PhD Defense Notice - Noninvasive Glucose Detection Using Infrared Photoacoustic Spectroscopy and Machine Learning

Wednesday, December 6, 2023 9:00 am - 12:00 pm EST (GMT -05:00)

Candidate: Abdulrahman Aloraynan
Date: December 6, 2023
Time: 9:00 AM - 12:00 PM
Place: Remote Attendance
Supervisor(s): Ban, Dayan

Abstract:

The ideal method to monitor diabetes is to obtain the glucose level with a fast, accurate, and pain-free measurement that does not require blood drawing or finger pricking. Although the development of noninvasive devices for blood glucose measurement started three decades ago, no clinically proven devices were commercially released in the market. Among all the noninvasive glucose detection techniques, optical spectroscopy has rapidly advanced, including infrared (IR) and photoacoustic (PA) spectroscopy.

The combination of IR and PA spectroscopy has shown promising developments in recent years as a substitute for invasive glucose monitoring technology.  The IR region has a strong relationship with glucose due to the presence of glucose absorption peaks. PA spectroscopy utilizes the vibration modes of the glucose molecules in the IR region  and the weak water absorption  of  acoustic signals as an alternative  approach  to compensate for the optical losses in the IR transmission and absorbance spectroscopy. The concept of PA spectroscopy relies on generating acoustic waves by an electromagnetic source that are distinguishable from one material  to another  and can be detected  by  sensitive ultrasonic or piezoelectric sensors.

The first part of the thesis demonstrates the development of the IR and PA system for noninvasive glucose monitoring. The IR and PA system has been developed using a single wavelength quantum cascade laser (QCL), lasing at a glucose fingerprint of 1080 cm-1. In biomedical applications, phantoms are widely used as test models to substitute targeted body objects. Biomedical skin phantoms with similar properties to human skin have been prepared at different glucose concentrations of ±25 mg/ d L as test models for the setup. The system shows feasibility in detecting glucose using artificial skin phantoms, covering the normal and hyperglycemia blood glucose ranges. Machine learning classification models have been employed to enhance the prediction accuracy of glucose levels using unprocessed acoustic signals.

The second part of the thesis extends the development of the IR and PA system. A dual single-wavelength QCLs system has been developed using PA spectroscopy for noninvasive glucose monitoring. The glucose detection sensitivity of the IR and PA spectroscopy has improved to ±12.5 mg/ dL using dual QCLs lasing at 1080 & 970 cm-1. The artificial skin phantoms have been prepared with other blood components at different glucose concentrations. The dual QCLs system demonstrates sustainability in detecting glucose concentrations in the presence of albumin, sodium lactate, cholesterol, and urea. An ensemble classifier model has been developed to predict the glucose level of skin samples. The model has achieved 96.7% prediction  accuracy for samples with and without  blood components, with 100% of the predicted  data located in zones A and B of Clarke's error grid analysis.

After demonstrating the glucose detectability of the IR and PA system for the in vitro measurements, the system has progressed to the in vivo quantifying. The operating power of the QCLs has been lowered to fulfill the safety guidelines of using light sources on human skin. The blood glucose concentration can be potentially  measured  from the interstitial fluid (ISF) located underneath the skin in the epidermis layer. The glucose diffuses from the blood to the ISF layer, creating a significant opportunity for noninvasive monitoring systems. The in vivo measurements of the fiber-coupled dual QCLs and PA system have been assessed by oral glucose tolerance test (OGTT). The preliminary results from the In vivo measurements demonstrate that the MIR and PA system can detect glucose levels not only in the biological samples but also in real human skin. Finally, a Gaussian Process regression model has been developed to improve the prediction accuracy of the IR and PA system.