Diabetes management by insulin administration is based on medical experts' experience, intuition, and expertise. As there is very little information in medical literature concerning practical aspects of this issue, medical experts adopt their own rules for insulin regimen specification and dose adjustment. This paper investigates the application of a neural network approach for the development of a prototype system for knowledge classification in this domain. The system will further facilitate decision making for diabetic patient management by insulin administration. In particular, a generating algorithm for learning arbitrary classification is employed. The factors participating in the decision making were among others diabetes type, patient age, current treatment, glucose profile, physical activity, food intake, and desirable blood glucose control. The resulting system was trained with 100 cases and tested on 100 patient cases. The system proved to be applicable to this particular problem, classifing correctly 92% of the testing cases.

A Neural Network Approach in Diabetes Management by Insulin Administration

Clinical evaluation of the DIABETES expert system for decision support by multiple regimen insulin dose adjustment

Insulin regime prescription is performed by medical personnel based on a number of patient related factors such as age, activity, type of current medication, desirable control, whether the patient belongs to a special category, for example whether he has fever or has undergone surgery, etc. No general rules apply so that each expert adopts his/her own rules for insulin regime specification based on his/her experience, intuition and expertise. This is why there is very little in medical literature concerning this issue. This paper describes a system supporting the decision making of medical personnel with respect to the specification of insulin regimes, based on a neural network methodology. In particular, an adaptive version of the backpropagation algorithm is used for the system training. This algorithm dramatically reduces training time and guarantees the monotonically decreasing nature of the error function. The training set consisted of one hundred and eight training vectors. The system offers support with respect to diabetes management by insulin regime prescription. The choice of the factors participating in the decision making of the system described in this paper, is based on an extensive interviewing of a number of diabetologists in leading diabetological centres in Greece.

Decision support for insulin regime prescription based on a neural-network approach.

With the development of technologies in wireless communication especially the third generation (3G) mobile network, Internet, software agent, it is possible now for hospitals to provide a seamless or ubiquitous virtual care environment for patients especially for those who have suffered with chronic diseases such as diabetes requiring high frequency patient-physician contact. Such an environment can provide intelligent and personalized monitoring services to patients, best-practice decision support to physicians, and wellness maintenance for cost control. In this paper, we present a new approach using 3G mobile agents for intelligent diabetes management. A conceptual model is presented and issues related to the implementation of the virtual environment are discussed.

3G network oriented mobile agents for intelligent diabetes management: a conceptual model

A Diabetes monitoring method has been developed using the blood glucose measurement made non-invasively. Glucose is the prime factor which is considered for the diagnosis of Diabetes mellitus. The common method for determining the glucose content in blood involves hand pricking by taking the blood samples. Regular pricking can cause pain and inconvenience which can even lead to calluses on the fingers and poor blood flow. Non-invasive technique is the recent advancement which does not involve drawing of any human interstitial fluids. The paper involves the design of a noninvasive glucose level detector using the Near Infrared (NIR) Spectroscopy concept and a smart device. The signals send through the fingertip will be absorbed based on vibrational movements. The result is obtained as voltage variations. The data thus obtained is then interfaced to an android device via Bluetooth to a monitoring android application which assist in keeping track of the glucose level.

Non Invasive Blood Glucose Detection along with an Assistive Diabetes Monitoring App

Optimal glycaemic control is achieved by diet manipulation and insulin administration. The potential benefits in using decision support systems for diabetic patient management are the cost saving they provide in terms of expensive man hours of verbal instruction by medical experts and the support in terms of objective and consistent decision making by the experts. This paper describes an expert system to assist diabetic patient management by blood glycose monitoring through insulin administration. The system incorporates decision making situations of patient management in Greece where diet, life style and administration of insulin differ from Northern European countries. This application is carried out at the First Propaedeutic Medical Clinic, the Ahepa General Hospital of Thessaloniki, Greece. >

http://ieeexplore.ieee.org/iel2/3093/8853/00390883.pdf

G. Ziakas

Papers

Decision support in diabetes management for optimal glycaemic control by insulin administration