Intelligent estimation of blood glucose level using wristband PPG signal and physiological parameters

Prabha, Anju; Yadav, Jyoti; Rani, Asha; Singh, Vijander

doi:10.1016/j.bspc.2022.103876

Cited by 16 publications

(7 citation statements)

References 103 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gupta et al [18] applied classical machine learning-based regression techniques on features extracted from transmissive and reflective PPG signals from three frequency bands (green, red and infrared (IR)) to estimate BGL. Prabha et al [19] tried to estimate BGL from PPG signals collected from wearable wristbands using classical ML techniques. Riaz et al [20] tried to extract some features from PPG signals and link them to corresponding glucose readings.…”

Section: Introductionmentioning

confidence: 99%

QU-GM: An IoT Based Glucose Monitoring System From Photoplethysmography, Blood Pressure, and Demographic Data Using Machine Learning

Nazmul Islam Shuzan,

Hossain Chowdhury,

Chowdhury

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Patients with hyperglycemia require routine glucose monitoring to effectively treat their condition. We have developed a lightweight wristband device to capture Photoplethysmography (PPG) signals. We collected PPG signals, demographic information, and blood pressure data from 139 diabetic (49.65%) and non-diabetic (50.35%) subjects. Blood glucose was estimated, and diabetic severity (normal, warning, and dangerous) was stratified using Mel frequency cepstral coefficients, time, frequency, and statistical features from PPG and their derivative signals along with physiological parameters. Bagged Ensemble Trees outperform other algorithms in estimating blood glucose level with a correlation coefficient of 0.90. The proposed model's prediction was all in Zone A and B in the Clarke Error Grid analysis. The predictions are thus clinically acceptable. Furthermore, K-nearest neighbor model classified the severity levels with an accuracy of 98.12%. Furthermore, the proposed models were deployed in Amazon Web Server. The wristband is connected to an Android mobile application to collect real-time data and update the estimated glucose and diabetic severity every 10-seconds, which will allow the users to gain better control of their diabetic health.

show abstract

Section: Introductionmentioning

confidence: 99%

QU-GM: An IoT Based Glucose Monitoring System From Photoplethysmography, Blood Pressure, and Demographic Data Using Machine Learning

Nazmul Islam Shuzan,

Hossain Chowdhury,

Chowdhury

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In this study, we focused on noninvasively estimating blood glucose levels by using wrist PPG signals and applying empirical mode decomposition (EMD)-based machine learning algorithms. Algorithms such as random forest (RF), XGBoost, CatBoost, and LightGBM [8][9][10][11] have been applied to prediction models with the goal of achieving accurate glucose level estimation from PPG signals and diabetes datasets. However, some PPG-based estimations include external features such as BMI, SpO 2 , age, and other relevant factors to improve the accuracy of predictions.…”

Section: Introductionmentioning

confidence: 99%

EMD-Based Noninvasive Blood Glucose Estimation from PPG Signals Using Machine Learning Algorithms

Satter,

Turja,

Kwon

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Effective management of diabetes requires accurate monitoring of blood glucose levels. Traditional invasive methods for such monitoring can be cumbersome and uncomfortable for patients. In this study, we introduce a noninvasive approach to estimate blood glucose levels using photoplethysmography (PPG) signals. We have focused on blood glucose prediction using wrist PPG signals and explored various PPG waveform-based features, including AC to DC ratio (AC/DC) and intrinsic mode function (IMF)-based features derived from empirical mode decomposition (EMD). To the best of our knowledge, no studies have been found using EMD-based features to estimate blood glucose levels noninvasively. Additionally, feature importance-based selection has also been used to further improve the accuracy of the proposed model. Among the four machine learning algorithms considered in this study, CatBoost consistently outperformed XGBoost, LightGBM, and random forest across a wide number of features. The best performing model, CatBoost, achieved Pearson’s r of 0.96, MSE 0.08, R2 score 0.92, and MAE 8.01 when considering the top 50 features selected from both PPG waveform-based features and IMF-based features. The p-values for all models were <0.001, indicating statistically significant correlations. Overall, this study provides valuable insights into the feasibility and effectiveness of noninvasive blood glucose monitoring using advanced machine learning techniques.

show abstract

“…The correlation coefficient between the results and the standard method was 0.99. It showed that the predicted glucose value was clinically usable [ 21 ]. A similar smartphone, combined with PPG under the calculation of artificial intelligence, was used to estimate the heart rate (HR) using PPG in fingertip video captured by the smartphone camera.…”

Section: Introductionmentioning

confidence: 99%

Reflex Auriculo-Cardiac (RAC) Induced by Auricular Laser and Needle Acupuncture: New Case Results Using a Smartphone

Chen

Lan

Hou

et al. 2023

Life

View full text Add to dashboard Cite

The reflex auriculo-cardiac (RAC), dynamic pulse reaction (Nogier reflex), or vascular autonomic signal was proposed by Nogier. It refers to the pulse changes that can occur in the radial artery immediately after auricular acupuncture is performed. RAC is helpful for the clinical practice of auricular acupuncture, but there is a lack of objective verification methods. Photoplethysmography (PPG) has been used to objectively calculate radial artery blood flow. This study used PPG via a smartphone to measure RAC induced by auricular acupuncture. Thirty subjects without major diseases were recruited to receive traditional needle and laser acupuncture. The Shen Men ear point and control points were stimulated for 20 s. PPG was continuously measured during the acupuncture. The PPG data were tested for differences with a paired t-test. The results showed that there were no statistical differences in the frequency and amplitude of PPG obtained before and after acupuncture, either with a traditional needle or laser acupuncture. However, interestingly, it was found that one patient with insomnia, one patient with viral respiratory symptoms, and two menstruating females exhibited changes in PPG within five seconds of needle placement. We hypothesized that RAC might be induced by auricular acupuncture and could be quantified by PPG, even among subjects suffering from mild diseases; however, auricular acupuncture might not induce a measurable RAC in totally healthy subjects.

show abstract

Intelligent estimation of blood glucose level using wristband PPG signal and physiological parameters

Cited by 16 publications

References 103 publications

QU-GM: An IoT Based Glucose Monitoring System From Photoplethysmography, Blood Pressure, and Demographic Data Using Machine Learning

QU-GM: An IoT Based Glucose Monitoring System From Photoplethysmography, Blood Pressure, and Demographic Data Using Machine Learning

EMD-Based Noninvasive Blood Glucose Estimation from PPG Signals Using Machine Learning Algorithms

Reflex Auriculo-Cardiac (RAC) Induced by Auricular Laser and Needle Acupuncture: New Case Results Using a Smartphone

Contact Info

Product

Resources

About