Diabetic peripheral neuropathy class prediction by multicategory support vector machine model: a cross-sectional study / 한국역학회지

OBJECTIVES: Diabetes is increasing in worldwide prevalence, toward epidemic levels. Diabetic neuropathy, one of the most common complications of diabetes mellitus, is a serious condition that can lead to amputation. This study used a multicategory support vector machine (MSVM) to predict diabetic peripheral neuropathy severity classified into four categories using patients' demographic characteristics and clinical features. METHODS: In this study, the data were collected at the Diabetes Center of Hamadan in Iran. Patients were enrolled by the convenience sampling method. Six hundred patients were recruited. After obtaining informed consent, a questionnaire collecting general information and a neuropathy disability score (NDS) questionnaire were administered. The NDS was used to classify the severity of the disease. We used MSVM with both one-against-all and one-against-one methods and three kernel functions, radial basis function (RBF), linear, and polynomial, to predict the class of disease with an unbalanced dataset. The synthetic minority class oversampling technique algorithm was used to improve model performance. To compare the performance of the models, the mean of accuracy was used. RESULTS: For predicting diabetic neuropathy, a classifier built from a balanced dataset and the RBF kernel function with a one-against-one strategy predicted the class to which a patient belonged with about 76% accuracy. CONCLUSIONS: The results of this study indicate that, in terms of overall classification accuracy, the MSVM model based on a balanced dataset can be useful for predicting the severity of diabetic neuropathy, and it should be further investigated for the prediction of other diseases.

Prevalence and risk factors of five most common upper extremity disorders in diabetics

In addition to macrovascular and along with other microvascular complications, diabetic patients suffer from some common musculoskeletal complications. The aim of this study was to assess the prevalence of five musculoskeletal disorders of upper extremity including shoulder capsulitis [SC], limited joint mobility [LJM], Dupuytren's contracture [DC], carpal tunnel syndrome [CTS], and trigger finger [TF] as well as identify their related risk factors in diabetic patients. We recruited 432 types 1 or 2 diabetic patients and evaluated them for the presence of musculoskeletal disorders and their-related risk factors in 2012-13. The patients were exam-ined by an endocrinologist and then suspected subjects evaluated by a rheumatologist for defin-ing final diagnosis. The most prevalent musculoskeletal disorder of upper extremity was SC [8.79%], fol-lowed by CTS [8.56%], LJM [6.94%], DC [7.4%], and TF [6.71%]. Advanced age, female sex, smoking, and duration of diabetes were associated with the appearance of SC; female sex and duration of diabetes with CTS; advanced age and smoking with LJM; advanced age, duration of diabetes and history of foot ulcer with DC; and history of laser photocoagulation was associated with TF. The results show lower prevalence of upper musculoskeletal disorders and differ-ent associated risk factors in our diabetic population in comparison with previous studies on other populations.

prevalence and associated risk factors of peripheral diabetic neuropathy in Hamedan, Iran

Diabetic neuropathy is one of the most common complications of diabetes mellitus, of which it's most prevalent form is chronic sensorimotor neuropathy. The aim of this study is to assess the prevalence of diabetic peripheral neuropathy [DPN] and its associated risk factors among diabetic patients who reside in Hamedan, Iran. A cross-sectional study of 600 types 1 and 2 diabetic patients was performed using the standard Neuropathy Symptom Score [NSS] and Neuropathy Disability Score [NDS] criteria for the diagnosis of diabetic neuropathy. Overall prevalence of DPN in this population was 45.7% [95% CI: 42.6%-48.8%]. The prevalence of DPN in type 1 diabetic patients was 21.5%, whereas in type 2 diabetic patients it was 49.3% [P<0.001]. Duration of diabetes and education level were significantly associated with DPN in type 1 diabetic patients and a history of foot ulcer, age, duration of diabetes, weight, education level, and sex had a significant association with DPN in type 2 diabetic patients according to multiple logistic regression analysis. The results of our study showed a relatively high prevalence of DPN in our diabetic population. A significant difference existed in the prevalence of DPN between types 1 and 2 diabetic patients

Grape seed extract to improve liver function in patients with nonalcoholic fatty liver change

Therapeutic intervention in nonalcoholic fatty liver disease are limited, while anti-oxidative materials have shown benefits in animal models. This study aimed to evaluate grape seed extract as an anti-oxidative material in this process. Therapeutic effects of grape seed extract were evaluated in comparison to vitamin C in a double-blind setting. Fifteen patients were enrolled in each group. Liver function tests were done; also, grade of steatosis and pattern of echogenicity of the liver were determined. Patients were followed up by the same evaluation repeated in first, second and third months. Mean age +/- standard deviation was 43.2 +/- 10.3 years. Grape seed extract [GSE] significantly improved the grade of fatty liver change; and resulted in significant decrease in alanine aminotransferase in patients receiving the concentrate compared to those receiving vitamin C independently, from the initial grade of steatosis. This study describes the beneficial effect of using grape seed extract for three months in patients with nonalcoholic fatty liver disease. These results may improve with a longer period of follow-up