IIT Jodhpur Researchers Develop App for Smartphone-Integrated Glucose Testing System

Researchers at the Indian Institute of Technology Jodhpur have introduced an innovative system enabling smartphones to conduct quick and accessible glucose level tests for patients. This groundbreaking system integrates a Paper-based Analytical Device (PAD) with any Android smartphone via a dedicated app, facilitating glucose detection within a concentration range of 10−40 mM.

PADs, portable devices revolutionizing point-of-need testing, quickly analyze biochemical samples. The device incorporates functionalized biodegradable paper that changes color based on glucose levels. The smartphone connection expedites the process, enabling rapid and personalized glucose level tracking without the need for complex laboratory settings.

Designed for public personal use, the system offers on-the-spot glucose testing without technical requirements. Moreover, it boasts cost-effectiveness and biodegradability, with current lab costs at approximately Rs. 10, expected to reduce to Rs. 5 during mass production.

The research, spearheaded by Prof. Ankur Gupta, alongside Vinay Kishnani, Nikhil Kashyap, and Shivam Shashank from the Department of Mechanical Engineering at IIT Jodhpur, aims to bridge technological integration gaps in healthcare.

Dr. Ankur Gupta, Associate Professor, highlights the seamless integration potential of smartphones with other platforms, facilitating remote monitoring and data sharing crucial for healthcare professionals and researchers.

Unlike conventional PADs requiring specific light conditions, this system operates effectively under diverse lighting, ensuring accurate transmission to smartphones. Machine learning applications processed artificial glucose sample images to develop the smartphone app, ensuring color intensity remains unaffected by varying camera optics.

Published in ACS Publications, the research demonstrates the system's capability for initial disease screening and diagnosis. Dr. Gupta emphasizes its potential for improving healthcare screening accuracy and enabling rapid disease diagnosis through machine learning techniques.

The module's adaptability extends to detecting other diseases, with ongoing research targeting simultaneous glucose, uric acid, and lactate detection using distinct color indicators. Although presently focusing on glucose, the framework holds promise for screening and diagnosing various diseases, requiring adaptation for different analytes, enzymes, and indicators.

Ultimately, this research signifies a significant step towards democratizing healthcare through accessible, smartphone-integrated diagnostic solutions.