Testing of a Short-Term Blood Glucose Prediction Algorithm Using the DirecNet Database

摘要

A short-term blood glucose prediction algorithm was validated using the DirecNet clinical database. Noise at 0, 10, 15, 20, and 25% levels was added to blood glucose tracks to assess the stability of the algorithm. Computer modeling showed that the average prediction error was 2.0, 3.0, 6.6, 7.4, and 13.7%, respectively. Diabetes mellitus (DM) is an endocrine disease associated with carbohydrate metabolism disorders. Insulin therapy, i.e., normalization of glucose uptake by insulin administration, is the most effective technique for DM compensation. This procedure should be performed according to the recommendations of the consulting physician and accompanied by glycemic (blood glucose) monitoring. At present, patients with DM set the insulin administration mode and perform blood glucose (BG) monitoring manually. Automation of insulin therapy would make it possible to increase the efficiency of DM compensation and to improve the quality of life of patients with DM type 1. A device for automated insulin therapy comprises a BG meter (glucometer) and an insulin pump united into a single system for BG control using special software. The automated system used in this work is based on a nonin-vasive glucometer. Therefore, the stability and quality of the system performance depend to a high extent on the short-term BG prediction algorithm and the software controlling the system elements. Thus, a closed-loop control system is formed.