Multiple Regression Analysis Based Non-Invasive Blood Glucose Level Estimation Using Photoplethysmography

2021 ◽  
Author(s):  
Suvojit Kumar Singha ◽  
Mohiuddin Ahmad ◽  
Md. Rabiul Islam
Keyword(s):  
Regression Analysis ◽  
Blood Glucose ◽  
Blood Glucose Level ◽  
Multiple Regression Analysis ◽  
Multiple Regression ◽  
Glucose Level ◽  
Non Invasive

scholarly journals Comparison of Functional Regression and Functional Principal Component Regression for Estimating Non-Invasive Blood Glucose Level

2021 ◽  
Vol 5 (1) ◽  
pp. 14-25
Author(s):  
Nurul Fadhilah ◽  
Erfiani Erfiani ◽  
Indahwati Indahwati
Keyword(s):  
Blood Glucose ◽  
Blood Glucose Level ◽  
Glucose Level ◽  
Principal Component Regression ◽  
Principal Component ◽  
Functional Regression ◽  
Glucose Levels ◽  
Non Invasive ◽  
Blood Glucose Levels ◽  
Functional Principal Component

The calibration method is an alternative method that can be used to analyze the relationship between invasive and non-invasive blood glucose levels. Calibration modeling generally has a large dimension and contains multicolinearities because usually in functional data the number of independent variables (p) is greater than the number of observations (p>n). Both problems can be overcome using Functional Regression (FR) and Functional Principal Component Regression (FPCR). FPCR is based on Principal Component Analysis (PCA). In FPCR, the data is transformed using a polynomial basis before data reduction. This research tried to model the equations of spectral calibration of voltage value excreted by non-invasive blood glucose level monitoring devices to predict blood glucose using FR and FPCR. This study aimed to determine the best calibration model for measuring non-invasive blood glucose levels with the FR and FPCR. The results of this research showed that the FR model had a bigger coefficient determination (R2) value and lower Root Mean Square Error (RMSE) and Root Mean Square Error Prediction (RMSEP) value than the FPCR model, which was 12.9%, 5.417, and 5.727 respectively. Overall, the calibration modeling with the FR model is the best model for estimate blood glucose level compared to the FPCR model.

scholarly journals Association between neutrophil to lymphocyte ratio and blood glucose level at admission in patients with spontaneous intracerebral hemorrhage

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Fan Zhang ◽  
Yanming Ren ◽  
Wei Fu ◽  
Yuelong Wang ◽  
Juan Qian ◽  
...  
Keyword(s):  
Regression Analysis ◽  
Blood Glucose ◽  
Intracerebral Hemorrhage ◽  
Blood Glucose Level ◽  
Glucose Level ◽  
Inflammatory Responses ◽  
Neutrophil To Lymphocyte Ratio ◽  
Secondary Brain Injury ◽  
Imaging Features ◽  
Lymphocyte Ratio

Abstract Previous studies indicated that both inflammatory responses and hyperglycemia are involved in the similar pathophysiological mechanisms after onset of intracerebral hemorrhage (ICH). However the relationship between hyperglycemia and inflammation remains unknown. We aim to evaluate the associations of hyperglycemia with inflammation and neutrophil to lymphocyte ratio (NLR) in patients with ICH. Patients with acute ICH were retrospectively enrolled. Clinical characteristics and imaging features were obtained. The associations between outcome and laboratory biomarkers were assessed by multivariable logistic regression analysis. Spearman analysis and multiple linear regression analysis were performed to estimate the association of NLR and serum glucose. 175 patients were enrolled. Poor outcome occurred in 86 patients at 30 days. Elevated blood glucose level (BGL) and NLR were strongly associated with outcome in patients with ICH. Moreover, combined NLR-BGL exhibited a better predictive accuracy compared with the peripheral leukocyte counts. Furthermore, there was a robust association between BGL and NLR. We first demonstrated both of NLR and BGL were independently associated with each other. Our results indicate that inflammatory responses and the pathological process of hyperglycemia may influence each other by several complex pathological mechanisms and have a mutual promoting effect to secondary brain injury.

scholarly journals Biochemical markers in saliva of patients with diabetes mellitus

2012 ◽  
Vol 59 (4) ◽  
pp. 198-204 ◽  
Author(s):  
Biljana Andjelski-Radicevic ◽  
Radica Dozic ◽  
Tatjana Todorovic ◽  
Ivan Dozic
Keyword(s):  
Diabetes Mellitus ◽  
Blood Glucose ◽  
Blood Glucose Level ◽  
Glucose Level ◽  
Diabetic Patients ◽  
Non Invasive ◽  
Stress Markers ◽  
Frequent Monitoring ◽  
Patients With Diabetes ◽  
Protein Components

Diabetes mellitus is metabolic syndrome characterized by disorder in metabolism of carbon hydrates, lipids and proteins. The diagnosis of diabetes is established by measuring the blood glucose level using standardized methods. Frequent monitoring of blood glucose level could be inconvenient for patients because of possible pain during blood sample taking. In the last few years biological materials with non invasive sampling, like saliva, have been analyzed. Research has confirmed that some organic and inorganic components of saliva are modified in diabetic patients (glucose, lipid and protein components, oxidative stress markers, electrolytes). Beside other markers, the analysis of glucose in saliva is an attempt to find a non-invasive and painless way for frequent monitoring of glucose concentration in diabetic patients. Collecting saliva is simple and economical, it neither requires expensive equipment nor specially trained staff. Saliva can be taken many times and in unlimited quantity. In regards to the data about the possibilities for using saliva as biological sample in monitoring diabetes mellitus, which could be alternative to blood serum or plasma, the conclusion is that saliva becomes more important in this context.

PARAMETRIC AND NON-PARAMETRIC REGRESSION APPROACHES FOR NON-INVASIVE BLOOD GLUCOSE MONITORING

2020 ◽  
Vol 32 (06) ◽  
pp. 2050043
Author(s):  
Keshava N. Acharya ◽  
M. G. Yashwanth Gowda ◽  
M. Vijay ◽  
S. Deepthi ◽  
S. Malathi ◽  
...  
Keyword(s):  
Health Care ◽  
Blood Glucose ◽  
Blood Glucose Level ◽  
Glucose Level ◽  
Glucose Monitoring ◽  
Sensor Data ◽  
Blood Glucose Monitoring ◽  
Self Monitoring ◽  
Non Invasive ◽  
Non Parametric

Blood glucose monitoring systems (BGMSs) play a crucial role in health care applications. Invasive measurements are more accurate while non-invasive BGMS encourage self monitoring and reduce the cost of health care. Though multiple sensor data acquisition and suitable processing improve accuracy, self-monitoring becomes difficult in such non-invasive systems due to multiple signal acquisition. This paper investigates a non-invasive BGMS prototype that renders accurate measurements by statistically processing a single sensor data. The developed prototype is based on near-infrared (NIR) spectroscopy, which provides an electronic voltage that gets mapped to corresponding blood glucose level. This mapping is proposed using two different statistical regression approaches, parametric Bayesian Regression (BR) approach and the non-parametric Gaussian Process Regression (GPR) approach. Dataset is acquired from 33 subjects who visited Ramaiah Medical College Hospital, India. On each subject, voltage from the BGMS prototype and corresponding invasively obtained blood glucose level have been recorded. The BR and GPR approaches are trained with 75% of the data while the remaining 25% is used for testing. Test results show that BR approach renders root mean square error (RMSE) of 3.7[Formula: see text]mg/dL, while the mean absolute percentage error (MAPE) is around 2.5. The GPR with different radial basis function kernels revealed that a multiquadric kernel provides a lowest RMSE of 3.28[Formula: see text]mg/dL and lowest MAPE of 2.2, thus outperforming the parametric BR approach. Investigations also show that for a training data of less than 15 entries, BR renders better accuracy than the GPR approach.

Sign in / Sign up

Export Citation Format

Share Document