Microcontroller Implementation of Support Vector Machine for Detecting Blood Glucose Levels Using Breath Volatile Organic Compounds.

Matthew Boubin,Sudhir Shrestha

doi:10.3390/s19102283

Matthew Boubin, Sudhir Shrestha

Open Access

https://doi.org/10.3390/s19102283

Copy DOI

Abstract

This paper presents an embedded system-based solution for sensor arrays to estimate blood glucose levels from volatile organic compounds (VOCs) in a patient’s breath. Support vector machine (SVM) was trained on a general-purpose computer using an existing SVM library. A training model, optimized to achieve the most accurate results, was implemented in a microcontroller with an ATMega microprocessor. Training and testing was conducted using artificial breath that mimics known VOC footprints of high and low blood glucose levels. The embedded solution was able to correctly categorize the corresponding glucose levels of the artificial breath samples with 97.1% accuracy. The presented results make a significant contribution toward the development of a portable device for detecting blood glucose levels from a patient’s breath.

Highlights

In the United States, obesity, diabetes, cardiovascular diseases, and other metabolic disorders have been increasing in prevalence and severity at an extreme rate since the 1990s
With the prevalence of diabetes increasing at such an alarming rate, many new technologies are emerging to better monitor and manage blood glucose level
Published data on diabetes breath analysis were reviewed for volatile organic compounds (VOCs) linked to blood glucose levels and their correlated concentrations [20,21,22]

Summary

Introduction

In the United States, obesity, diabetes, cardiovascular diseases, and other metabolic disorders have been increasing in prevalence and severity at an extreme rate since the 1990s. With the prevalence of diabetes increasing at such an alarming rate, many new technologies are emerging to better monitor and manage blood glucose level. Recent research has focused on technologies such as meal detection [8], analysis of glucose in sweat [9], artificial pancreas technologies [10], and correlation between blood glucose levels and compounds present in breath [11,12]. Researchers used variations of electronic-nose technologies to quantify glucose and other compounds. Several examples of electronic-nose applications include respiratory illness diagnosis [13], detection of cancers [14,15], detection of fungal diseases in harvested blueberries [16], and the general detection of volatile organic compounds (VOCs) in human breath [12]. Refs [18,19] demonstrated the ability

Methods

Results

Conclusion