Glucose Monitoring System using Machine Learning

Bio-medical analysis is an indispensable procedure for identifying health-related diseases like diabetes. Monitoring the glucose level in our body regularly helps us identify hyperglycemia and hypoglycemia which can cause severe medical problems like nerve damage or kidney diseases. This paper outlines a technique for predicting the Glucose concentration in blood samples utilizing Image Processing and Machine Learning Algorithms. The glucose solution is prepared by the Glucose Oxidase (GOD) and Peroxidase (POD) method. Experimental database is generated based on colorimetric technique. The image of the glucose solution is captured by the raspberry pi camera and analyzed using Image Processing by extracting the RGB, HSV, LUX color space values. Regression algorithms like Multiple Linear Regression, Decision Tree, RandomForest, and XGBoost were used to predict the unknown glucose concentration. Since multiple linear regression yields the best results when compared to other models, with the highest accuracy of 96.56% for selected features and 89.73% for all features, it should be used to predict blood sample glucose levels. The image processing and machine learning based approach reduces the hardware complexities of the existing platforms.