Development of Blood Glucose Monitoring System using Image Processing and Machine Learning Techniques

• Autorzy: Thomas Angel , Palekar Sangeeta , Kalambe Jayu

Identyfikatory

DOI

10.24425/ijet.2022.139885

• Języki publikacji: EN

Abstrakty

EN

Glucose concentration measurement is essential for diagnosis, monitoring and treatment of various medical conditions like diabetes mellitus, hypoglycemia, etc. This paper presents a novel image-processing and machine learning based approach for glucose concentration measurement. Experimentation based on Glucose oxidase - peroxidase (GOD/POD) method has been performed to create the database. Glucose in the sample reacts with the reagent wherein the concentration of glucose is detected using colorimetric principle. Colour intensity thus produced, is proportional to the glucose concentration and varies at different levels. Existing clinical chemistry analyzers use spectrophotometry to estimate the glucose level of the sample. Instead, this developed system uses simplified hardware arrangement and estimates glucose concentration by capturing the image of the sample. After further processing, its Saturation (S) and Luminance (Y) values are extracted from the captured image. Linear regression based machine learning algorithm is used for training the dataset consists of saturation and luminance values of images at different concentration levels. Integration of machine learning provides the benefit of improved accuracy and predictability in determining glucose level. The detection of glucose concentrations in the range of 10–400 mg/dl has been evaluated. The results of the developed system were verified with the currently used spectrophotometry based Trace40 clinical chemistry analyzer. The deviation of the estimated values from the actual values was found to be around 2-3%.

Słowa kluczowe

EN

glucose; image processing; machine learning; colorimetry

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2022
• Tom: Vol. 68, No. 2
• Strony: 323--328
• Opis fizyczny: Bibliogr. 32 poz., wykr., tab., rys.

Twórcy

autor

Thomas Angel

• Shri Ramdeobaba College of Engineering & Management, India

autor

Palekar Sangeeta

• Shri Ramdeobaba College of Engineering & Management, India

autor

Kalambe Jayu

• Shri Ramdeobaba College of Engineering & Management, India

Bibliografia

• [1] A. T. Kharroubi, “Diabetes mellitus: The epidemic of the century,” World J. Diabetes, vol. 6, no. 6, p. 850, 2015. https://dx.doi.org/10.4239/wjd.v6.i6.850
• [2] Y. Wu, Y. Ding, Y. Tanaka, and W. Zhang, “Risk factors contributing to type 2 diabetes and recent advances in the treatment and prevention,” Int. J. Med. Sci., vol. 11, no. 11, pp. 1185–1200, 2014, https://dx.doi.org/10.7150/ijms.10001 https://dx.doi.org/
• [3] “Diabetes,” 2021. https://www.who.int/news-room/fact-sheets/detail/-diabetes
• [4] C. Fabris and B. Kovatchev, Glucose Monitoring Devices: Measuring Blood Glucose to Manage and Control Diabetes. 2020.
• [5] C. C. Barr, “Retinopathy and nephropathy in patients with type 1 diabetes four years after a trial of intensive insulin therapy,” Surv. Ophthalmol., vol. 45, no. 5, pp. 459–460, 2001. https://dx.doi.org/10.1016/S0039-6257(01)00187-4
• [6] C. L. Martin, J. Albers, P. Cleary, B. Waberski, D. A. Greene, and E. L. Feldman, “Neuropathy Among the Diabetes Control and Complications Trial Cohort 8 Years,” Diabetes Care, vol. 29, no. 2, pp. 340–344, 2006, [Online] Available: http://care.diabetesjournals.org/content/29/2/340.full.pdf+html
• [7] D. M. Nathan and S. Russell, “The future of care for type 1 diabetes,” Cmaj, vol. 185, no. 4, pp. 285–286, 2013. https://dx.doi.org/10.1503/cmaj.130011
• [8] S. Inoue, M. Egi, J. Kotani, and K. Morita, “Accuracy of blood-glucose measurements using glucose meters and arterial blood gas analyzers in critically ill adult patients: Systematic review,” Crit. Care, vol. 17, no. 2, pp. 2–5, 2013. https://dx.doi.org/10.1186/cc12567
• [9] C. Bay, P. L. Kristensen, U. Pedersen-Bjergaard, L. Tarnow, and B. Thorsteinsson, “Nocturnal continuous glucose monitoring: Accuracy and reliability of hypoglycemia detection in patients with type 1 diabetes at high risk of severe hypoglycemia,” Diabetes Technol. Ther., vol. 15, no. 5, pp. 371–377, 2013. https://dx.doi.org/10.1089/dia.2013.0004
• [10] P. Mohammadnejad, S. S. Asl, S. Aminzadeh, and K. Haghbeen, “A new sensitive spectrophotometric method for determination of saliva and blood glucose,” Spectrochim. Acta - Part A Mol. Biomol. Spectrosc., vol. 229, p. 117897, 2020. https://dx.doi.org/10.1016/j.saa.2019.117897
• [11] Y. Chen et al., “Skin-like biosensor system via electrochemical channels for noninvasive blood glucose monitoring,” Sci. Adv., vol. 3, no. 12, pp. 1–8, 2017. https://dx.doi.org/10.1126/sciadv.1701629
• [12] B. Feldman et al., “Freestyle(TM): A small-volume electrochemical glucose sensor for home blood glucose testing,” Diabetes Technol. Ther., vol. 2, no. 2, pp. 221–229, 2000. https://dx.doi.org/10.1089/15209150050025177
• [13] G. Purvinis, B. D. Cameron, and D. M. Altrogge, “Noninvasive Polarimetric-Based Glucose Monitoring: An,” vol. 5, no. 2, pp. 380–387, 2011.
• [14] J. R. Castle and W. K. Ward, “Amperometric glucose sensors: Sources of error and potential benefit of redundancy,” J. Diabetes Sci. Technol., vol. 4, no. 1, pp. 221–225, 2010. https://dx.doi.org/10.1177/193229681000400127
• [15] H. Zhang, Z. Chen, J. Dai, W. Zhang, Y. Jiang, and A. Zhou, “A low-cost mobile platform for whole blood glucose monitoring using colorimetric method,” Microchem. J., vol. 162, no. November 2020, p. 105814, 2021, https://dx.doi.org/10.1016/j.microc.2020.105814
• [16] H.-C. Wang, F.-Y. Chang, T.-M. Tsai, C.-H. Chen, and Y.-Y. Chen, “Development and clinical trial of a smartphone-based colorimetric detection system for self-monitoring of blood glucose,” Biomed. Opt. Express, vol. 11, no. 4, p. 2166, 2020. https://dx.doi.org/10.1364/boe.389638
• [17] C. P. Price, “Point-of-Care Testing in Diabetes Mellitus,” vol. 41, no. 9, pp. 1213–1219, 2003.
• [18] A. Heller and B. Feldman, “Electrochemical glucose sensors and their applications in diabetes management,” Chem. Rev., vol. 108, no. 7, pp. 2482–2505, 2008. https://dx.doi.org/10.1021/cr068069y
• [19] R. Morris, “Spectrophotometry,” Curr. Protoc. Essent. Lab. Tech., vol. 11, no. 1, pp. 2.1.1-2.1.30, 2015. https://dx.doi.org/10.1002/9780470089941.et0201s11
• [20] A. Málnási-Csizmadia, “Spectrophotometry and protein concentration measurements,” Introd. to Pract. Biochem., pp. 42–59, 2013.
• [21] S. Edition, Handbook of Second Edition Biomedical Instrumentation. .
• [22] N. Demitri and A. M. Zoubir, “Measuring Blood Glucose Concentrations in Photometric Glucometers Requiring Very Small Sample Volumes,” IEEE Trans. Biomed. Eng., vol. 64, no. 1, pp. 28–39, 2017. https://dx.doi.org/10.1109/TBME.2016.2530021
• [23] S. Piramanayagam, E. Saber, and D. Heavner, “Measurement of glucose concentration by image processing of thin film slides,” Med. Imaging 2012 Image Process., vol. 8314, p. 83144U, 2012. https://dx.doi.org/10.1117/12.910978
• [24] A. Fatoni, A. N. Aziz, and M. D. Anggraeni, “Sensing and Bio-Sensing Research Low-cost and real-time color detector developments for glucose biosensor,” vol. 28, no. November 2019, pp. 0–5, 2020.
• [25] J. S. Kim et al., “A study on detection of glucose concentration using changes in color coordinates,” Bioengineered, vol. 8, no. 1, pp. 99–104, 2017. https://dx.doi.org/10.1080/21655979.2016.1227629
• [26] R. B. Dominguez, M. A. Orozco, G. Chávez, and A. Márquez-Lucero, “The evaluation of a low-cost colorimeter for glucose detection in salivary samples,” Sensors (Switzerland), vol. 17, no. 11, pp. 19–21, 2017. https://dx.doi.org/10.3390/s17112495
• [27] “Digital Image Processing Techniques for Hardcopy,” Digital Image Processing Techniques for Hardcopy, vol. 25, no. 3. pp. 171–179, 1988. https://dx.doi.org/10.11413/nig1987.25.171
• [28] A. Raja and K. Sankaranarayanan, “Use of RGB Color Sensor in Colorimeter for better Clinical measurement of Blood Glucose,” BIME J., no. 06, pp. 4–9, 2006, [Online]. Available: http://scholar.google.com/scholar?hl=en&btnG=Search&q=intitle:Use+of+RGB+Color+Sensor+in+Colorimeter+for+better+Clinical+measurement+of+Blood+Glucose#0
• [29] S. Singhal, P. Ralhan, and N. Jatana, “Smartphone-based colorimetric detection to measure Blood Glucose Levels,” 2015 8th Int. Conf. Contemp. Comput. IC3 2015, pp. 269–274, 2015. https://dx.doi.org/10.1109/IC3.2015.7346691
• [30] V. N. AMBADE, Y. SHARMA, and B. SOMANI, “Methods for Estimation of Blood Glucose : a Comparative Evaluation,” Med. J. Armed Forces India, vol. 54, no. 2, pp. 131–133, 1998. https://dx.doi.org/10.1016/s0377-1237(17)30502-6
• [31] M. Gusev et al., “Review Article Noninvasive Glucose Measurement Using Machine Learning and Neural Network Methods and Correlation with Heart Rate Variability,” vol. 2020, 2020.
• [32] Y. Marcus et al., “Improving blood glucose level predictability using machine learning,” Diabetes. Metab. Res. Rev., vol. 36, no. 8, 2020. https://dx.doi.org/10.1002/dmrr.3348

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).