Predictive data modeling of human type II diabetes related statistics (original) (raw)
Related papers
American Journal of Biomedical Sciences, 2013
In this paper, a comparison of two different approaches that can be used in developing time series mathematical models (MM) of diabetes mellitus was carried out. The trade-off should be considered between the complexity of the model and its accuracy to predict future glucose concentration. This work is a continuation of the author's work and results obtained previously and showed the potential and superiority of using autoregressive with exogenous terms (ARX) model in describing the dynamics of diabetes. Moreover, it is shown that despite the models are of general form but they are different depending on individuals' regimen of diabetes management. The last fact was demonstrated by using six diabetic patients' records, with rich information about their life style and treatment program, to derive models. In addition to that an answer is given to two main questions: how many future samples of glucose levels can be predicted with acceptable accuracy and what is the acceptable order of the model-complexity-, if the prediction horizon is specified. Both types of models were developed, tested and compared. This work emphasizes the fact that diabetes management plan should be formulated as an individualized therapeutic to achieve the desired level of diabetes control. This can be of help in improving the metabolic control of type-1diabetes patients by implementing these characteristics and models in both computerized controlled decision support system and simulation systems for educating and training of healthcare professional staff. Additionally, these MM of glucose-insulin interaction are expected to aid in reaching a generalized model.
2020
In this paper, a comparison of two different approaches that can be used in developing time series mathematical models (MM) of diabetes mellitus was carried out. The trade-off should be considered between the complexity of the model and its accuracy to predict future glucose concentration. This work is a continuation of the author's work and results obtained previously and showed the potential and superiority of using autoregressive with exogenous terms (ARX) model in describing the dynamics of diabetes. Moreover, it is shown that despite the models are of general form but they are different depending on individuals' regimen of diabetes management. The last fact was demonstrated by using six diabetic patients' records, with rich information about their life style and treatment program, to derive models. In addition to that an answer is given to two main questions: how many future samples of glucose levels can be predicted with acceptable accuracy and what is the accep...
Short-term diabetes blood glucose prediction based on blood glucose measurements
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2008
Insulin Dependent Diabetes Mellitus (IDDM) is a chronic disease characterized by the inability of the pancreas to produce sufficient amounts of insulin. Daily compensation of the deficiency requires 4-6 insulin injections to be taken daily, the aim of this insulin therapy being to maintain normoglycemia--i.e., a blood glucose level between 4-7 mmol/L. To determine the quantity and timing of these injections, various different approaches are used. Currently, mostly qualitative and semi-quantitative models and reasoning are used to design such a therapy. Here, an attempt is made to show how system identification and control may be used to estimate predictive quantitative models to be used in design of optimal insulin regimens. The system was divided into three subsystems, the insulin subsystem, the glucose subsystem and the insulin-glucose interaction. The insulin subsystem aims to describe the absorbtion of injected insulin from the subcutaneous depots and the glucose subsystem the a...
Computer methods and programs in biomedicine, 2015
In this paper, the problem of predicting blood glucose concentrations (BG) for the treatment of patients with type 1 diabetes, is addressed. Predicting BG is of very high importance as most treatments, which consist in exogenous insulin injections, rely on the availability of BG predictions. Many models that can be used for predicting BG are available in the literature. However, it is widely admitted that it is almost impossible to perfectly model blood glucose dynamics while still being able to identify model parameters using only blood glucose measurements. The main contribution of this work is to propose a simple and identifiable linear dynamical model, which is based on the static prediction model of standard therapy. It is shown that the model parameters are intrinsically correlated with physician-set therapy parameters and that the reduction of the number of model parameters to identify leads to inferior data fits but to equivalent or slightly improved prediction capabilities ...
Applying a novel combination of techniques to develop a predictive model for diabetes complications
PloS one, 2015
Among the many related issues of diabetes management, its complications constitute the main part of the heavy burden of this disease. The aim of this paper is to develop a risk advisor model to predict the chances of diabetes complications according to the changes in risk factors. As the starting point, an inclusive list of (k) diabetes complications and (n) their correlated predisposing factors are derived from the existing endocrinology text books. A type of data meta-analysis has been done to extract and combine the numeric value of the relationships between these two. The whole n (risk factors) - k (complications) model was broken down into k different (n-1) relationships and these (n-1) dependencies were broken into n (1-1) models. Applying regression analysis (seven patterns) and artificial neural networks (ANN), we created models to show the (1-1) correspondence between factors and complications. Then all 1-1 models related to an individual complication were integrated using ...
Linear Modeling and Prediction in Diabetes Physiology
Lecture Notes in Bioengineering, 2014
Diabetes Mellitus is a chronic disease characterized by the inability of the organism to autonomously regulate the blood glucose level due to insulin deficiency or resistance, leading to serious health damages. The therapy is essentially based on insulin injections and depends strongly on patient daily decisions, being mainly based upon empirical experience and rules of thumb. The development of a prediction engine capable of personalized on-the-spot decision making concerning the most adequate choice of insulin delivery, meal intake and exercise would therefore be a valuable initiative towards an improved management of the desease. This thesis presents work on data-driven glucose metabolism modeling and short-term, that is, up to 120 minutes, blood-glucose prediction in Type 1 Diabetes Mellitus (T1DM) subjects. In order to address model-based control for blood glucose regulation, low-order, individualized, data-driven, stable, physiological relevant models were identified from a population of 9 T1DM patients data. Model structures include: autoregressive moving average with exogenous inputs (ARMAX) models and state-space models. ARMAX multi-step-ahead predictors were estimated by means of least-squares estimation; next regularization of the autoregressive coefficients was introduced. ARMAX-based predictors and zero-order hold were computed to allow comparison. Finally, preliminary results on subspace-based multi-step-ahead multivariate predictors is presented. 3 kept an eye on me as my mum would have done! Anders Blomdell and Leif Andersson deserves credit for computer support, Leif is also acknowledged for the typesetting of this thesis. I owe my gratitude to the Ph.D. fellows Anna, Meike, Isolde, Maria, Daria, Mikael, Karl M., Erik and Aivar for their moral support! Becoming homeless almost immediately after my arrival in Lund brought its benefits: Rolf and Siv Braun! I have really enjoyed being your daughter even for only three months. I acknowledge the SK RAN triathles, in particular Angela, Emil, Esther, Frida, Johannes, Marianne, Matthew and Rickard for being my support system over the past year. Last, I would like to thank my family for being supportive in all I have been doing and for making me feel your love despite the distance! 6
Prediction models for cardiovascular disease in diabetes mellitus
Oxford Textbook of Endocrinology and Diabetes, 2011
Throughout the history of medicine, physicians have diagnosed and treated patients relying on their complaints and symptoms. Today, to gauge a patient’s risk of future ill health, physicians rely in addition on patient characteristics expressed as numerical values from physical and laboratory measurements, and from family and past medical histories. Risk scores represent examples of mathematical equations that utilize this information to model reality. Although sometimes not recognized as such, models currently aid in the everyday care of patients with diabetes and include, for example, simple models for adiposity (e.g. body mass index), more complex models for glomerular function, and even more complex algorithms to calculate dosages for continuous subcutaneous insulin based on levels of blood glucose, insulin sensitivity, exercise, diet, and more. Calculators such as the Framingham or United Kingdom Prospective Diabetes Study (UKPDS) risk equations are increasingly being used to p...
Comparison of algorithms for the prediction of glucose levels in patients with diabetes
Nova Scientia, 2021
This work presents a comparison between two algorithms for the prediction of glucose levels in diabetic patients by using a univariate time series. The algorithms are applied to the history of fasting glucose levels to predict the five following values. The comparison is performed between 1) The Autoregressive Neural Networks (ARNN) and 2) The autoregressive integrated moving average (ARIMA) models. A total of 70 series are analyzed, and we show that the results obtained for the ARIMA model have error percentages higher than 25% of the predicted value to the expected value. In contrast, in 73% of the cases, the percentage error was less than 25% for the Autoregressive Neural Networks.
Statistical modeling for prediction of diabetes in Malaysians
2018
Type II Diabetes Mellitus is one of the silent killer diseases worldwide. According to the World Health Organization, 347 million people are suffering from diabetes throughout the world. To overcome the sharp rise in the disease, various diagnostic or prediction models were developed through various techniques such as artificial intelligence, classification and clustering, pattern recognition and statistical methods. The study led to the related open issues of identifying the need of a relation between the major factors that lead to the development of diabetes. This is possible by investigating the links found between the independent and dependant variables in the dataset. This paper investigates the effect of binary logistic regression applied on a dataset. The results show that the most effective method was the enter method which gave a prediction accuracy of almost 93%.