Machine Learning Based System And Method For Detecting Diabetes From Breath Sample Of An Individual
Abstract
Embodiments disclose a method and a non-invasive glucometer system thereof, for detecting diabetes from breath sample of an individual, comprising: an air storage for collecting breath sample of an individual/user, when a user blows into it; a user terminal having a user interface (UI) for entering demographic data and body vital information of the user; a volatile organic compounds (VOC) analyzer, operably coupled to the air storage, to infuse the breath sample collected into the VOC analyzer, said VOC analyzer comprising a sensor array chamber having a plurality of embedded electrochemical sensors, said VOC analyzer is configured to: generate corresponding sensor voltages from the plurality of embedded sensors, wherein the sensed output voltages correspond to the concentration of VOCs in the breath sample; determine volatile organic compounds (VOCs) in the breath sample of the user; and transmit sensed output voltages to a processing and controlling unit, in real-time. The processing and controlling unit comprising a microcontroller, said unit is configured to: receive and store, demographic data and body vital information of the user, from the user terminal; receive and store, the sensed output voltages, from the plurality of embedded sensors; send, the stored combined data set relating to demographic data and body vital information of the user, and the sensed output voltages, from the plurality of embedded electrochemical sensors, on receiving a breath sample of the user, to train a machine learning (ML) model. The user terminal is configured to receive a diabetes prediction report for a test breath sample, from the trained ML model.
References
2. American Diabetes Association. "Standards of medical care in diabetes—2021." Diabetes Care, 44(Supplement 1), S1-S232, 2021.
3. International Diabetes Federation. "IDF Diabetes Atlas, 9th edition." 2019.
4. Guo, D., Zhang, D., Zhang, L., & Lu, G. "Non-invasive blood glucose monitoring for diabetics by means of breath signal analysis." Sensors and Actuators B: Chemical, 173, 106- 113, 2012.
5. Rydosz, A. "A negative correlation between blood glucose level and acetone concentration in exhaled breath of type 1 diabetic patients using the correlation and regression analysis." Journal of Diabetes and its Complications, 32(6), 2018.
6. Paleczek, A., Grochala, D., & Rydosz, A. "Artificial breath classification using XGBoost algorithm for diabetes detection." Sensors, 21(8), 2788, 2021.
7. Li, Z., Wang, C., Yang, Z., & Wang, J. "Review of non-invasive continuous glucose monitoring based on impedance spectroscopy technique." Current Pharmaceutical Biotechnology, 21(12), 1116-1122, 2020.
8. Ohira, S. I., & Toda, K. "Miniaturized device for measuring blood glucose levels from exhaled breath." Analytical Chemistry, 82(21), 8927-8931, 2010.
9. Righettoni, M., Tricoli, A., & Pratsinis, S. E. "Si: WO3 sensors for highly selective detection of acetone for easy diagnosis of diabetes by breath analysis." Analytical Chemistry, 82(9), 3581-3587, 2010.
10. Pundir, C. S., & Narwal, V. "Determination of acetone in body fluids: a review." Biosensors and Bioelectronics, 41, 2013.
11. Schaller, E., Bosset, J. O., & Escher, F. "‘Electronic noses’ and their application to food." LWT-Food Science and Technology, 31(4), 305-316, 1998.
12. Turner, A. P. "Biosensors: sense and sensibility." Chemical Society Reviews, 42(8), 3184- 3196, 2013.
13. Kumar, A., & Sharma, R. "Recent developments in optical sensors for non-invasive glucose monitoring." Current Diabetes Reports, 17(12), 2017.
14. Tamaki, Y., Seto, K., & Sugimoto, T. "Non-invasive glucose monitoring device using near- infrared absorption spectroscopy." Journal of Biomedical Optics, 9(5), 1185-1190, 2004.
15. Brady, C. W. "Nasal exhaled breath condensate as a biomarker in diabetes mellitus: a review." Clinical Biochemistry, 47(6), 500-511, 2014.
16. Borchers, A. T., Uibo, R., Gershwin, M. E. "The geoepidemiology of type 1 diabetes." Autoimmunity Reviews, 9(5), A355-A365, 2010.
17. Patel, B. A., & Aravamudhan, S. "Emerging trends in non-invasive wearable electrochemical sensors for continuous glucose monitoring." Trends in Analytical Chemistry, 110, 133-141, 2019.
18. Teymourian, H., Parrilla, M., Sempionatto, J. R. "Wearable electrochemical sensors for the monitoring and screening of diabetes." Nature Reviews Chemistry, 4(6), 2020.
19. McKnight, J. A., Wild, S. H., Lamb, M. J., Cooper, M. N., Jones, T. W., Davis, E. A., & Hofer, S. E. "Glycaemic control of Type 1 diabetes in clinical practice early in the 21st century: an international comparison." Diabetic Medicine, 32(8), 1036-1050, 2015.
20. World Health Organization. "Use of glycated haemoglobin (HbA1c) in the diagnosis of diabetes mellitus: abbreviated report of a WHO consultation." Diabetes Research and Clinical Practice, 93(3), 299-309, 2011.
21. Li, X., Zheng, C., & Gao, H. (2018). Breath-based diabetes detection using metal oxide sensors. IEEE Sensors Journal, 18(16), 6681-6689.
22. Kostov, Y., & Trushin, A. (2019). Breath-based diabetes detection and monitoring: A review. Journal of Diabetes Science and Technology, 13(3), 481-490.
23. Sun, X., Xu, Y., & Wang, H. (2020). Breathe analysis for diabetes detection: Advances and challenges. Critical Reviews in Analytical Chemistry, 50(2), 130-145.
24. Cummings, K., & Li, Q. (2017). Real-time breath monitoring for diabetes using electronic noses. Journal of Biomedical Optics, 22(6), 061206.
25. Patel, S., & O’Hare, J. (2018). Non-invasive glucose monitoring: Current status and future directions. Sensors, 18(6), 1790.
26. Khandelwal, A., & Kaur, M. (2020). A comparative study of machine learning algorithms for breath-based diabetes detection. Applied Sciences, 10(14), 4930.
27. Wang, Y., Xu, M., & Zhang, Z. (2019). Detection of diabetes from breath samples using advanced sensor technologies. Analytical and Bioanalytical Chemistry, 411(19), 4765-4772.
28. Liu, Y., & Zhang, R. (2021). Machine learning approaches for breath-based diabetes detection. Journal of Healthcare Engineering, 2021, 6667413.
29. Bhardwaj, S., & Kumar, A. (2021). Advances in non-invasive glucose monitoring technologies. Biological Measurement, 15(1), 45-58.
30. Narayanan, S., & Kumar, S. (2022). Breathe analysis for diabetes monitoring: A review of recent developments. Sensors and Actuators B: Chemical, 352, 131033.
31. Zhang, L., & Wang, Y. (2021). Review of electronic nose technologies for breath analysis. Journal of Sensors, 2021, 7583091.
32. Chen, W., & Zhang, H. (2019). Real-time monitoring of breath VOCs using an array of metal oxide sensors. Sensors and Actuators B: Chemical, 295, 126-134.
33. Smith, J., & Lee, T. (2018). Breath-based detection of volatile organic compounds for medical diagnostics. Biomedical Engineering Letters, 8(1), 55-65.
34. Davila et al., 2014; Vishinkin and Haick, 2015.
35. Wilson and Baietto, 2011; Chen et al., 2022.
