Non-Invasive Blood Glucose Monitoring using a Hybrid Technique

Nanayakkara, Nuwan D.; Munasingha, Shashika Chamod; Ruwanpathirana, G P

doi:10.1109/mercon.2018.8421885

Cited by 12 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the early stopping method avoided over-training of the model. In comparison with [12,13,[15][16][17]21,[25][26][27], which served as the standard for predicting blood glucose, the proposed blood glucose estimation system had an MSE, RMSE, MAE, MARD, and R 2 of 40.736, 6.3824, 5.0896, 4.4321, and 0.997, respectively, all of which fell within region A of the Clarke EGA.…”

Section: Analyses and Discussion Of Network Experiments Resultsmentioning

confidence: 99%

“…Nanayakkara et al measured bioelectrical impedance through 940 nm infrared light and a frequency of 3 to 100 kHz and compared the obtained features with least squares regression and neural network algorithms. The results revealed that the least squares regression was the superior algorithm and that the combination of infrared light and bioelectrical impedance yielded improved accuracy [16]. Pathirage et al obtained a multiwavelength near-infrared light spectrum from multi-wavelength infrared light and extracted the features of bioelectrical impedance every 0.5 kHz from 50 to 100 kHz.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Non-Invasive Blood Glucose Estimation System Based on a Neural Network with Dual-Wavelength Photoplethysmography and Bioelectrical Impedance Measuring

Yen

Chen

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

This study proposed a noninvasive blood glucose estimation system based on dual-wavelength photoplethysmography (PPG) and bioelectrical impedance measuring technology that can avoid the discomfort created by conventional invasive blood glucose measurement methods while accurately estimating blood glucose. The measured PPG signals are converted into mean, variance, skewness, kurtosis, standard deviation, and information entropy. The data obtained by bioelectrical impedance measuring consist of the real part, imaginary part, phase, and amplitude size of 11 types of frequencies, which are converted into features through principal component analyses. After combining the input of seven physiological features, the blood glucose value is finally obtained as the input of the back-propagation neural network (BPNN). To confirm the robustness of the system operation, this study collected data from 40 volunteers and established a database. From the experimental results, the system has a mean squared error of 40.736, a root mean squared error of 6.3824, a mean absolute error of 5.0896, a mean absolute relative difference of 4.4321%, and a coefficient of determination (R Squared, R2) of 0.997, all of which fall within the clinically accurate region A in the Clarke error grid analyses.

show abstract

Section: Analyses and Discussion Of Network Experiments Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Non-Invasive Blood Glucose Estimation System Based on a Neural Network with Dual-Wavelength Photoplethysmography and Bioelectrical Impedance Measuring

Yen

Chen

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Another study demonstrated a wearable prototype system for non-invasive glucose monitoring based on bioimpedance measurement and showed that certain parameters of bioimpedance were sensitive to changes in blood glucose levels ( Liu et al, 2016 ). Another study proposed a hybrid technique that combined bioimpedance with near-infrared measurements to monitor glucose ( Nanayakkara et al, 2018 ). Using machine learning (i.e., regression), the combination of the two measurements achieved better results based on Clarke’s error grid (i.e., 90% points in region A) when compared to the reference blood glucose.…”

Section: Non-invasive Sensors and Wearablesmentioning

confidence: 99%

Sense and Learn: Recent Advances in Wearable Sensing and Machine Learning for Blood Glucose Monitoring and Trend-Detection

Alhaddad

Aly

Gad

et al. 2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Diabetes mellitus is characterized by elevated blood glucose levels, however patients with diabetes may also develop hypoglycemia due to treatment. There is an increasing demand for non-invasive blood glucose monitoring and trends detection amongst people with diabetes and healthy individuals, especially athletes. Wearable devices and non-invasive sensors for blood glucose monitoring have witnessed considerable advances. This review is an update on recent contributions utilizing novel sensing technologies over the past five years which include electrocardiogram, electromagnetic, bioimpedance, photoplethysmography, and acceleration measures as well as bodily fluid glucose sensors to monitor glucose and trend detection. We also review methods that use machine learning algorithms to predict blood glucose trends, especially for high risk events such as hypoglycemia. Convolutional and recurrent neural networks, support vector machines, and decision trees are examples of such machine learning algorithms. Finally, we address the key limitations and challenges of these studies and provide recommendations for future work.

show abstract

“…In the literature, a novel approach has been proposed for the non-invasive measurement of blood glucose levels [18], using a hybrid technique that combines NIR absorption and bio-impedance measurement. The preliminary results of this hybrid technique have been described.…”

Section: -3-hybrid Techniquementioning

confidence: 99%

Acoustic Photometry of Biomedical Parameters for Association with Diabetes and Covid-19

et al. 2022

View full text Add to dashboard Cite

Because of their mortality rate, diabetes and COVID-19 are serious diseases. Moreover, people with diabetes are at a higher risk of developing COVID-19 complications. This article therefore proposes a single, non-invasive system that can help people with diabetes and COVID-19 to monitor their health parameters by measuring oxygen saturation (SPO2), heart rate, and body temperature. This is in contrast to other pulse oximeters and previous work reported in the literature. A Max30102 sensor, consisting of two light-emitting diodes (LEDs), can serve as a transmission spectrum to enable three synchronous parameter measurements. Hence, the Max30102 sensor facilitates identification of the relationship between COVID-19 and diabetes in a cost-effective manner. Fifty subjects (20 healthy, 20 diabetic, and 10 with COVID-19), aged 18-61 years, were recruited to provide data on heart rate, body temperature, and oxygen saturation, measured in a variety of activities and scenarios. The results showed accuracy of ±97% for heart rate, ±98% for body temperature, and ±99% for oxygen saturation with an enhanced time efficiency of 5-7 seconds in contrast to a commercialized pulse oximeter, which took 10-12 seconds. The results were then compared with those of commercially available pulse oximetry (Oxitech Pulse Oximeter) and a thermometer (Medisana Infrared Thermometer). These results revealed that uncontrolled diabetes can be as dangerous as COVID-19 in terms of high resting heart rate and low oxygen saturation. Doi: 10.28991/esj-2022-SPER-04 Full Text: PDF

show abstract

Non-Invasive Blood Glucose Monitoring using a Hybrid Technique

Cited by 12 publications

References 7 publications

Non-Invasive Blood Glucose Estimation System Based on a Neural Network with Dual-Wavelength Photoplethysmography and Bioelectrical Impedance Measuring

Non-Invasive Blood Glucose Estimation System Based on a Neural Network with Dual-Wavelength Photoplethysmography and Bioelectrical Impedance Measuring

Sense and Learn: Recent Advances in Wearable Sensing and Machine Learning for Blood Glucose Monitoring and Trend-Detection

Acoustic Photometry of Biomedical Parameters for Association with Diabetes and Covid-19

Contact Info

Product

Resources

About