A hybrid super ensemble learning model for the early-stage prediction of diabetes risk.

Diabetes mellitus has become a rapidly growing chronic health problem worldwide. There has been a noticeable increase in diabetes cases in the last two decades. Recent advances in ensemble machine learning methods play an important role in the early detection of diabetes mellitus. These methods are both faster and less costly than traditional methods. This study aims to propose a new super ensemble learning model to enable an early diagnosis of diabetes mellitus. Super learner is a cross-validation-based approach that makes better predictions by combining prediction results of more than one machine learning algorithm. The proposed super learner model was created with four base-learners (logistic regression, decision tree, random forest, gradient boosting) and a meta learner (support vector machines) as a result of a case study. Three different dataset were used to measure the robustness of the proposed model. Chi-square was determined as an optimal feature selection technique from five different techniques, and also hyper-parameter settings were made with GridSearch. Finally, the proposed new super learner model achieved to obtain the best accuracy results in the detection of Diabetes mellitus compared to the base-learners for the early-stage diabetes risk prediction (99.6%), PIMA (92%), and diabetes 130-US hospitals (98%) dataset, respectively. This study revealed that super learner algorithms can be effectively used in the detection of diabetes mellitus. Also, obtaining of the high and convincing statistical scores shows the robustness of the proposed super learner model.

The effect of motivational interview persons with diabetes on self-management and metabolic variables.

OBJECTIVE: To evaluate the effect of motivational interviewing on diabetics related to perceived self-management and metabolic variables. METHODS: The randomised controlled and experimental study was conducted at a public hospital located in the city of Gaziantep in Turkey and comprised diabetes patients attending the outpatient clinic of endocrinology and metabolic diseases from April to July 2015. The subjects were randomised into two equal intervention and control groups. Four motivational interviewing sessions, each of which took about 15-20 minutes, were conducted by a nurse to the intervention group. Data was collected using a questionnaire and the Perceived Diabetes Self-Management Scale. RESULTS: Of the 60 subjects, there were 30 (50%) in ach of the two groups. The perceived self-management perception mean score of the intervention group was 17.1 } 5.6 at baseline and increased to 35.0 } 4.1 postintervention (p<0.05). Mean scores of body mass index, fasting and postprandial blood glucose, glycated haemoglobin, cholesterol, triglyceride, low density lipoprotein cholesterol and systolic and diastolic blood pressures of subjects in the intervention group decreased after the intervention, and their high density lipoprotein cholesterol mean scores increased (p<0.05). CONCLUSIONS: Motivational interviewing technique positively affected the metabolic control indicators of the diabetes patients and increased their perceived self-management.

The Challenge of Diabetes in the Elderly and Affecting Factors: A Turkish Study.

This study was conducted with the goal of evaluating the challenge of diabetes in elderly individuals and affecting factors. This descriptive study was conducted with 88 diabetic patients 65 years of age or older who were admitted to the endocrinology and metabolism disorders outpatient clinic data of the study collected by using a questionnaire prepared by the researchers and the Elderly Diabetes Burden Scale. Total score of the scale varies between 19 and 92 points. While a higher score indicates a higher burden a lower score indicates a lower burden, data were analyzed by using Student t test, 1-way analysis of variance, Mann-Whitney U test, and Kruskal-Wallis test. Subscale and total mean scores of patients were as follows: 9.4 ± 3.2 for symptom burden; 12.4 ± 3.4 for social burden; 11.4 ± 3.3 for burden by dietary restrictions; 11.9 ± 3.7 for burden of worry about diabetes; 4.3 ± 1.3 for burden from treatment dissatisfaction; 9.4 ± 4.6 for burden by oral antidiabetic drugs or insulin; and 58.5 ± 9.6 for total diabetes burden score. Diabetes burden was found to be higher for patients who were at an advanced age, single, female, had a lower income, receiving oral antidiabetic or insulin treatment, and had diabetes duration of 6 to 11 years, a concomitant chronic condition or a diabetic person among first-degree relatives and who did not come for regular follow-up visits, had no assistance for their care, and who stated a poor quality of life and treatment compliance. Elderly diabetic patients were found to have a high total Elderly Diabetes Burden Scale score, and the highest scores were observed for the subscales of burden by dietary restrictions, social burden, and burden of worry about diabetes. Thus, it could be recommended to perform appropriate nursing interventions in order to assess and reduce diabetes challenge during planning of necessary treatment and care in elderly diabetic patients.