Journal of Diabetic Complications & Medicine

There is growing interest in the potential of plant remedies to treat and manage many diseases owing to the adverse side effects, unavailability and unaffordability associated with the conventional therapy. Among the traditional plants that has been prescribed for clinical use for many ailments including diabetes mellitus is Azardirachta indica. Their continued use is largely based on their long-term therapeutic effects although this has not been authenticated scientifically. This study therefore, aims to evaluate the in vivo hypoglycemic effect of aqueous leaf extracts of A. indica in alloxan-induced white male albino mice. The blood glucose lowering effect of the extract was intraperitoneally and orally bioscreened in diabetic mice in serial dilutions of the extract at 25 mg/kgbwt, 48.4 mg/kgbwt, 93.5 mg/kgbwt, 180.9 mg/kgbwt and 350 mg/kgbwt. Qualitative analysis of phytochemicals was done using standard procedures. In both routes, the extract lowered blood glucose at all dosages in a dose independent manner. The extracts contained flavonoids, tannins, sterols, saponins, anthraquinones and alkaloids. The antidiabetic activity may be attributable to these phytochemicals present in the plant extract. The study confirms the traditional use of this plant part in the treatment of diabetes mellitus. However, organic solvent extraction of the leaves of this plant should be done to compare effects of both organic and aqueous fractions.

Background: The aim of the study was to investigate the association between two polymorphisms of the angiotensinogen (AGT) gene (rs699 and rs4762) and subclinical markers of carotid atherosclerosis in subjects with type 2 diabetes mellitus (T2DM).

Patients and methods: In this cross-sectional study 599 subjects with T2DM and 200 subjects without T2DM (control group) were enrolled. The CIMT and plaque characteristics (presence/absence and plaque thickness) on both the near and the far walls in the common carotid artery, bulb and internal carotid arteries, bilaterally were assessed ultrasonographically. After several years (3.8 ± 0.5 years), patients were re-assessed and changes in subclinical markers of carotid atherosclerosis were calculated. Polymorphisms rs699 and rs4762 of the AGT gene were genotyped by using allele-specific PCR (KASPar) assay.

Results: The highest increase in carotid plaque thickness was observed in homozygote carriers of the A allele, even after adjustment for confounding variables. Polymorphism rs699 did not affect the progression of CIMT in the increase of number of segments with plaques.

Conclusions: In the study we have found that the rs699 of the AGT gene is a potential genetic marker of carotid atherosclerosis progression (expressed as increase in carotid plaque thickness) in Slovenian patients with T2DM. It did not affect other ultrasonographic markers of carotid atherosclerosis progression. Polypmorphism rs4762 was not associated with carotid atherosclerosis progression in Slovenian patients with T2DM.

Objective: The present study aimed at investigating machine learning methods for automated detection of severe diabetic neuropathy. Severe diabetic neuropathy represents a significant neurological problem in diabetes as it requires urgent intervention to reduce the risk of sudden cardiac death. Automated detection provides a tool that can be applied to clinical data and for identifying comorbidities that can trigger diagnosis and treatment.

Methods: We applied multi scale Allen factor to determine heart rate variability, a marker for diabetic neuropathy from ECG recordings as features to be used for the machine learning methods and automated detection. The major innovation of this work is the introduction of a new Graph-Based Machine Learning System (GBMLS). This method is intended to enhance the effectiveness of the diagnosis of severe diabetic neuropathy. We applied it to the multi scale Allen factor (MAF) features as a collection of attributes determined from the recorded ECG bio signals. These attributes can be collected as a result of routine ECG investigation of patients regardless of the presenting medical problems.

Results: Our experiments compared the sensitivity and specificity of the automated detection produced by GBMLS with analogous outcomes achieved by various other machine learning approaches. To this end we used a comprehensive collection of important classifiers and clusterers available in the open source machine learning software package Scikit-learn. The experiments have demonstrated that the best outcomes were obtained by GBMLS in combination with MAF, which improved sensitivity to 0.89 and specificity to 0.98 and outperformed several other classifiers and clusterers including Random Forest with sensitivity of 0.83 and specificity of 0.92.

Conclusion: The novel GBMLS machine learning technique applied to MAF attributes has outperformed other machine learning methods and achieved excellent sensitivity and specificity. These results are significant and sufficiently effective to be recommended for practical application of this technique.