A minute volume such as a few hundred nano-litres of gingival crevicular fluid (GCF) will evaporate within one minute at room temperature after collection. In order to investigate the feasibility of a method for noninvasive blood glucose measurement using this fluid, a fabricated GCF-collecting device, and the time-course changes of blood and GCF glucose levels in diabetics were evaluated. As a result of improvement in the GCF-collecting device such that the color of a filter paper changed from white to black upon collection of the sample, the completion of the collecting procedure could be visually confirmed. Using this device, we succeeded in collecting 200 nl of GCF within 30 s, despite the fact that GCF is usually secreted at a rate between 2 and 3 microl per tooth per hour. This method could be applicable for collecting small volume of other biological fluids. The time-course changes of blood and GCF glucose levels in ten type 2 diabetic subjects were examined, the correlation coefficient, R, between both glucose levels was 0.878. The result proved to be similar to that for normal healthy subjects in a previous study. A significant time difference between the two glucose levels was not observed. In diabetes period of 4.8 +/- 1.7 years, the influence of the disease on the GCF glucose level was minimal. Furthermore, from the ROC curve analysis, both sensitivity and specificity showed favorable results. It was suggested that the measurement of GCF glucose levels was a promising screening method for diabetics.

Many diabetics carry a portable-type blood glucose monitor and collect their own blood to examine their blood glucose levels daily (self monitoring of blood glucose, SMBG). The use of a physical condition variable was suggested in order to estimate the blood glucose level for diabetics. Four sets of data, including FBG, food intake, metabolic rate and physical condition, were collected from four Type 1 diabetics over a five-month period. Using these data, an increasing or decreasing tendency for FBG for the next day was estimated using the data mining method. The results revealed that the estimation accuracy was improved when a physical condition variable was used. An average correspondence rate of 81 % was observed, with a maximum of 90 %. These results indicated that the data mining method could be effective in the estimation of blood glucose levels.