A novel automated discontinuous venous blood monitoring system for ex vivo glucose determination in humans

intensive insulin therapy reduces mortality and morbidity in critically ill patients but imposes great demands on medical staff who must take frequent blood samples for the determination of glucose levels. A solution to this resourcing problem would be provided by an automated blood monitoring system. The aim of the present clinical study was to evaluate such a system comprising an automatic blood sampling unit linked to a glucose biosensor. Our approach was to determine the correlation and system error of the sampling unit alone and of the combined system with respect to reference levels over 12 h in humans. Two venous cannulae were inserted to connect the automatic and reference systems to the subjects. Blood samples were taken at 15 and 30 min intervals. The median Pearson coefficient of correlation between manually and automatically withdrawn blood samples was 0.982 for the sampling unit alone and 0.950 for the complete system. The biosensor had a linear range up to 20 mmol l(-1) and a 95% response, time of <2 min. Clark Error Grid analysis showed that 96.93% of the data (228 data pairs) was in zone A and 3.07% in zone B. Insulin Titration Error Grid analysis suggested an acceptable treatment in 99.56% of cases. Implementation of a "Keep Vein Open" saline infusion into the automated blood sampling system reduced blood withdrawal failures through occluded catheters fourfold. in summary, automated blood sampling from a peripheral vein coupled with automatic glucose determination is a promising alternative to frequent manual blood sampling. (C) 2008 Elsevier B.V. All rights reserved.