Kapur, R.; Kumar, Y.; Sharma, S.; Rastogi, V.; Sharma, S.; Kanwar, V.; Sharma, T.; Bhavsar, A.; Dutt, V. DiabeticSense: A Non-Invasive, Multi-Sensor, IoT-Based Pre-Diagnostic System for Diabetes Detection Using Breath. J. Clin. Med.2023, 12, 6439.
Kapur, R.; Kumar, Y.; Sharma, S.; Rastogi, V.; Sharma, S.; Kanwar, V.; Sharma, T.; Bhavsar, A.; Dutt, V. DiabeticSense: A Non-Invasive, Multi-Sensor, IoT-Based Pre-Diagnostic System for Diabetes Detection Using Breath. J. Clin. Med. 2023, 12, 6439.
Kapur, R.; Kumar, Y.; Sharma, S.; Rastogi, V.; Sharma, S.; Kanwar, V.; Sharma, T.; Bhavsar, A.; Dutt, V. DiabeticSense: A Non-Invasive, Multi-Sensor, IoT-Based Pre-Diagnostic System for Diabetes Detection Using Breath. J. Clin. Med.2023, 12, 6439.
Kapur, R.; Kumar, Y.; Sharma, S.; Rastogi, V.; Sharma, S.; Kanwar, V.; Sharma, T.; Bhavsar, A.; Dutt, V. DiabeticSense: A Non-Invasive, Multi-Sensor, IoT-Based Pre-Diagnostic System for Diabetes Detection Using Breath. J. Clin. Med. 2023, 12, 6439.
Abstract
Diabetes mellitus is a widespread chronic metabolic disorder demanding regular blood glucose level surveillance (BGLs). Current invasive techniques, such as finger-prick tests, often result in discomfort for patients, leading to infrequent monitoring and potential health complications. The primary objective of this study was to design a novel, portable, non-invasive system for diabetes detection using breath samples, named as DiabeticSense, an affordable digital health device for early detection, encouraging immediate intervention. The device employed MOSFET-based electrochemical sensors to assess volatile organic compounds in breath samples, whose concentrations differ between diabetic and non-diabetic individuals. The system merged body vital signs with sensor voltages obtained by processing breath sample data to predict diabetic conditions. Our research used readings from 100 patients at a nationally recognised hospital to form the dataset. Data was then processed 10 using a Gradient Boosting Classifier model, and performance was cross-validated. The proposed system attained a promising accuracy of 86.6%, marking an improvement of 20.72% over an existing regression technique. The developed device introduces a non-invasive, cost-effective, and user-friendly solution for preliminary diabetes detection. It has the potential to increase patient adherence to regular monitoring.
Keywords
digital health devices; diabetes test; bio-markers; blood glucose monitoring; diabetes; exhaled breath analysis; non-invasive; volatile organic compounds
Subject
Medicine and Pharmacology, Endocrinology and Metabolism
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
