Prediction of blood glucose levels in diabetic patients using a hybrid AI technique. |
| |
| Authors: | J J Liszka-Hackzell |
| |
| Affiliation: | 1. Internal Medicine Department, Besancon University Hospital, Besancon, France;2. Intensive Care Unit Department, Besancon University Hospital, Besancon, France;3. Infectious and tropical disease Department, Besancon University Hospital, Besancon, France;4. Laboratory of virology, Besancon University Hospital, Besancon, France;5. Department of Hematology, Besancon University Hospital, Besancon, France;6. Oncology Department, Besancon University Hospital, Besancon, France;7. UMR 1098, Interaction Hôte-Greffon-Tumeurs/Ingénierie Cellulaire et Génique;8. UMR CNRS 6249, Chrono environnement, University of Bourgogne Franche-Comté;2. The Cardiovascular Center, the First Hospital of Jilin University, Changchun, China;3. Laboratory for Cardiovascular Diseases, Institute of Translational Medicine, the First Hospital of Jilin University, Changchun, China.;1. Hangzhou Dianzi University (HDU), China;2. University of Technology Sydney (UTS) and CSIRO, Australia;3. INRIA, Bordeaux Research Center, France |
| |
| Abstract: | One of the problems in the management of the diabetic patient is to balance the dose of insulin without exactly knowing how the patient's blood glucose concentration will respond. Being able to predict the blood glucose level would simplify the management. This paper describes an attempt to predict blood glucose levels using a hybrid AI technique combining the principal component method and neural networks. With this approach, no complicated models or algorithms need be considered. The results obtained from this fairly simple model show a correlation coefficient of 0.76 between the observed and the predicted values during the first 15 days of prediction. By using this technique, all the factors affecting this patient's blood glucose level are considered, since they are integrated in the data collected during this time period. It must be emphasized that the present method results in an individual model, valid for that particular patient under a limited period of time. However, the method itself has general validity, since the blood glucose variations over time have similar properties in any diabetic patient. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
