Non-Invasive Blood Glucose Estimation Using PPG Derivative Features and MFCCs with Random Forest
DOI:
https://doi.org/10.12928/irip.v8i2.16069Keywords:
APG, Diabetes, Fiducial Features, MFCCs, Non-invasiveAbstract
Conventional blood glucose measurement devices remain dominated by invasive methods that require direct contact with body tissues and cause patient discomfort, motivating the development of accurate and non-invasive blood glucose monitoring approaches. Therefore, blood glucose estimation has performed using Photoplethysmography (PPG) signals by exploiting the Velocity Photoplethysmogram (VPG) and the Acceleration Photoplethysmogram (APG) as derivative signals. PPG signals were acquired non-invasively from 58 participants using an optical MAX30102 sensor placed on the finger. Morphological fiducial features and Mel-Frequency Cepstral Coefficients (MFCCs) were extracted from PPG, VPG, and APG signals to capture temporal, morphological, and spectral characteristics related to peripheral hemodynamic changes. The extracted features were then used to model blood glucose levels using a Random Forest algorithm. The results showed that the combined use of PPG, VPG, and APG produced the best performance, achieving Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Relative Difference (MARD) values of 6.35 mg/dL, 9.74 mg/dL, and 6.07%, respectively. Clarke Error Grid Analysis (CEGA) showed that 97.44% of the predictions were located in Zone A and 2.56% in Zone B, indicating that all estimates were within clinically acceptable regions. The main scientific contribution of this study lies in integrating derivative PPG signals with fiducial and MFCC-based feature representations within a unified machine learning framework. These findings indicate that combining PPG, VPG, and APG provides a richer physiological representation than PPG alone and offers practical potential for the development of wearable-based, non-invasive blood glucose monitoring technology.
References
M. J. Hossain, M. Al‐Mamun, and M. R. Islam, “Diabetes mellitus, the fastest growing global public health concern: Early detection should be focused,” Heal. Sci. Reports, vol. 7, no. 3, Mar. 2024, doi: 10.1002/hsr2.2004.
International Diabetes Federation, Atlas Diabetes 2025, 11th ed. 2025. [Online]. Available: https://diabetesatlas.org/resources/idf-diabetes-atlas-2025/
International Diabetes Federation, “IDF global clinical practice recommendations for managing type 2 diabetes – 2025,” 2025. doi: 10.1016/j.diabres.2025.112152.
M. Farouk, A. S. A. El-Hameed, A. R. Eldamak, and D. N. Elsheakh, “Noninvasive blood glucose monitoring using a dual band microwave sensor with machine learning,” Sci. Rep., vol. 15, no. 1, p. 16271, May 2025, doi: 10.1038/s41598-025-94367-6.
N. Uluç et al., “Non-invasive measurements of blood glucose levels by time-gating mid-infrared optoacoustic signals,” Nat. Metab., vol. 6, no. 4, pp. 678–686, Mar. 2024, doi: 10.1038/s42255-024-01016-9.
Q. Gong et al., “Non-Invasive and Accurate Blood Glucose Detection Based on an Equivalent Bioimpedance Spectrum,” Appl. Sci., vol. 15, no. 3, p. 1266, Jan. 2025, doi: 10.3390/app15031266.
S.-E. Jian, Y.-L. Lo, Y.-T. Chuang, and S.-H. Kuo, “Using Machine learning to predict blood glucose level based on Photoplethysmography,” Measurement, vol. 253, p. 117421, Sep. 2025, doi: 10.1016/j.measurement.2025.117421.
E. Mejía-Mejía, J. Allen, K. Budidha, C. El-Hajj, P. A. Kyriacou, and P. H. Charlton, Photoplethysmography signal processing and synthesis. 2021. doi: 10.1016/B978-0-12-823374-0.00015-3.
Z. Nie, M. Rong, and K. Li, “Blood glucose prediction based on imagingphotoplethysmography in combination with Machine learning,” Biomed. Signal Process. Control, vol. 79, p. 104179, Jan. 2023, doi: 10.1016/j.bspc.2022.104179.
J. Chu, W.-T. Yang, W.-R. Lu, Y.-T. Chang, T.-H. Hsieh, and F.-L. Yang, “90% Accuracy for Photoplethysmography-Based Non-Invasive Blood Glucose Prediction by Deep Learning with Cohort Arrangement and Quarterly Measured HbA1c,” Sensors, vol. 21, no. 23, p. 7815, Nov. 2021, doi: 10.3390/s21237815.
G. Hammour and D. P. Mandic, “An In-Ear PPG-Based Blood Glucose Monitor: A Proof-of-Concept Study,” Sensors, vol. 23, no. 6, p. 3319, Mar. 2023, doi: 10.3390/s23063319.
S. Alghlayini, M. A. Al-Betar, and M. Atef, “Enhancing Non-Invasive Blood Glucose Prediction from Photoplethysmography Signals via Heart Rate Variability-Based Features Selection Using Metaheuristic Algorithms,” Algorithms, vol. 18, no. 2, p. 95, Feb. 2025, doi: 10.3390/a18020095.
S. Sen Gupta, T.-H. Kwon, S. Hossain, and K.-D. Kim, “Towards non-invasive blood glucose measurement using machine learning: An all-purpose PPG system design,” Biomed. Signal Process. Control, vol. 68, p. 102706, Jul. 2021, doi: 10.1016/j.bspc.2021.102706.
J. Cheng, P. Xie, H. Zhao, and Z. Ji, “Differential Absorbance and PPG-Based Non-Invasive Blood Glucose Measurement Using Spatiotemporal Multimodal Fused LSTM Model,” Sensors, vol. 25, no. 17, p. 5260, Aug. 2025, doi: 10.3390/s25175260.
M. Zeynali, K. Alipour, B. Tarvirdizadeh, and M. Ghamari, “Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML,” Sci. Rep., vol. 15, no. 1, p. 581, Jan. 2025, doi: 10.1038/s41598-024-84265-8.
C. Salamea-Palacios, M. Montalvo-López, R. Orellana-Peralta, and J. Viñanzaca-Figueroa, “Photoplethysmography Feature Extraction for Non-Invasive Glucose Estimation by Means of MFCC and Machine Learning Techniques,” Biosensors, vol. 15, no. 7, p. 408, Jun. 2025, doi: 10.3390/bios15070408.
A. Zilgarayeva et al., “Optical sensor to improve the accuracy of non-invasive blood sugar monitoring,” Indones. J. Electr. Eng. Comput. Sci., vol. 34, no. 3, p. 1489, Jun. 2024, doi: 10.11591/ijeecs.v34.i3.pp1489-1498.
D. Di Filippo, F. Sunstrum, J. Khan, and A. Welsh, “Non-Invasive Glucose Sensing Technologies and Products: A Comprehensive Review for Researchers and Clinicians,” Sensors, vol. 23, no. 22, p. 9130, Nov. 2023, doi: 10.3390/s23229130.
I. Oshina and J. Spigulis, “Beer–Lambert law for optical tissue diagnostics: current state of the art and the main limitations,” J. Biomed. Opt., vol. 26, no. 10, Oct. 2021, doi: 10.1117/1.JBO.26.10.100901.
M. Elgendi, Y. Liang, and R. Ward, “Toward Generating More Diagnostic Features from Photoplethysmogram Waveforms,” Diseases, vol. 6, no. 1, p. 20, Mar. 2018, doi: 10.3390/diseases6010020.
S. Ali et al., “Development and Evaluation of a Sensor-Based Non-Invasive Blood Glucose Monitoring System Using Near-Infrared Spectroscopy,” in ICSEE 2024, Basel Switzerland: MDPI, Nov. 2024, p. 19. doi: 10.3390/ecsa-11-20395.
Y. Liang, M. Elgendi, Z. Chen, and R. Ward, “An optimal filter for short photoplethysmogram signals,” Sci. Data, vol. 5, no. 1, p. 180076, May 2018, doi: 10.1038/sdata.2018.76.
M.-S. Song and S.-B. Lee, “Interpretable machine learning for hypertension detection using photoplethysmography (PPG) signals and their derivatives,” Biomed. Signal Process. Control, vol. 113, p. 109194, Mar. 2026, doi: 10.1016/j.bspc.2025.109194.
G. A. Alonso-Silverio, V. Francisco-García, I. P. Guzmán-Guzmán, E. Ventura-Molina, and A. Alarcón-Paredes, “Toward Non-Invasive Estimation of Blood Glucose Concentration: A Comparative Performance,” Mathematics, vol. 9, no. 20, p. 2529, Oct. 2021, doi: 10.3390/math9202529.
X. Hu et al., “Blood pressure stratification using photoplethysmography and light gradient boosting machine,” Front. Physiol., vol. 14, Feb. 2023, doi: 10.3389/fphys.2023.1072273
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Ferdyan Rahmadani Adhi Pramudya, Muhammad Bagoes Anargiansyah, Bilqis Regita Pratiwi Fayensi, Moh Khikam Amrullah, Nisa'ul Fadhilah, Nainunis Mutawakkillah, Muhimmatul Khoiro
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish in IRiP agree to the following terms: Authors retain copyright and grant the IRiP right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share (copy and redistribute the material in any medium or format) and adapt (remix, transform, and build upon the material) the work for any purpose, even commercially with an acknowledgment of the work's authorship and initial publication in IRiP. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in IRiP. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
