Estimation of HbA1c level among diabetic patients using second derivative of Photoplethysmography

Usman, Sahnius; Harun, Norhaslinda; Dziyauddin, Rudzidatul Akmam; Bani, Nurul Aini

doi:10.1109/scored.2017.8305415

Cited by 13 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…13with Eqs. (22) and (23) to calculate the ratio equations directly from the received light from the fingertip and obtain…”

Section: A Blood Vessel Modelmentioning

confidence: 99%

“…For the blood vessel model, we obtain the following equations by taking the wavelength ( ) values as 1 = 525 nm, 2 = 465 nm, and 3 = 615 nm and placing the parameter values from Table 1 into Eqs. (22)…”

Section: B Ratio Equations With Coefficient Valuesmentioning

confidence: 99%

“…The coefficients 1 to 12 are the values we get after solving Eqs. (22) and (23). The values of these coefficients are given in the results section (Section III-c) of this manuscript.…”

Section: A Blood Vessel Modelmentioning

confidence: 99%

“…One research discussed the estimation of in-vitro HbA1c 20 , but only focused on the PPG sensor design and did not cover non-invasive in-vivo estimation methods. And there are other conference papers, which also focuses on the classification of a person's diabetic status, but not estimation of glycated hemoglobin 21,22 . And another paper focuses on breath acetone-based HbA1c estimation 23 , but the error rate is very high.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Derivation and Validation of Gray-Box Models to Estimate Non-Invasive In-vivo Percentage Glycated Hemoglobin Using Digital Volume Pulse Waveform

Hossain

Gupta

Kwon

et al. 2020

Preprint

View full text Add to dashboard Cite

Glycated hemoglobin and blood oxygenation are the two most important factors for monitoring a patient’s oxygen levels in the blood and the amount of average blood glucose levels. Digital Volume Pulse acquisition is a convenient method, even for a person with no previous training or experience, can be utilized to estimate the two abovementioned physiological parameters. The physiological basis assumptions are utilized to develop two-finger models for estimating the percent glycated hemoglobin and blood oxygenation levels. The first model consists of a blood vessel only hypothesis, while the second model is based on a whole-finger model system. We validated our two gray-box systems on diabetic and non-diabetic patients and obtained the mean absolute errors for the percent glycated hemoglobin (%HbA1c) and percent oxygen saturation (%SpO2) of 0.375 and 1.676, respectively, for the blood vessel model and 0.271 and 1.395, respectively, for the whole-finger model. The precision analysis indicated that these models resulted in 2.08% and 1.74% mean %CV for %HbA1c and 0.54% and 0.49% mean %CV for %SpO2 in the respective models. Herein, both models exhibit close performances to each other (HbA1c estimation Pearson R values are 0.92 and 0.96, respectively), even though the model assumptions greatly differed between them. Both of the models have a very high potential to be used in real-world scenarios. The whole-finger model performs better in terms of higher precision and accuracy compared to the blood vessel model.

show abstract

“…13with Eqs. (22) and (23) to calculate the ratio equations directly from the received light from the fingertip and obtain…”

Section: A Blood Vessel Modelmentioning

confidence: 99%

Section: B Ratio Equations With Coefficient Valuesmentioning

confidence: 99%

“…The coefficients 1 to 12 are the values we get after solving Eqs. (22) and (23). The values of these coefficients are given in the results section (Section III-c) of this manuscript.…”

Section: A Blood Vessel Modelmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Derivation and Validation of Gray-Box Models to Estimate Non-Invasive In-vivo Percentage Glycated Hemoglobin Using Digital Volume Pulse Waveform

Hossain

Gupta

Kwon

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…At present, several types of research on PPG have been done which extracted information on other applications apart from heart rate estimation and the likes [2]. These include stenosis vessel analysis after hemodialysis process [9], blood-oxygenlevel measurement [10], blood flow analysis as indicator of blood pressure [11], blood volume changes [12], arterial condition analysis for diabetics [13], measurement of deviations in oxygen saturation [14], [15], [16] analysis of sleep staging phase [17], vital signs detection [18], heart rate measurement during bike activity [19], pulse volume estimation [20], blood pressure monitoring while sleeping [21], drowsiness assessment [22], blood flow estimation in the carotid artery [23], arterial oxygen saturation [24], to name some. All these involved PPG circuits being connected to body parts where information is desired and without any discomfort felt by the patient [25].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Photodetectors for the Photoplethysmographic Signal Detection of Hand Epidermal Layer

2020

IJATCSE

View full text Add to dashboard Cite

This study presents the potential of using photoplethysmography (PPG) as an alternative to the use of expensive spectroscopy or invasive skin biopsy to analyse skin conditions, particularly of the presence or absence of melanin in both dorsal and palmar skin of human subjects. This study seeks to analyse the sensing capabilities of three photodetectors (phototransistor, light dependent resistor, photodiode) vis-à-vis varying LED colors and quantities using backscatter radiation. Further, it intends to distinguish the best detector and LED color-quantity combination for the sensing of PPG signal in both dorsal and palmar skin of human volunteers. Photoplethysmography (PPG) is considered as a facile and cost effective optical process frequently used for monitoring heart rate. A light source or emitter and a light sensor or detector make up a PPG circuit. A light emitting diode (LED) is the frequently used light source while phototransistor, photodiode or light dependent resistor are the usual light sensors or detector employed. The simulation results revealed that four pieces of yellow LED and phototransistor detector are the best combination for applications involving the melanin in dorsal and palmar skin. The results further showeddirect proportionality relationship between reflected light and age.

show abstract

An explainable Artificial Intelligence software system for predicting diabetes

Srinivasu,

Ahmed,

Hassaballah

et al. 2024

Heliyon

View full text Add to dashboard Cite

Estimation of HbA1c level among diabetic patients using second derivative of Photoplethysmography

Cited by 13 publications

References 13 publications

Derivation and Validation of Gray-Box Models to Estimate Non-Invasive In-vivo Percentage Glycated Hemoglobin Using Digital Volume Pulse Waveform

Derivation and Validation of Gray-Box Models to Estimate Non-Invasive In-vivo Percentage Glycated Hemoglobin Using Digital Volume Pulse Waveform

Evaluation of Photodetectors for the Photoplethysmographic Signal Detection of Hand Epidermal Layer

An explainable Artificial Intelligence software system for predicting diabetes

Contact Info

Product

Resources

About