Volume 5, Issue 4 (Winter 2019)
jhbmi 2019, 5(4): 469-480 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Javid B, Fotouhi- Ghazvini F, Zakeri F S. Determining Blood Glucose Concentration using Near Infrared Spectroscopy: Early Findings. jhbmi 2019; 5 (4) :469-480
URL: http://jhbmi.ir/article-1-276-en.html
URL: http://jhbmi.ir/article-1-276-en.html
MSc in Information Technology Engineering, Computer Engineering and Information Technology Dept., University of Qom, Qom, Iran
Abstract: (6275 Views)
Introduction: Diabetes mellitus is one of the diseases that have grown dramatically in today's societies. People with diabetes should continuously measure their blood glucose level. Continuous blood glucose measurement by commonly used methods is painful and difficult. On the other hand, mobile phone can be a useful tool for accessing physicians and telemedicine services more easily. The aim of this study was to provide a medical care system for mobile monitoring of diabetes.
Method: This study is an applied study and the proposed system includes a non-invasive sensor for measuring blood glucose using the near-infrared spectroscopy and an Android application. To evaluate the system, experiments were performed on glucose solution and on the body. In these experiments, both the transmittance and the reflectance modes were examined.
Results: It was observed that with increasing glucose concentrations, the output voltage of sensor increased in the transmittance mode and decreased in reflectance mode. When testing on the body, the mean error rate was 34.14 in the transmittance mode and 35.9 in the reflectance mode. The results indicated that by combining transmittance and reflectance modes, better results were obtained. In this case, the mean percentage of error was 8.27 and RMSE was 52.18mg/dl.
Conclusion: Finally, it can be inferred that near-infrared spectroscopy can be used in the future as an alternative for invasive methods in measuring blood glucose levels. There is also the possibility of providing remote medical services to diabetics using mobile phones.
Method: This study is an applied study and the proposed system includes a non-invasive sensor for measuring blood glucose using the near-infrared spectroscopy and an Android application. To evaluate the system, experiments were performed on glucose solution and on the body. In these experiments, both the transmittance and the reflectance modes were examined.
Results: It was observed that with increasing glucose concentrations, the output voltage of sensor increased in the transmittance mode and decreased in reflectance mode. When testing on the body, the mean error rate was 34.14 in the transmittance mode and 35.9 in the reflectance mode. The results indicated that by combining transmittance and reflectance modes, better results were obtained. In this case, the mean percentage of error was 8.27 and RMSE was 52.18mg/dl.
Conclusion: Finally, it can be inferred that near-infrared spectroscopy can be used in the future as an alternative for invasive methods in measuring blood glucose levels. There is also the possibility of providing remote medical services to diabetics using mobile phones.
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
