Analysis diabetes mellitus on complications with data mining

Front Genet 6;9:

Analysis diabetes mellitus on complications with data mining

CiteSeerX — Mining Diabetes Complication and Treatment Patterns for Clinical Decision Support

They used the classification and regression tree approach to analyze the data sets Breault et al. The diabetes in Saudi Arabia had been investigated and found that the overall prevalence of diabetes adults in KSA is They further recommend a longitudinal study to demonstrate the importance of modifying risk factors for the development of diabetes and reducing its prevalence in KSA Al-Nozha et al, The factors contribute to improvement in glycemic control, published in Data mining indicated that intensity of education did not predict changes in HbA1c levels Sigurdardottir et al.

The insulin therapy and episodes of severe hypoglycaemia in preschool children were investigated Yokotaa et al. The therapeutic management and control of diabetes with cardiovascular modification in case of type diabetes in France had been studied.

The study was proposed to diabetologists across France.

Analysis diabetes mellitus on complications with data mining

However, both awareness and application of published recommendations need to be reinforced Charpentier et al. The diabetic control study in the Western Pacific Region to identify factors associated with glycemic control and hypoglycemia.

Clinical and management details were recorded and finger-pricked blood samples were obtained for central glycated hemoglobin HbA1c Craig et al. The prevalence of diabetes mellitus and islet auto antibodies in an adult population from Southern Spain and the prevalence of Type 2 diabetes and LADA are high in the south of Spain Soriguer-Escofet et al.

Diabetes due to specific mechanisms and diseases is divided into two subgroups; diabetes in which genetic susceptibility is clarified at the DNA level and diabetes associated with other diseases or conditions Richards et al.

Association analysis of diabetes mellitus (DM) with complication states based on association rules

The data of Smoking habits were reported to the Swedish National Diabetes Register NDR the trend in the proportion of smoking in diabetes and to study associations between smoking, glycaemic control and micro albuminuria and their studies concluded that Smoking in patients with diabetes was widespread, especially in young female type 1 and in middle-aged type 1 and 2 diabetes patients and should be the target for smoking cessation campaigns.

Smoking was associated with both poor glycaemic control and microalbuminuria, independently of other study characteristics Nilsson et al. Investigated on weight loss goal among participants enrolled in an adapted Diabetes Prevention Program DPPfindings highlight the importance of supporting participants in lifestyle interventions to initiate and maintain dietary self-monitoring and increased levels of physical activity Harwell et al.

Application of data mining in health care is an attracting field of research. Proposed research work provides an overview of this emerging field, clarifying how data mining techniques is applicable on healthcare analysis to predict the mode of diabetic intervention control.

INFONA - science communication portal

In general, data mining is the analysis of observation data sets to find unsuspected relationship and we will summarize the data in novel ways that are understandable and useful to the common man and medical fraternity. In this paper, we give a methodological review of data mining, focusing on diabetic data analysis process using classification technique and highlighting ROC plots and formation of confusion matrix to give the performance measures of related to best mode of diabetic intervention control.

This is publicly available dataset on the web portal of WHO http: The approach of process of model building is carried out in data mining technique the steps of generation of model are described in the process model as given in the Fig. The database was designed in oracle 10g database.

Connecting server to client: In present case the server is Oracle database 10 g and connection is established with Oracle data miner 10 g. The oracle data miner applies the mechanism of building, testing and applying a model in order to find the mode of diabetic intervention control.Targeting weight loss interventions to reduce cardiovascular complications of type 2 diabetes: a machine learning-based post-hoc analysis of heterogeneous treatment effects in the Look AHEAD trial Machine Learning and Data Mining Methods in Diabetes Research.

Updating Cart........ Please Wait........

Computational and Structural Biotechnology Journal, Vol. 15 Type 2 Diabetes. Keywords— diabetes mellitus, data analysis, data mining, diabetes prevalence, complications INTRODUCTION: Diabetes is a group of metabolic diseasescaused by the lack of insulin in the body or inability to produce as normal.

project, a data mining pipeline has been used to derive a set of predictive models of type 2 diabetes mellitus (T2DM) complications based on electronic health record data of nearly one thousand patients. machine, type 2 diabetes mellitus. 1. Introduction preventing and delaying the progression of complications of diabetes [5].

Data mining techniques could be used as on principal component analysis and adaptive neuro-fuzzy inference system to diagnosis of diabetes disease. In Expert. A New Classification of Diabetic Gait Pattern Based on Cluster Analysis of Biomechanical Data Zimi Sawacha, Ph.D.,1 Gabriella Guarneri, M.D.,2 Angelo Avogaro, one of the most serious complications of diabetes mellitus and a major risk factor for A New Classification of Diabetic Gait Pattern Based on Cluster Analysis of Biomechanical.

Application of Data Mining Methods and Techniques for Diabetes Diagnosis K. Rajesh, V. Sangeetha Diabetes mellitus, or simply diabetes, is a set of related Analysis was performed on the given dataset to rank the. ISSN:

Application of data mining: Diabetes health care in young and old patients - ScienceDirect