PhD researcher at K. J. Somaiya Institute of Technology with over 10 years of teaching experience, three research publications, and a GATE 2022 qualification. My doctoral work focuses on the development of ODOSCAN, an innovative medical diagnostic device based on electronic nose (E-nose) technology for the early detection of lung cancer through the analysis of volatile organic compounds (VOCs) in exhaled breath. Her research interests include biomedical sensing technologies, breathomics and VOC biomarker profiling, AI and machine learning applications in medical diagnostics, and medical device innovation, with a strong emphasis on translating sensor-based data into practical, non-invasive, and cost-effective healthcare solutions through industry–academia collaboration.
Breathomics and VOC biomarker analysis – studying volatile organic compounds in exhaled breath for disease detection. AI and machine learning in medical diagnostics – applying data-driven models for pattern recognition and classification of biomarkers. Medical device innovation and development – designing non-invasive cost-effective diagnostic tools. Industry–academia collaboration– integrating research with practical clinical solutions. Biomedical sensing technologies – especially electronic nose (E-nose) systems for healthcare applications.
Digital olfaction systems are an emerging class of technologies that mimic the human sense of smell by detecting, processing, and interpreting volatile organic compounds (VOCs) using sensors and artificial intelligence. These systems have shown immense potential in applications ranging from food safety, agriculture to disease diagnosis, enabling non-invasive, real-time analysis of complex gas mixtures. Early detection of lung cancer significantly improves treatment outcomes, yet current diagnostic methods remain invasive, costly, and inaccessible in many settings. This study presents ODOScan, a non-invasive electronic nose (e-nose) system designed to profile volatile organic compounds (VOCs) in exhaled breath for early lung cancer detection. By simulating human olfaction, ODOScan leverages a sensor array to detect disease-specific VOC biomarkers and applies machine learning algorithms for pattern recognition and diagnosis. The system integrates with an Android application to provide real-time screening results, enhancing usability in clinical and remote environments. The diagnostic models are validated using breath samples and supported by clinical feedback, demonstrating the potential of VOC-based digital olfaction as a reliable, portable, and cost-effective tool for early cancer detection. ODOScan aligns with India's innovation priorities in low-cost, accessible diagnostics and is currently in the prototype validation stage. Its potential lies not only in early detection but also in mass screening applications, especially in resource-constrained settings. The system aims to bridge the gap between clinical need and technological capability in lung cancer diagnostics.ODOScan integrates these advancements into a compact and user-friendly device, offering a cost-effective, non-invasive platform for rapid screening in both clinical and remote healthcare environments.
