Search

Type 2 Diabetes (T2D) is a chronic disease associated with a number of micro- and macrovascular complications that increase the morbidity and mortality of patients. The risk of diabetic complications has a strong genetic component. To this end, we sought to evaluate the association of 40 single nucleotide polymorphisms (SNPs) in 21 candidate genes with T2D and its vascular complications in 503 T2D patients and 580 healthy controls. The genes were chosen because previously reported to be associated with T2D complications and/or with the aging process. We replicated the association of T2D risk with IGF2BP rs4402960 and detected novel associations with TERT rs2735940 and rs2736098. The addition of these SNPs to a model including traditional risk factors slightly improved risk prediction. After stratification of patients according to the presence/absence of vascular complications, we found significant associations of variants in the CAT, FTO, and UCP1 genes with diabetic retinopathy and nephropathy. Additionally, a variant in the ADIPOQ gene was found associated with macrovascular complications. Notably, these genes are involved in some way in mitochondrial biology and reactive oxygen species regulation. Hence, our findings strongly suggest a potential link between mitochondrial oxidative homeostasis and individual predisposition to diabetic vascular complications.

Innovative biomarkers are required to manage type 2 diabetic patients (T2DM). We focused our study on miR-126-3p and miR-21-5p levels, as biomarkers of endothelial function and inflammation. MiRNAs levels were measured in plasma from 107 healthy subjects (CTR) and 193 diabetic patients (T2DM), 76 without (T2DM NC) and 117 with (T2DM C) complications. When diabetic complication were analysed as a whole, miR-126-3p and miR-21-5p levels declined significantly from CTR to T2DM NC and T2DM C patients. When miRNAs levels were related to specific complications, significantly higher miR-21-5p levels (0.46 ± 0.44 vs. 0.26 ± 0.33, p < 0.001) and significant lower miR-126-3p levels (0.21 ± 0.21 vs. 0.28 ± 0.22, p = 0.032) were found in T2DM with previous major cardiovascular events (MACE) vs. all the others T2DM patients. To confirm these results we focused on circulating angiogenic cells (CACs) from a subgroup of 10 CTR, 15 T2DM NC and 15 T2DM patients with MACE. CACs from T2DM patients expressed higher miR-21-5p and lower miR-126-3p levels than CACs from CTR. Furthermore, CACs from T2DM + MACE showed the highest levels of miR-21-5p. Circulating miR-21-5p and miR-126-3p emerge as dynamic biomarkers of systemic inflammatory/angiogenic status. Their expression levels in CACs from T2DM with MACE suggest a shift from a proangiogenic to a proinflammatory profile.

Diabetic retinopathy (DR) is a diabetes complication that damages the retina. This type of medical condition affects up to 80% of patients with diabetes for 10 or more years. The expertise and equipment required are often lacking in areas where diabetic retinopathy detection is most needed. Most of the work in the field of diabetic retinopathy has been based on disease detection or manual extraction of features. Thus, this research aims at automatic diagnosis of the disease in its different stages using deep learning neural network approach. This paper presents the design and implementation of Graphic Processing Unit (hereby GPU) accelerated deep convolutional neural networks to automatically diagnose and thereby classify high-resolution retinal images into five stages of the disease based on its severity. The accuracy of the single model convolutional neural networks presented in this paper is 71.65% from VGG-16.

Diabetic Retinopathy is a diabetes complication that causes permanent blindness. This also affects both eyes, beginning with no visual symptoms. Yet it may lead to permanent blindness without adequate treatment. Early detection of diabetic retinopathy can be an opportunity to prevent vision loss. It involves many complicated and costly treatment methodologies and sophisticated analysis of retinal fundus images by expert doctors. Many researchers proposed different image processing and segmentation techniques. The unavailability of good quality of fundus images made the techniques unstable. Deep learning showed significant performance in various medical fields, including diabetic retinopathy. But due to a lack of high cost labeled sample dataset and performance issues due to the use of large parameters, made the approaches inefficient. In this paper, we have proposed an ensemble of 5 models using the optimal transfer learning model, EfficientNet-B5 with 2 phase training. We trained the model with a large number of sample datasets from Kaggle. Our model can early screen diabetic retinopathy and also achieved a high metric (quadratic weighted kappa score of 0.961).

Diabetic Retinopathy (DR) is a diabetes complication that affects vision. It is caused by damage to the blood vessels of retina. Early and accurate detection of DR is crucial to reduce likelihood of progression to proliferative retinopathy and blindness. This paper proposes a method for classifying the severity of DR using deep learning. Experiments were conducted by blending the members of EfficientNet for classification of the diabetic retinopathy image as no DR, mild, moderate, severe, or proliferative DR. The models have been trained using different datasets and best model achieved a quadratic kappa score of 0.924377 on the APTOS test dataset. The results are promising and warrant further investigation. The presented model has the potential aid in fast diagnosis for better early detection of DR.

Diabetic retinopathy (DR) is the kind of diabetes complication that affects eyes and can damage the blood vessels inside the retina. To diagnose the strength of DR disease based on examination of the retina. Nowadays, the common diagnosis process asks for experienced ophthalmologists to inspect both fundus image and OCT (optical coherence tomography) images, which is time-consuming and not very convenient for remote rural inhabitants. The research purpose in this paper is to propose a new paradigm of automatic DR diagnosis by using artificial intelligence and cloud computing. Inside the DCNN, we changed max-pooling layers with factional max-pooling. We trained using support vector machine (SVM) to learn the underlying boundary of distribution of each category. Using that proposed method, we achieved the results of the recognition up to 86.17%. We also develop an iPhone APP. It called 'Deep Retina' that equipped with a handheld ophthalmoscope, a layman can take fundus images and perform the diagnosis automatically without intervention from ophthalmologists. It is a practically applicable telemedicine system which benefits the home care, remote medical care, and self-examination.

Diabetic Retinopathy (DR) is a diabetes complication that causes damage to the blood vessels of the light sensitive tissue at the back of the eye. All the people who are suffering from diabetes have a high risk of subjecting to DR which may lead to total blindness. Red lesions, cotton-wool spots and exudates are symptoms of non proliferative diabetic retinopathy which is the early stage of diabetic retinopathy. When the disease develops to proliferative diabetic retinopathy fluid leaking from retinal capillaries and the formation of new vessels on the surface of the retina happens. At this stage there is a very low possibility of preventing total blindness. Therefore, early detection of DR is important to prevent vision loss. So, if there is an easy way of detecting early signs of DR accurately that will be beneficial. Red lesion detection is more important for the early identification of DR. In this paper, we are proposing a method for the automated detection of red lesions in retinal images using image processing techniques and machine learning. The developed algorithm has sensitivity and specificity of 92.05% and 88.68% respectively.

Diabetic retinopathy (DR) is one of the major causes of blindness worldwide. It is a diabetes complication that occurs after the damage of the blood vessels in the light-sensitive tissue in the retina. So, early detection of DR could reduce the severity of the disease and help ophthalmologists in treating and investigating it more efficiently. In this paper, we developed a computer-aided diagnosis (CAD) system that can detect early signs of DR using both optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) images. Our system is able to segment the blood vessels from two retinal plexuses using OCTA images. Also, it segments twelve different retinal layers from OCT scans. Then, seven different features are extracted from both segmented OCTA plexuses and OCT layers. Finally, these features are fused to generate a comprehensive diagnostic non-invasive tool for detecting early signs of DR. A total number of 76 cases (23 normal and 53 DR) were used in evaluating the performance of the proposed systems. Using 4-fold cross-validation, our proposed system achieved an average accuracy of 100%. These results show the potential of the proposed system.

In today’s era, most of the people are suffering with chronic diseases because of their lifestyle, food habits and reduction in physical activities. Diabetes; is one of the most common chronic diseases which is happened to the people of all ages. Diabetes complication arises in human body due to increase of blood glucose (sugar) level than the normal level. Type-2 diabetes is considered as one of the most prevalent endocrine disorders. Type-2 diabetes is considered one of the most prevalent endocrine disorders. In this circumstance, we have tried to apply Machine learning algorithm to create the statistical prediction based model that people having diabetes can aware of their prevalence. The aim of this paper is to detect the prevalence of diabetes relevant complications among patients with type-2 diabetes mellitus. The processing and statistical analysis we used Scikit-Learn, Pandas for Python. We also have used unsupervised Machine Learning approaches known as Artificial Neural Network (ANN) and K-means Clustering for developing classification system based prediction model to judge type-2 diabetes mellitus chronic diseases.

The metabolic changes associated with diabetes mellitus (DM ) affect a variety of organs and systems, including the skin. Skin lesions are frequently observed in patients with DM , resulting from a complex interaction among biochemical, vascular, immune, and metabolic changes. Cutaneous manifestations may develop at any time in the course of DM. They can be the first sign of the disease, possibly helping in diagnosis, or represent a marker of poor glycemic control. Given the high prevalence of cutaneous manifestations in DM , their possible role in favoring DM early diagnosis, and their relationship with the patient's metabolic control, a group of Italian dermatologists and diabetologists, the DiaDex expert group, jointly formulated a few basic statements aimed at favoring a stricter interdisciplinary cooperation in order to improve patients' management. Deeper knowledge of the skin lesions most commonly associated with DM, their early identification, and prompt reciprocal referral, when appropriate, are the pivotal points of these statements and should represent the pillars of such desired cooperation. The dermatologists and diabetologists of the DiaDex group believe that their different diagnostic and therapeutic skills put together may significantly benefit the many DM patients with cutaneous complications and hope that this paper may provide some guidance on how to achieve this goal.

Aims and objectives. The aim of this paper is to explore self-care in diabetes and to present a model of factors that affect self-care according to reviewed literature. Background. Self-care in diabetes is crucial to keep the disease under control. Self-care consists at least four aspects: (i) self-monitoring of blood glucose, (ii) variation of nutrition to daily needs, (iii) insulin dose adjustments to actual needs and (iv) taking exercise regularly. It is known that diverse factors influence self-care such as knowledge, physical skills and emotional aspects and self-efficacy which have been listed as being of high importance. Methods. The searched databases were ProQuest, PsycINFO and Medline from 1995 to 2002. The search terms were ‘self-care’ or ‘self-management’ coexisting with diabetes and ‘self-efficacy’. The search was limited to English and adults with type 1 diabetes. Results. The main components of the model clarify how knowledge, physical skills and emotional factors as well as self-efficacy influence self-care which again affects metabolic control. Flexible self-care indicates high level of self-care when patients are able to care for and manage the disease in a responsible and flexible way that does not affect their life extensively, resulting in adequate glycosylated haemoglobin value. Self-efficacy is a strong predictor of flexible self-care and affects metabolic control through increased perceived ability to conduct self-care. Conclusions. The review illuminated that benefits of self-care should be emphasized and knowledge of the Diabetes Complication and Control Trial results can contribute to better self-care. However, factors affecting flexible self-care still require better identification. Relevance to clinical practice. The review emphasizes and adds to the topic, that in daily practice health care practitioners must assess diabetes-related knowledge, physical skills and emotional factors in combination with self-efficacy and the four self-care areas. The effects of self-monitoring of blood glucose needs better clarifications as it is now regarded the cornerstone of flexible self-care.

This paper examines how to develop a Model for Knowledge Management System (KMS) for diabetes complication diseases. People with diabetes have a higher risk of developing a series of serious health problems. Each patient has different condition that could lead to different disease and health problem. But, with the right information, patient could have early detection so the health risk could be minimized and avoided. Hence, the objective of this research is to propose a conceptual framework that integrates social network model, Knowledge Management activities, and content based reasoning (CBR) for designing such a diabetes health and complication disease KMS. The framework indicates that the critical knowledge management activities are in the process to find similar case and the index table for algorithm to fit the framework for the social media. With this framework, KMS developers can work with healthcare provider to easily identify the suitable IT associated with the CBR process when developing a diabetes KMS.

The fast development of hospital information systems (HIS) produces a large volume of electronic medical records, which provides a comprehensive source for exploratory analysis and statistics to support clinical decision-making. In this paper, we investigate how to utilize the heterogeneous medical records to aid the clinical treatments of diabetes mellitus. Diabetes mellitus, simply diabetes, is a group of metabolic diseases, which is often accompanied with many complications. We propose a Symptom-Diagnosis-Treatment model to mine the diabetes complication patterns and to unveil the latent association mechanism between treatments and symptoms from large volume of electronic medical records. Furthermore, we study the demographic statistics of patient population w.r.t. complication patterns in real data and observe several interesting phenomena. The discovered complication and treatment patterns can help physicians better understand their specialty and learn previous experiences. Our experiments on a collection of one-year diabetes clinical records from a famous geriatric hospital demonstrate the effectiveness of our approaches.

Diabetes is one of the greatest public health challenges to face Australia. It is already Australia’s leading cause of kidney failure, blindness (in those under 60 years) and lower limb amputation, and causes significant cardiovascular disease. Australia’s diabetes amputation rate is one of the worst in the developed world, and appears to have significantly increased in the last decade, whereas some other diabetes complication rates appear to have decreased. This paper aims to compare the national burden of disease for the four major diabetes-related complications and the availability of government funding to combat these complications, in order to determine where diabetes foot disease ranks in Australia. Our review of relevant national literature indicates foot disease ranks second overall in burden of disease and last in evidenced-based government funding to combat these diabetes complications. This suggests public funding to address foot disease in Australia is disproportionately low when compared to funding dedicated to other diabetes complications. There is ample evidence that appropriate government funding of evidence-based care improves all diabetes complication outcomes and reduces overall costs. Numerous diverse Australian peak bodies have now recommended similar diabetes foot evidence-based strategies that have reduced diabetes amputation rates and associated costs in other developed nations. It would seem intuitive that “it’s time” to fund these evidence-based strategies for diabetes foot disease in Australia as well.

Background Diabetes is Australia’s leading cause of kidney failure, blindness (under 60yo), and amputation, plus, causes significant cardiovascular disease. Australia’ sd iabetes amputation rate has increased by 30% in the last decade and is one of the worst in the developed world, yet other Australian diabetes complication outcomes have improved. This paper aims to compare the national burden of disease for the four major diabetes-related complications and the availability of government funding to combat these complications, in order to determine where diabetes foot disease ranks in Australia. Methods Electronic databases, government and health websites were searched for papers (1995 – 2012) reporting Australian national diabetes-related complication numbers, incidence or prevalence rates, burden of disease, economic costs and program funding. Publications reviewed included epidemiological, health economic, evidence-based guidelines, government, Medicare and Pharmaceutical Benefits Scheme reports. Results Foot disease ranked second in numbers affected, deaths, cost per episode and overall burden of disease of the four diabetes complications in Australia. However, 50% of the national evidence-based diabetic foot disease guideline recommendations are funded via Medicare, compared to 100% of other national diabetes complication guideline recommendations. Furthermore, foot disease ranked last for additional program funding. Conclusions Findings suggest foot disease is the second leading cause of burden of disease, yet receives the least available government funding of the four major diabetes complications in Australia. This low level of clinical funding may be a major factor in Australia’s poor end stage foot outcomes (amputation rates) compared to other diabetes end stage outcomes.

Modern diabetes management emphasizes the early detection and prompt treatment of diabetic complications. However it is difficult to organize comprehensive screening at the primary care level. To address this problem we established a complication assessment service whereby all the major diabetes-specific complications were assessed in a single 3 h visit. A report with results and recommendations was sent to the general practitioner (GP). Being philosophically a complication-specific service, no attempt was made to intervene with metabolic management. This paper describes our experience with the first 743 patients of whom 92% had been referred from GPs. Of the diabetes-specific complications, 22% of patients had one, 5% had two, and 1% had three major complications. Many of the patients were unaware of the presence of these complications. One hundred and three people had attended the service on more than one occasion with an average time between visits of 1.7 years. The results demonstrated that GPs were very good at following a recommendation to refer a patient for ophthalmic assessment (85% of cases) and improving hypertension but were less successful in treating hyperlipidaemia. This service has proven to be an excellent forum for the collection of data and the teaching of health professionals. It is a move away from the traditional format of hospital-based clinics providing comprehensive diabetes management.