Ideal Laser Wavelengths for Non-Invasive Glucometers
Disciplines
Artificial Intelligence and Robotics | Bioimaging and Biomedical Optics | Bioinformatics | Graphics and Human Computer Interfaces
Abstract (300 words maximum)
Diabetes and metabolic diseases are some of the most crucial health issues of the 21st century. Monitoring blood glucose, the lead indicator of these diseases, is a cumbersome process of constantly drawing blood or using subcutaneous needles. However, new technologies have emerged for non-invasive blood glucose monitoring that use spectroscopy, which involves emitting light and capturing patient data with cameras. These new devices remove the cost of multiple tests, reduce the risk of skin conditions, and create more patient-friendly solutions.
However, the hardware variables of these devices have not been tested thoroughly. One such avenue is via laser wavelength, which affects the data collected and used by these devices. Different wavelengths interact with skin in varying ways, shown by several previous studies. This study aims to investigate the impact of wavelength on performance of the team's non-invasive device across different races, genders, and ages of people. The tested model is to use our previous device with multiple lasers (ranging from 650nm-980nm), an HD camera, and a refactored finger-shroud.
Every test with a patient will utilize each of the varying wavelengths of lasers. The wavelengths will be compared to each other in accuracy of the glucose estimation model. Ultimately, we seek to improve our current GlucoCheck model through the comparisons of results and range of errors. A review of recent literature leads us to expect lower precision and accuracy in lower wavelengths, with higher precision and accuracy in higher wavelengths. Finally, we plan to publish our findings in Biosensors, a journal by MDPI, and present them at the National Conference of Undergraduate Research.
Academic department under which the project should be listed
CCSE - Information Technology
Primary Investigator (PI) Name
Maria Valero
Ideal Laser Wavelengths for Non-Invasive Glucometers
Diabetes and metabolic diseases are some of the most crucial health issues of the 21st century. Monitoring blood glucose, the lead indicator of these diseases, is a cumbersome process of constantly drawing blood or using subcutaneous needles. However, new technologies have emerged for non-invasive blood glucose monitoring that use spectroscopy, which involves emitting light and capturing patient data with cameras. These new devices remove the cost of multiple tests, reduce the risk of skin conditions, and create more patient-friendly solutions.
However, the hardware variables of these devices have not been tested thoroughly. One such avenue is via laser wavelength, which affects the data collected and used by these devices. Different wavelengths interact with skin in varying ways, shown by several previous studies. This study aims to investigate the impact of wavelength on performance of the team's non-invasive device across different races, genders, and ages of people. The tested model is to use our previous device with multiple lasers (ranging from 650nm-980nm), an HD camera, and a refactored finger-shroud.
Every test with a patient will utilize each of the varying wavelengths of lasers. The wavelengths will be compared to each other in accuracy of the glucose estimation model. Ultimately, we seek to improve our current GlucoCheck model through the comparisons of results and range of errors. A review of recent literature leads us to expect lower precision and accuracy in lower wavelengths, with higher precision and accuracy in higher wavelengths. Finally, we plan to publish our findings in Biosensors, a journal by MDPI, and present them at the National Conference of Undergraduate Research.