Skip to content

  • Projects
  • Groups
  • Snippets
  • Help
    • Loading...
    • Help
    • Submit feedback
    • Contribute to GitLab
  • Sign in / Register
B
bloodvitals-spo25630
  • Project
    • Project
    • Details
    • Activity
    • Cycle Analytics
  • Issues 37
    • Issues 37
    • List
    • Boards
    • Labels
    • Milestones
  • Merge Requests 0
    • Merge Requests 0
  • CI / CD
    • CI / CD
    • Pipelines
    • Jobs
    • Schedules
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Members
    • Members
  • Collapse sidebar
  • Activity
  • Create a new issue
  • Jobs
  • Issue Boards
  • Cara Hartz
  • bloodvitals-spo25630
  • Issues
  • #1

Closed
Open
Opened Aug 11, 2025 by Cara Hartz@carahartz4941
  • Report abuse
  • New issue
Report abuse New issue

Development of A Noninvasive Blood Glucose Monitoring System Prototype: Pilot Study


Background: Diabetes mellitus is a severe disease characterized by excessive blood glucose levels ensuing from dysregulation of the hormone insulin. Diabetes is managed by way of physical activity and dietary modification and requires careful monitoring of blood glucose concentration. Blood glucose focus is often monitored throughout the day by analyzing a sample of blood drawn from a finger prick using a commercially obtainable glucometer. However, this process is invasive and painful, and results in a risk of infection. Therefore, there may be an urgent want for noninvasive, inexpensive, novel platforms for steady blood sugar monitoring. Objective: Our examine aimed to explain a pilot take a look at to test the accuracy of a noninvasive glucose monitoring prototype that makes use of laser know-how based on near-infrared spectroscopy. Methods: Our system is predicated on Raspberry Pi, a portable camera (Raspberry Pi camera), and a visible gentle laser. The Raspberry Pi digital camera captures a set of pictures when a visible mild laser passes by way of pores and BloodVitals SPO2 skin tissue. The glucose concentration is estimated by an artificial neural network mannequin utilizing the absorption and BloodVitals SPO2 scattering of gentle within the skin tissue.


This prototype was developed using TensorFlow, Keras, and Python code. A pilot study was run with eight volunteers that used the prototype on their fingers and ears. Blood glucose values obtained by the prototype had been in contrast with commercially out there glucometers to estimate accuracy. Results: When utilizing photos from the finger, the accuracy of the prototype is 79%. Taken from the ear, the accuracy is attenuated to 62%. Though the present information set is limited, these outcomes are encouraging. However, three essential limitations have to be addressed in future research of the prototype: (1) increase the size of the database to improve the robustness of the artificial neural community model; (2) analyze the impression of exterior components such as skin colour, pores and skin thickness, and ambient temperature in the current prototype; and (3) improve the prototype enclosure to make it appropriate for easy finger and ear placement. Conclusions: Our pilot examine demonstrates that blood glucose concentration could be estimated utilizing a small hardware prototype that uses infrared photos of human tissue.


Although more studies have to be conducted to overcome limitations, this pilot study exhibits that an inexpensive system can be utilized to avoid using blood and a number of finger pricks for blood glucose monitoring in the diabetic inhabitants. Successful management of diabetes includes monitoring blood glucose levels multiple occasions per day. This system determines glucose focus from a droplet of blood obtained from a finger prick or a laboratory blood draw. Therefore, noninvasive strategies are an attractive alternative, nonetheless, those who can be found in the present day have a number of limitations. Figure 1 illustrates an instance of each sort of noninvasive and minimally invasive blood glucose monitoring. These devices have the benefit of being each portable and cheap. Here, we describe the event of a novel noninvasive glucose monitoring system that makes use of the computing energy of sensors and Internet of Things devices to continuously analyze blood glucose from a microcomputer and a sensor embedded within a clip positioned on the finger or ear. The prototype makes use of infrared spectroscopy to create pictures of the rotational and vibrational transitions of chemical bonds within the glucose molecule, and incident gentle reflection to measure their corresponding fluctuation.


The photographs are transformed into an array listing, which is used to offer entries for an artificial neural community (ANN) to create an estimate of blood glucose focus. The prototype is straightforward to make use of and is paired with a cellular app totally free-living environments. Figure 2 shows an overview of the proposed system. I0 is the initial light depth (W/cm2), I is the depth of the ith at any depth within the absorption medium in W/cm2, l is the absorption depth within the medium in centimeters, e is the molar extinction coefficient in L/(mmol cm), BloodVitals SPO2 and c is the concentration of absorbing molecules in mmol/L. The product of and c is proportional to the absorption coefficient (µa). The concentration of absorbing molecules relies on the above equation. However, the effect of different blood parts and absorbing tissue components affects the amount of light absorbed. Then, to reduce the absorption on account of all the opposite parts, the wavelength of the sunshine supply must be chosen in order that the sunshine supply is highly absorbed by glucose and is usually clear to blood and tissue parts.


Although the Raspberry Pi camera captures pictures, a laser light captures absorption. A small clip that can be positioned on a finger or earlobe holds the laser on the top half and the camera on the underside. Figure three depicts the elements of the prototype (Raspberry Pi, camera, and laser mild). The prototype has been named GlucoCheck. The Raspberry Pi digicam captures one image each eight seconds over 2 minutes, for a complete of 15 photographs. Brightness and distinction levels are set to 70 cycles/degree, digicam ISO sensitivity is set to 800, and decision is ready to 640 × 480. Figures 4 and 5 present the prototype connected to the finger and ear, respectively. The supplies for the GlucoCheck prototype cost roughly US $79-$154 in 2022, relying on the availability of chips, which has been an ongoing difficulty in latest months. Typically, pc boards are ample, but 2022 noticed a scarcity of chips, leading to inflated prices compared to earlier years.

Assignee
Assign to
None
Milestone
None
Assign milestone
Time tracking
None
Due date
None
0
Labels
None
Assign labels
  • View project labels
Reference: carahartz4941/bloodvitals-spo25630#1