Non-Invasive Blood Sugar Measuring Tool Using Arduino-Based Linear Regression Method

Abstract

Diabetes Mellitus is a disease characterized by high blood sugar levels caused by decreased production or function of the hormone insulin in the body. Traditional tests are usually invasive, involving skin puncture to obtain a blood sample, which can be unsuitable for some sufferers. Non-invasive methods provide a viable alternative for monitoring blood sugar levels. This research aims to create an Arduino-based non-invasive blood sugar level measuring device, leveraging the optical property of laser absorption in liquid media, detected by a photodiode sensor. The primary objective is to develop a device that accurately measures blood sugar levels without the need for invasive procedures. The photodiode sensor outputs voltage, which is then converted into blood sugar level (mg/dl) using a linear regression equation. The derived linear regression equation is y = 31.401 + 36.002x, with a previously obtained correlation value of 0.971 between voltage and blood sugar levels at a significance level of 0.01. The average error value (errata) of this device is 0.0905. The smallest measurement error was observed in patients C and Q, at 0.01 or approximately 1%, while the largest error was in patient L, at 0.22 or around 22%. The contributions of this research include the development of a non-invasive, accurate, and cost-effective method for blood sugar monitoring, potentially improving patient compliance and comfort.