Accepted for/Published in: JMIR Formative Research
Date Submitted: Apr 12, 2022
Open Peer Review Period: Apr 11, 2022 - Apr 20, 2022
Date Accepted: Jul 9, 2022
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Non-Invasive Glucose Monitoring System for Diabetes Management using Internet of Things and Machine Learning
ABSTRACT
Background:
Diabetes Mellitus is a chronic disease that affects the human body by impairing it from producing, responding, or utilizing a hormone called insulin. This disease is commonly diagnosed in adults 40 to 65 years of age. Although there is no cure for Diabetes, it can be kept in check by maintaining a healthy lifestyle and monitoring the blood-glucose readings on a timely basis. The standard method for monitoring blood glucose is invasive, which involves needles, lancets, and blood samples that cause a lot of discomfort and stress.
Objective:
To reduce the use of invasive approaches for monitoring blood glucose, this paper proposes building and testing a non-invasive glucose monitoring prototype that does not require any blood sample and does not involve any kind of invasive procedure.
Methods:
Our system is based on inexpensive devices such as a Raspberry Pi (RPi), a portable camera (RPi camera), and a visible light laser. A set of pictures would be taken using the RPi camera when a visible light laser passes through the human tissue. By studying the absorption and analyzing how light is scattered along the human tissue using this image dataset, the glucose concentration can be estimated by an ANN (Artificial neural network) model. Our prototype was developed using TensorFlow, Keras, and Python code.
Results:
Preliminary results with limited data exhibit an accuracy of around 79% in blood glucose estimation, which is promising for more extensive experimentation.
Conclusions:
We conclude that is possible to estimate glucose concentration using images from the human tissue.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.