorably or unfavorably. The dyslipidemia observed in type 2 diabetes mellitus (T2DM) can be characterized as both ominous and cryptic, in terms of unrecognized, disproportionately elevated atherogenic cholesterol particle concentrations, in spite of deceptively and relatively lower levels of low-density lipoprotein cholesterol (LDL-C). Several factors, most notably insulin resistance, associated with the unfavorable discordance of elevated triglyceride (TG) levels and low levels of high-density lipoprotein cholesterol (HDL-C), have been shown to correlate with an increased risk/number of ASCVD events in patients with T2DM. This review focuses on known changes in the routine lipid profile (LDL-C, TGs, and HDL-C) observed with commonly prescribed medications for patients with T2DM, including antihyperglycemic agents, antihypertensive agents, weight loss medications, antibiotics, analgesics, oral contraceptives, and hormone replacement therapies. Given that the risk of ASCVD is already elevated for patients with T2DM, the use of polypharmacy may warrant close observation of overall alterations through ongoing lipid-panel monitoring. Ultimately, the goal is to reduce levels of atherogenic cholesterol particles and thus the patient's absolute risk.

Cardiovascular effects of anti-diabetes drugs

INTRODUCTION

Cardiovascular disease remains the major contributor to morbidity and mortality in diabetes. From the need to reduce cardiovascular risk in diabetes and to ensure that such risk is not exacerbated by drug treatments, governmental regulators and drug manufacturers have focused on clinical trials evaluating cardiovascular outcomes.

AREAS COVERED

Findings from mechanistic and clinical trials of biguanides, sulfonylureas, thiazolidinediones, dipeptidyl peptidase-4 (DPP-4) inhibitors, glucagon-like peptide-1 (GLP-1) receptor agonists, and sodium-glucose co-transporter 2 (SGLT-2) inhibitors will be reviewed. These drug classes will be compared within the context of available cardiovascular outcomes data. Clinical implications of new study regulations will be examined.

EXPERT OPINION

Recent cardiovascular studies provide a more comprehensive evaluation of specific anti-diabetes therapy in individuals with high cardiovascular risk. Long-term effects of anti-hyperglycemic agents in patients with lower cardiovascular risk are still speculative. Historical data supports continued use of metformin as a first-line agent. DPP-4 inhibitors and GLP-1 receptor agonists appear to have neutral effects on cardiovascular outcomes. The significantly decreased cardiovascular risk associated with empagliflozin SGLT-2 inhibitor therapy is impressive and may change how practitioners prescribe add-on therapy to metformin.

The Association between Psoriasis Area and Severity Index and Cardiovascular Risk Factor in Korean Psoriasis Patients

Background

Psoriasis is associated with increased risk of cardiovascular morbidities, especially in severe cases. Severity of the disease has been known to be associated with higher prevalence of these risk factors. However, in the absence of robust measurements, studies to date relied mostly on treatment spectrum as a proxy for the severity.

Objective

To evaluate the relationship between psoriasis area and severity index (PASI) and cardiovascular risk factors in Korean patients.

Methods

Presence of diabetes mellitus (DM), hypertension, smoking history was surveyed through questionnaires and serum lipid profile analysis were done after fasting overnight. The severity of psoriasis was assessed using PASI scores: mild, <10; moderate to severe, ≥10. Cardiovascular risk factors such as smoking, hypertension, diabetes and dyslipidemia were compared between the mild group and moderate to severe group. The prevalence of diabetes and hypertension was compared among these two groups of psoriasis patients and the general population based control; age and gender were matched among three groups accordingly prior to analysis.

Results

A total of 256 patients with plaque type psoriasis were included. Between mild group and moderate to severe group, significant differences of cardiovascular risk factors including lipid profile were not discovered except in triglyceride level. Comparing to general population, prevalence of diabetes was found significantly higher in psoriasis patients while that of hypertension was similar.

Conclusion

Our results suggest that among cardiovascular risks, presence of DM and triglyceride level seem to be associated with the presence of psoriasis in Korean psoriasis patients, while other factors may not contribute meaningfully.

Harnessing publicly available genetic data to prioritize lipid modifying therapeutic targets for prevention of coronary heart disease based on dysglycemic risk

Therapeutic interventions that lower LDL-cholesterol effectively reduce the risk of coronary artery disease (CAD). However, statins, the most widely prescribed LDL-cholesterol lowering drugs, increase diabetes risk. We used genome-wide association study (GWAS) data in the public domain to investigate the relationship of LDL-C and diabetes and identify loci encoding potential drug targets for LDL-cholesterol modification without causing dysglycemia. We obtained summary-level GWAS data for LDL-C from GLGC, glycemic traits from MAGIC, diabetes from DIAGRAM and CAD from CARDIoGRAMplusC4D consortia. Mendelian randomization analyses identified a one standard deviation (SD) increase in LDL-C caused an increased risk of CAD (odds ratio [OR] 1.63 (95 % confidence interval [CI] 1.55, 1.71), which was not influenced by removing SNPs associated with diabetes. LDL-C/CAD-associated SNPs showed consistent effect directions (binomial P = 6.85 × 10⁻⁵). Conversely, a 1-SD increase in LDL-C was causally protective of diabetes (OR 0.86; 95 % CI 0.81, 0.91), however LDL-cholesterol/diabetes-associated SNPs did not show consistent effect directions (binomial P = 0.15). HMGCR, our positive control, associated with LDL-C, CAD and a glycemic composite (derived from GWAS meta-analysis of four glycemic traits and diabetes). In contrast, PCSK9, APOB, LPA, CETP, PLG, NPC1L1 and ALDH2 were identified as “druggable” loci that alter LDL-C and risk of CAD without displaying associations with dysglycemia. In conclusion, LDL-C increases the risk of CAD and the relationship is independent of any association of LDL-C with diabetes. Loci that encode targets of emerging LDL-C lowering drugs do not associate with dysglycemia, and this provides provisional evidence that new LDL-C lowering drugs (such as PCSK9 inhibitors) may not influence risk of diabetes.

Combination therapy with insulin glargine plus metformin but not insulin glargine plus sulfonylurea provides similar glycemic control to triple oral combination therapy in patients with type 2 diabetes uncontrolled with dual oral agent therapy

AIMS

Evaluate substituting insulin glargine (GLAR) for a thiazolidinedione (TZD) versus adding a third oral antidiabetes drug (OAD) in patients with uncontrolled type 2 diabetes mellitus (T2DM) on TZD+metformin or TZD+sulfonylurea.

METHODS

In this multicenter, open-label study, 337 T2DM patients with a glycated hemoglobin A1c (A1C) of 7.5-12.0% despite≥3months of treatment with a TZD plus metformin or a sulfonylurea were randomized to a third OAD (3OAD; metformin or glyburide) or GLAR+1 OAD (metformin or sulfonylurea) with TZD cessation, titrated to a fasting blood glucose≤94mg/dL.

RESULTS

Substitution of GLAR for a TZD led to an adjusted mean A1C change from baseline of-1.66% versus-1.86% in the 3OAD arm (adjusted mean difference 0.20 [95% confidence interval, - 0.11, 0.51], not meeting the noninferiority criteria). This difference was driven by the GLAR+sulfonylurea stratum. GLAR+metformin was as effective as 3OAD in achieving glycemic control but with greater improvements in lipid parameters, less weight gain, and lower hypoglycemia rates.

CONCLUSIONS

These findings favor substitution of GLAR for a TZD in T2DM patients not controlled on TZD+metformin. GLAR+sulfonylurea was less effective at lowering A1C than 3OAD and not associated with the benefits observed with GLAR+metformin.

Circulatory adipocytokines and lipid profile variations in type-2 diabetic subjects: desirable side-effects of antidiabetic drugs

AIM

Inspite of availability of a variety of drugs to treat type 2 diabetes, little is known about their effects on other systems. Normalization of glucose metabolism by these drugs may consequently affect the secretory function in adipocytes. Secretory adipocytokines like adiponectin and leptin are emerging as novel therapeutic targets for type 2 diabetes mellitus (T2DM). The present study was undertaken to analyze the effects of commonly used Oral Hypoglycemic Agents (OHAs) alone, or in combination with other drugs and/or insulin on circulatory adiponectin and leptin levels, lipid profile, and blood pressure in diabetic subjects.

METHODS

The study was undertaken at IRSHA and Bharati Vidyapeeth Medical College and Hospital, MS, India. Clinically diagnosed T2DM subjects and age, gender matched healthy controls were recruited. Fasting blood was collected from each subject and the blood samples were analyzed for circulatory adipocytokines and lipid parameters using commercial kits.

RESULTS

Serum adiponectin levels were significantly increased while leptin significantly decreased in diabetic men (p<0.05) and women (p<0.001) on OHA, as compared to healthy controls. Triglyceride levels significantly decreased (p<0.05) in diabetic men, however, they remained unchanged in women despite same drug treatment. Serum HDL and LDL levels (p<0.001) were significantly lower in diabetic women as compared to healthy women. Systolic (p<0.05) and diastolic (p<0.001) blood pressure was significantly high in diabetic men but remained unchanged in women.

CONCLUSIONS

Frequently used OHAs significantly improve circulatory levels of adipocytokines. Selecting best treatment option for each patient is a key, and 2012 European Association for the Study of Diabetes (EASD) and ADA guidelines recommend diabetes treatment to be individualized depending on various socioeconomic and lifestyle factors. We recommend regular analysis of circulatory adipocytokines in T2DM patients to help clinicians select the best treatment option to normalize levels of these important therapeutic targets.

Biological activity, pH dependent redox behavior and UV-Vis spectroscopic studies of naphthalene derivatives

Two naphthalene derivatives, naphthalene-2,3-dicarboxylic acid (NDA) and 1,8-dimethoxynaphthalene (DMN) were screened for antioxidant and anti-diabetic activities. Biological antioxidant studies revealed NDA as more effective antioxidant as compared to DMN. Both compounds significantly increased the cholesterol level but showed varied biological activities as regards glucose and triglyceride concentrations. The cytotoxicity results evidenced DMN to significantly inhibit the cell proliferation in a dose dependent manner with IC₅₀ of 0.13 mM. Like the biological antioxidant studies, the electrochemical results also witnessed NDA as stronger antioxidant than DMN. The pH dependent spectrophotometric and electrochemical behavior was investigated in order to provide useful mechanistic insights about the biological role of the selected compounds.