Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Diabetes Mellitus: Type 2 and Gestational01:22

Diabetes Mellitus: Type 2 and Gestational

3.6K
Type 2 diabetes, characterized by insulin resistance, arises when the insulin receptors on cells lose responsiveness to insulin, diminishing the cell's capacity to take up glucose, resulting in elevated blood glucose levels. To receive a diagnosis of Type 2 diabetes, a series of blood glucose tests are necessary to assess whether the blood glucose falls within normal parameters. If the result is out of the normal range, a patient may be diagnosed as prediabetic or diabetic, depending on the...
3.6K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

An Unmanned Surface Vehicle (USV): Development of an Autonomous Boat with a Sensor Integration System for Bathymetric Surveys.

Sensors (Basel, Switzerland)·2023
Same author

Association Between Obesity and Cardiovascular Outcomes: Updated Evidence from Meta-analysis Studies.

Current cardiology reports·2020
Same author

Review of Non-invasive Glucose Sensing Techniques: Optical, Electrical and Breath Acetone.

Sensors (Basel, Switzerland)·2020
Same author

Enhanced Controllability of Fries Rearrangements Using High-Resolution 3D-Printed Metal Microreactor with Circular Channel.

Small (Weinheim an der Bergstrasse, Germany)·2019
Same author

The Conceptual Design of a Novel Workstation for Seizure Prediction Using Machine Learning With Potential eHealth Applications.

IEEE journal of translational engineering in health and medicine·2019
Same author

Early detection of metabolic dysregulation using water T<sub>2</sub> analysis of biobanked samples.

Diabetes, metabolic syndrome and obesity : targets and therapy·2018

Related Experiment Video

Updated: Oct 26, 2025

Non-Invasive Monitoring of Microvascular Oxygenation and Reactive Hyperemia using Hybrid, Near-Infrared Diffuse Optical Spectroscopy for Critical Care
14:28

Non-Invasive Monitoring of Microvascular Oxygenation and Reactive Hyperemia using Hybrid, Near-Infrared Diffuse Optical Spectroscopy for Critical Care

Published on: May 10, 2024

1.8K

Non-Invasive Glucose Monitoring Using Optical Sensor and Machine Learning Techniques for Diabetes Applications.

Maryamsadat Shokrekhodaei1, David P Cistola2, Robert C Roberts1

  • 1Electrical and Computer Engineering Department, The University of Texas at El Paso, El Paso, TX 79968 USA.

IEEE Access : Practical Innovations, Open Solutions
|August 2, 2021
PubMed
Summary

This study enhances non-invasive glucose monitoring accuracy using multi-wavelength optical sensing and machine learning. Classification models, particularly support vector machines, achieved 99% accuracy, paving the way for improved diabetes management.

Keywords:
Classificationdecision treediabetesk-nearest neighbormachine learningneural networknon-invasiveoptimizationspectroscopysupport vector machine

More Related Videos

Simple Continuous Glucose Monitoring in Freely Moving Mice
03:25

Simple Continuous Glucose Monitoring in Freely Moving Mice

Published on: February 24, 2023

6.5K
Real-Time Monitoring of Neurocritical Patients with Diffuse Optical Spectroscopies
07:12

Real-Time Monitoring of Neurocritical Patients with Diffuse Optical Spectroscopies

Published on: November 19, 2020

2.3K

Related Experiment Videos

Last Updated: Oct 26, 2025

Non-Invasive Monitoring of Microvascular Oxygenation and Reactive Hyperemia using Hybrid, Near-Infrared Diffuse Optical Spectroscopy for Critical Care
14:28

Non-Invasive Monitoring of Microvascular Oxygenation and Reactive Hyperemia using Hybrid, Near-Infrared Diffuse Optical Spectroscopy for Critical Care

Published on: May 10, 2024

1.8K
Simple Continuous Glucose Monitoring in Freely Moving Mice
03:25

Simple Continuous Glucose Monitoring in Freely Moving Mice

Published on: February 24, 2023

6.5K
Real-Time Monitoring of Neurocritical Patients with Diffuse Optical Spectroscopies
07:12

Real-Time Monitoring of Neurocritical Patients with Diffuse Optical Spectroscopies

Published on: November 19, 2020

2.3K

Area of Science:

  • Biomedical Engineering
  • Optical Sensing
  • Machine Learning in Healthcare

Background:

  • Diabetes affects over 451 million people globally, necessitating accurate non-invasive glucose monitoring.
  • Current non-invasive methods face challenges with physiological and experimental factors affecting accuracy.
  • Machine learning shows promise in significantly improving glucose prediction accuracy.

Purpose of the Study:

  • To enhance glucose detection sensitivity and selectivity using multi-wavelength light sources in aqueous solutions.
  • To investigate the potential of multi-wavelength measurements to compensate for inter- and intra-individual variations.
  • To evaluate machine learning models for accurate glucose prediction using optical sensor data.

Main Methods:

  • Transmission measurements using a custom optical sensor with 18 wavelengths (410-940 nm).
  • Analysis of correlation between glucose concentration and transmission intensity at specific wavelengths.
  • Investigation of five machine learning methods (regression and classification) for glucose prediction.

Main Results:

  • High correlation (0.98) observed between glucose concentration and transmission intensity at four specific wavelengths (485, 645, 860, 940 nm).
  • Classification models significantly outperformed regression models, with a support vector machine achieving a 99% F1-score.
  • Clarke error grid analysis indicated 99.75% of readings fell within clinically acceptable zones.

Conclusions:

  • Multi-wavelength optical sensing combined with machine learning, specifically support vector machines, offers a highly accurate approach for non-invasive glucose monitoring.
  • This method demonstrates potential for critical glucose diagnosis, especially in emergency situations.
  • The findings represent a significant advancement towards replacing traditional finger-prick glucose testing.