Abstract
Diabetes and metabolic diseases are considered a silent epidemic in the United States. Monitoring blood glucose, the lead indicator of these diseases, involves either a cumbersome process of extracting blood several times per day or implanting needles under the skin. However, new technologies have emerged for non-invasive blood glucose monitoring, including light absorption and spectroscopy methods. In this paper, we performed a comparative study of diverse Machine Learning (ML) methods on spectroscopy images to estimate blood glucose concentration. We used a database of fingertip images from 45 human subjects and trained several ML methods based on image tensors, color intensity, and statistical image information. We determined that for spectroscopy images, AdaBoost trained with KNeigbors is the best model to estimate blood glucose with a percentage of 90.78% of results in zone “A” (accurate) and 9.22% in zone “B” (clinically acceptable) according to the Clarke Error Grid metric.
Supported by College of Computing and Software Engineering and Office of Research at Kennesaw State University.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sklearn.ensemble.adaboostregressor. https://scikit-learn.org
Alarcón-Paredes, A., Francisco-García, V., Guzmán-Guzmán, I.P., Cantillo-Negrete, J., Cuevas-Valencia, R.E., Alonso-Silverio, G.A.: An IoT-based non-invasive glucose level monitoring system using Raspberry Pi. Appl. Sci. 9(15), 3046 (2019). https://www.mdpi.com/2076-3417/9/15/3046/htm
Albawi, S., Mohammed, T.A., Al-Zawi, S.: Understanding of a convolutional neural network. In: 2017 International Conference on Engineering and Technology (ICET), pp. 1–6. IEEE (2017)
Amir, O., et al.: Continuous noninvasive glucose monitoring technology based on “occlusion spectroscopy” (2007)
Brownlee, J.: Histogram-based gradient boosting ensembles in Python (2021). https://machinelearningmastery.com/
Brownlee, J.: XGBoost for regression (2021). https://machinelearningmastery.com/xgboost-for-regression/
Centers for Disease Control and Prevention (CDC): National Diabetes Statistics Report website (2018). https://www.cdc.gov/diabetes/data/statistics-report/index.html. Accessed 2022
Clarke, W.L., Cox, D., Gonder-Frederick, L.A., Carter, W., Pohl, S.L.: Evaluating clinical accuracy of systems for self-monitoring of blood glucose (1987). https://doi.org/10.2337/diacare.10.5.622
Donges, N.: Random forest algorithm: a complete guide. https://builtin.com/data-science/random-forest-algorithm
Enejder, A.M., et al.: Raman spectroscopy for noninvasive glucose measurements. J. Biomed. Opt. 10(3), 031114 (2005)
Haxha, S., Jhoja, J.: Optical based noninvasive glucose monitoring sensor prototype. IEEE Photonics J. 8(6), 1–11 (2016)
Hull, E.L., et al.: Noninvasive skin fluorescence spectroscopy for detection of abnormal glucose tolerance. J. Clin. Transl. Endocrinol. 1(3), 92–99 (2014)
Kasahara, R., Kino, S., Soyama, S., Matsuura, Y.: Noninvasive glucose monitoring using mid-infrared absorption spectroscopy based on a few wavenumbers. Biomed. Opt. Express 9(1), 289–302 (2018)
Kramer, O.: K-nearest neighbors. In: Kramer, O. (ed.) Dimensionality Reduction with Unsupervised Nearest Neighbors, pp. 13–23. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38652-7_2
Maruo, K., et al.: Noninvasive blood glucose assay using a newly developed near-infrared system. IEEE J. Sel. Top. Quantum Electron. 9(2), 322–330 (2003)
Moore, J.X., Chaudhary, N., Akinyemiju, T.: Peer reviewed: metabolic syndrome prevalence by race/ethnicity and sex in the United States, National Health and Nutrition Examination Survey, 1988–2012. Preventing Chronic Dis. 14 (2017)
Noble, W.S.: What is a support vector machine? Nat. Biotechnol. 24(12), 1565–1567 (2006)
Pai, P.P., Sanki, P.K., Sahoo, S.K., De, A., Bhattacharya, S., Banerjee, S.: Cloud computing-based non-invasive glucose monitoring for diabetic care. IEEE Trans. Circuits Syst. I Regul. Pap. 65(2), 663–676 (2017)
Pickup, J.C., Khan, F., Zhi, Z.L., Coulter, J., Birch, D.J.: Fluorescence intensity-and lifetime-based glucose sensing using glucose/galactose-binding protein. J. Diab. Sci. Technol. 7(1), 62–71 (2013)
Pitzer, K.R., et al.: Detection of hypoglycemia with the GlucoWatch biographer. Clin. Diabetol. 2(4), 307–314 (2001)
Rachim, V.P., Chung, W.Y.: Wearable-band type visible-near infrared optical biosensor for non-invasive blood glucose monitoring. Sens. Actuators B Chem. 286, 173–180 (2019)
Raj, A.: Unlocking the true power of support vector regression (2020)
Robinson, M.R., et al.: Noninvasive glucose monitoring in diabetic patients: a preliminary evaluation. Clin. Chem. 38(9), 1618–1622 (1992)
Rothman, A.: The Bayesian paradigm & ridge regression (2020). https://towardsdatascience.com
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Saklayen, M.G.: The global epidemic of the metabolic syndrome. Curr. Hypertens. Rep. 20(2), 1–8 (2018)
Sakr, M.A., Serry, M.: Non-enzymatic graphene-based biosensors for continous glucose monitoring. In: 2015 IEEE SENSORS, pp. 1–4. IEEE (2015)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Shi, B., et al.: Learning better deep features for the prediction of occult invasive disease in ductal carcinoma in situ through transfer learning, p. 98 (2018). https://doi.org/10.1117/12.2293594
Tammina, S.: Transfer learning using VGG-16 with deep convolutional neural network for classifying images. Int. J. Sci. Res. Publ. (IJSRP) 9(10), 143–150 (2019)
Valero, M., et al.: Development of a non-invasive blood glucose monitoring system prototype: pilot study. J. Med. Internet Res. JMIR Formative Res. (forthcoming/in press)
Vashist, S.K.: Non-invasive glucose monitoring technology in diabetes management: a review. Anal. Chim. Acta 750, 16–27 (2012)
Vegesna, A., Tran, M., Angelaccio, M., Arcona, S.: Remote patient monitoring via non-invasive digital technologies: a systematic review. Telemed. e-Health 23(1), 3–17 (2017)
Verma, Y.: Hands-on tutorial on elasticnet regression (2021). https://analyticsindiamag.com/hands-on-tutorial-on-elasticnet-regression/
Dong, X., Yu, Z., Cao, W., Shi, Y., Ma, Q.: A survey on ensemble learning. Fron. Comput. Sci. 14, 241–258 (2020). https://doi.org/10.1007/s11704-019-8208-z
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Kazi, T., Ponakaladinne, K., Valero, M., Zhao, L., Shahriar, H., Ingram, K.H. (2023). Comparative Study of Machine Learning Methods on Spectroscopy Images for Blood Glucose Estimation. In: Tsanas, A., Triantafyllidis, A. (eds) Pervasive Computing Technologies for Healthcare. PH 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 488. Springer, Cham. https://doi.org/10.1007/978-3-031-34586-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-34586-9_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34585-2
Online ISBN: 978-3-031-34586-9
eBook Packages: Computer ScienceComputer Science (R0)