This project was dedicated to the problem of improving a non-invasive blood glucose monitor being developed by the VivaScan Corporation. The company has made some progress in the non-invasive blood glucose device development and approached WPI for a statistical assistance in the improvement of their model in order to predict the glucose level more accurately. The main goal of this project was to improve the ability of the non-invasive blood glucose monitor to predict the glucose values more precisely. The goal was achieved by finding and implementing the best regression model. The methods included ordinary least squared regression, partial least squares regression, robust regression method, weighted least squares regression, local regression, and ridge regression. VivaScan calibration data for seven patients were analyzed in this project. For each of these patients, the individual regression models were built and compared based on the two factors that evaluate the model prediction ability.
It was determined that partial least squares and ridge regressions are two best methods among the others that were considered in this work. Using these two methods gave better glucose prediction. The additional problem of data reduction to minimize the data collection time was also considered in this work.
According to the Center for Disease Control and Prevention (CDC), the number of Americans with diabetes more than doubled from 1989 to 2002 – from 5.8 million to 13.3 million. One in three Americans born after 2000 will develop diabetes in their lifetime [1]. People with diabetes have a shortage of insulin. This is a hormone that allows glucose, or sugar, to enter and be converted to energy. If left unchecked and uncontrolled, diabetes can lead to the serious conditions including heart attack, stroke, blindness, kidney failure, and blood vessel disease.
Despite these severe health problems, diabetes can be controlled and it can be managed. A recent 10-year study showed that diabetics who kept their blood glucose under control could reduce their risk or slow down the development of health complications that can happen from diabetes by 50 percent or more [2].
Monitoring blood glucose levels is a necessary daily procedure for people with diabetes. The results from these observations show the effectiveness of medications, diet, and life-style. Diabetics should regularly test and record their blood glucose. The results of self-blood-glucose-monitoring allow people with diabetes and their health care providers to effectively adjust their diabetes plan.
Download
Model-Based Calibration of A Non-Invasive Blood Glucose Monitor
