Kind Of Diabetes Research Articles

Diabetes Prediction Using Machine Learning and Flask

Diabetes is one of the costliest chronic diseases, it is a metabolic disorder in which a patient has excessive blood sugar levels due to the body's inability to create enough insulin, and it can also cause long-term harm to the heart, blood vessels, eyes, kidneys, and nerves. Adults with diabetes are twice as likely as non-diabetics to have a heart attack or stroke. Despite its massive impact on the global population, no kind of diabetes has a cure. Although most medications help patients manage their symptoms to some extent, diabetics nevertheless suffer several long-term health concerns. So, if we are able to predict diabetes early, we could control it and it can be done by using Machine learning techniques. Our work aim is to predict if the patient has diabetes using Machine learning techniques and the ensemble method. We will be using four algorithms which are SVM, KNN, Logistic Regression, and Random Forest classifier and we would also compare all four models to check which model is giving the best accuracy and link our best model to a web app that could predict if the patient has any chances of having diabetes.

Glucose forecasting combining Markov chain based enrichment of data, random grammatical evolution and Bagging

Diabetes Mellitus is a disease affecting more and more people every year. Depending on the kind of diabetes and sometimes on the stage of the illness, diabetic patients have to inject some amount of artificial insulin, namely bolus, before the meals, to make up the absence or malfunctioning of their natural insulin. This decision is a difficult task since they need to estimate the number of carbohydrates they are going to ingest, take into account the past and future circumstances, know the past values of glucose, evaluate if the effect of previously injected insulin has already finished and any other relevant information. In this paper, we present and compare a set of methodologies to automate the decision of the insulin bolus, which reduces the number of dangerous predictions. We combine two different data enrichment techniques based on Markov chains with grammatical evolution engines to generate models of blood glucose, and univariate marginal distribution algorithms and bagging techniques to select the set of models to assemble. In particular, we propose the Random-GE procedure, an adaptation of Random Forests to Grammatical Evolution, which leads to excellent prediction models, with a simple configuration and a reduced execution time. The ensemble gives the prediction of glucose for a duple of food and insulins, helping patients in the selection of the appropriate bolus to maintain healthy glucose levels after the meals. Experimental results show that our models get more accurate and robust predictions than previous approaches.

Effect of Gestational Diabetes on Gross Morphology, Histology and Histochemistry of Human Placenta

Gestational diabetes is the glucose intolerance of varying severity and complicates about 2-4% of pregnancies. While there is a surfeit of associative data that demonstrate the placental adaptive responses to gestational diabetes, the mechanisms at placental level remain elusive. One objective of this study was to investigate various anatomical, histological and some histochemical changes in placenta of gestational diabetes patients with re-evaluation of some mechanisms of placental adaptive responses to gestational diabetes. A second objective was to find whether the placenta adapts to diabetes and ultimately protects the fetus or whether it contributes to the adverse fetal outcome with diabetic pregnancies despite good care of these gestations. Two groups each of 30 placentas were collected at term and post Caesarian Section (CS) deliveries as one group was the control group (control) and the other group was collected from patients with gestational diabetes and were treated with zinc insulin. After morphological data assay, central and peripheral biopsies were processed for histological and histochemical assay. The diabetic placentas showed mild increase in diameter, central thickness and weight. This study confirmed that the villous portion with its corresponding intervillous space is the structural and functional unit of the placenta. Syncytial clumps among peripheral placenta were bigger than those of central placenta of the diabetic group and best examined by Hematoxylin and Eosin stain and to a lower extent by Van Gieson stain for light microscopy. The diabetic placentas showed marked increase of the chorionic villi which appeared more crowded centrally while the villous vasculature was higher peripherally. The increased young, immature and unspecialized villi among the diabetic placentas explained the enhanced fetal hypoxia with subsequent increased neonatal morbidity and mortality. These anatomical, histological and histochemical findings put diabetes in the moderate-high risk factors of vascular placental pathology. Also, placenta was not the primary cause to markedly affect the perinatal morbidity as the placenta showed a good degree of potentiality to adapt with derangements of gestational diabetes. So, the elevated rates of perinatal morbidity and mortality among diabetic deliveries were most probably due to metabolic abnormalities occurred in mother and fetus because of whatever kind of diabetes. Conclusion: Placenta itself is always perfect, innocent and helpful in managing and preventing complications via its endogenous mechanisms. It was necessary histologically to examine several preparations with different and specific measures to obtain detailed picture of the totality of the placenta structure. Lastly, the premium key in gestational diabetes is to apply scientific exogenous measures in harmony and accordance with early diagnosed and strictly controlled endogenous placental measures.

‘What kind of diabetes did you say I have?’

(2014). ‘What kind of diabetes did you say I have?’. European Diabetes Nursing: Vol. 11, No. 2, pp. 57-57.

‘What kind of diabetes did you say I have?’

A 15-year-old male with septo-optic dysplasia, panhypopituitarism, developmental delay, diabetes insipidus, and autism was admitted to the hospital for hypoglycaemia. The patient started having sudden seizure activity that prompted fuller evaluation. His glucose level, upon admission to the hospital, was 28mg/dl (1.6mmol/L). The patient was resuscitated with intravenous glucose and his seizure activity stopped. The past medical history included the diagnosis of septo-optic dysplasia at birth, growth hormone deficiency, secondary hypothyroidism, secondary adrenal insufficiency, diabetes insipi-dus, blindness, aggressive behaviour and autism. The patient had been taking growth hormone, levothyroxine, hydrocortisone and desmopressin acetate. There was no history of missed doses, fever, missed meals, vomiting, nor any other illnesses. He attends a school for blind children with special needs. His condition was monitored by a school nurse and supervised by a physician responsible for the school district system. His physical examination revealed no rashes, hyperpigmentation, nor any focal neurological finding. Laboratory findings revealed initial hypoglycaemia as mentioned previously, normal T4, and somatomedin-C levels, white blood cell count, and electrolytes. During hospital stay, the patient recovered from hypoglycaemia and went back to his previous functioning levels. Since there was no clear aetiology for the hypoglycaemia episode, the endocrinology team asked for documented dietary intake and scheduled medications given prior to hospital admission. This revealed no missed medication doses, but showed two daily doses of 20 units of insulin glargine (rDNA origin) injection that were given to the patient in the past two days prior to hospital admission. Further investigation showed that there was a new physician who took over the responsibility of the school system, and he ordered the insulin doses for a presumed diagnosis of diabetes mellitus rather than diabetes insipidus. The nurse never questioned the sudden start of insulin therapy without the documentation of hyperglycaemia. The mother was notified about the cause of hypoglycaemia; she sought legal action against this physician at the state school. The school system decided to settle the case out of court. The physician was penalised by the local State Medical Board and was required to take educational training courses to be able to differentiate types of diabetes. ‘Diabetes’ means to ‘flow through’ or to ‘siphon’ in Greek language since affected patients urinate frequently. Ancient Greek physicians used to taste urine to differentiate the two types of diabetes (mellitus vs insipidus) to distinguish the honeyed sweet diabetes. While the two conditions share the word ‘diabetes’, their aetiologies and medical management are completely different. Of note, Wolfram syndrome, or DIDMOAD syndrome, combines diabetes insipidus (DI), diabetes mellitus (DM), optic nerve atrophy (OA) and deafness (D).

Molekulargenetische Diagnostik bei Verdacht auf Maturity Onset Diabetes of the Young (MODY): Klinische Parameter zur Entscheidungshilfe

Monogenic forms of diabetes are often diagnosed by chance, due to the variety of clinical presentation and limited experience of the diabetologists with this kind of diabetes. Aim of this study was to evaluate clinical parameters for an efficient screening. Clinical parameters were: negative diabetes-specific antibodies at onset of diabetes, positive family history of diabetes, and low to moderate insulin requirements after one year of diabetes treatment. Molecular testing was performed through sequencing of the programming regions of HNF-4alpha (MODY 1), glucokinase (MODY 2) and HNF-1alpha/TCF1 (MODY 3) and in one patient the HNF-1beta/TCF2 region (MODY 5). 39 of 292 patients treated with insulin were negative for GADA and IA2A, and 8 (20.5%) patients fulfilled both other criteria. Positive molecular results were found in five (63%) patients (two with MODY 2, two with MODY 3, one with MODY 5). At diabetes onset, the mean age of the 5 patients with MODY was 10.6 ± 5.3 yrs (range 2.6-15 yrs), HbA(1c) was 8.4 ± 3.1 % (6.5-13.9%), mean diabetes duration until diagnosis of MODY was 3.3 ± 3.6 yrs (0.8-9.6 yrs) with insulin requirements of 0.44 ± 0.17 U/kg/d (0.2-0.6 U/kg/d). Patients with MODY 3 were changed from insulin to repaglinide, those with MODY 2 were recommended discontinuing insulin treatment. In patients with negative diabetes-specific antibodies at onset of diabetes, with a positive family history, and low to moderate insulin needs a genetic screening for MODY is indicated. Watchful consideration of these clinical parameters may lead to an early genetic testing, and to an adequate treatment.

Determinación ambulatoria de glucohemoglobina en el seguimiento y el control de la diabetes mellitus: revisión sistemática de la literatura

To compare out-patient determination of HbA(1c) with lab figures, by measuring metabolic control, quality of life and hypoglycaemia episodes, in adults with type-1 or -2 diabetes mellitus. Systematic review. MEDLINE (1966-August 2006), EMBASE (2000-August 2006), bases held by the Center for Reviews and Dissemination (DARE, INAHTA, NHS-EED), Cochrane Library (number 3, 2006), European Medication Agency, Food and Drug Administration and the European Network of Emerging Technologies. A manual search was made in Point of Care and in the register of trials, (ClinicalTrials.gov). Inclusion criteria were studies with type-1 or -2 diabetics who used portable out-patient devices and with comparison with lab references. Studies of minors, of any other kind of diabetes, of patients without a portable device and where the comparator did not include reference methods were excluded. Those that a priori met the criteria were recovered fully. A quality analysis was run according to the CASPe programme criteria and data were extracted with specific formulae. As meta-analysis was not possible, a qualitative synthesis was made. Twenty publications were selected. The values of most devices correlated well (R(2)=0.85 and R(2)=0.059; P< .001). Some studies described increase in glycaemia control, with drop in HbA(1c) of 0.1%-1.5% (P< .01); therapy control was more intense (95% CI, 0.95-1.52) and visits to the doctor decreased. Out-patient evaluations are rapid and comfortable, increasing patients' metabolic control. However, they possess certain limitations.

Vascular Endothelial Growth Factor Expression (VEGF) in Salivary Glands of Diabetic Rats

This study is aimed at evaluating vascular endothelial growth factor (VEGF) expression in the salivary glands of diabetic rats. Our study was carried out on 1 group of male Wistar rats and 1 group of male Bio Breeding Wistar (BB/W) pre-diabetic rats. The first group (control) was composed of 11 rats (4 months old), and the other (test) of 11 rats (4 months old) which showed diabetes at day 85 of life. This kind of diabetes can be compared to human diabetes mellitus type 1. The submandibular glands were removed and processed for immunohistochemical analysis of VEGF. Diabetes increased salivary gland VEGF expression in the rats. The tissues analyzed (vascular endothelium, ductal endothelium, mucinous glands) always expressed VEGF, thus demonstrating that not only vascular endothelial cells, but also the other elements evaluated, have a role in the neoangiogenesis process. In both control and diabetic rats, the VEGF expression was constantly negative only in serous acini; thus demonstrating that serous acini are not involved in the neoangiogenetic processes. The vascular growth is a fundamental part of normal salivary gland development, therefore we speculate that strategies aimed at preservation or promotion of salivary gland VEGF expression may mitigate or attenuate diabetic-induced gland microvascular injury.

Exercises for Type 2 Diabetes Patients

DR. NAGLER is physiatrist-in-chief, emeritus, and professor of rehabilitation medicine at Weill Medical College of Cornell University, New York. Type 2 diabetes is becoming increasingly common in the United States across all ages and ethnicities. This kind of diabetes, which is not dependent on insulin, can be controlled in many people by better attention to exercise and weight management. Weight control is important for patients with type 2 diabetes, and walking is a safe exercise, even for many elderly people who are not bed-ridden. However, diabetes can predispose patients to aches and pains that can limit mobility and discourage them from physical activity. In addition to promoting problems such as high blood pressure, type 2 diabetes can affect the nervous system. Consequently, patients may have problems with walking and develop an ungainly gait. Patients with type 2 diabetes should begin gait exercises as soon as they notice a problem with walking. I recommend that caregivers mark the positions of several of the patient's normal steps on the floor and have the patient walk back and forth, stepping on the marks to improve his or her gait. An awkward gait can lead to tightness in calves, hamstrings, and hip flexors. Conversely, preexisting tightness in those muscles can contribute to the development of gait problems. Strong and supple hip flexor muscles and adductor muscles are very helpful for a smooth, efficient gait. In this column, I describe several exercises that patients with type 2 diabetes should do before and after walking. (See illustrations and instructions below.) Proper footwear will make patients more comfortable. I also recommend athletic socks, preferably those made with moisture-wicking materials, and sneakers with laces that can be adjusted as the feet swell. It is especially important for patients with type 2 diabetes to have well-fitting shoes with a wide toe box, because their nervous system complications may prevent them from feeling foot pain that might be caused by ill-fitting shoes. I also recommend that patients with type 2 diabetes or their caregivers inspect the patient's feet every day. Once foot infection occurs, it is difficult to cure. Patients who sweat excessively can put baby powder inside the socks before walking to absorb moisture and prevent sores. In addition, remind patients with type 2 diabetes that they must not smoke and that they should work hard to control weight. Maintaining a healthy weight will not only help to reduce blood sugar levels; it will also reduce stress on the legs and improve the patient's gait.

Clinical Studies on Detosis in Diabetics

We determined acetone-bodies in urine of 29 diabetics before and after insulin therapy, and results are as follows:1) Acetone-bodies excretion in a day is found to be increased in all cases.2) Ketosis is not closely related to the severity of symptoms, and there seems to be certain cases which ketosis is only serious in spite of slight symptoms. We think that such kind of diabetes may be called ketosis type.3) In true diabetes and pluriglandular diabetes, ketosis ranges from low grade to high glade, on the other 'hand in extrapancreatic diabetes, ketosis is low grade in general.4) In most cases excluding ketosis type, ketosis is decreased by insulin therapy.5) Ketosis in diabetic coma in Japan is not so severe as that in Europe. From this fact, we may think that ketosis is not the only cause of diabetic coma.