A Comprehensive Review on Breath Analyzer as a Point-of-Care Device for VOC-Based Lung Cancer Risk Prediction using Deep Learning

DOI

10.2991/978-94-6463-976-6_8How to use a DOI?

Keywords

Exhaled Breath (EB); Volatile Organic Compounds (VOCs); Nanomaterials; Biosensors

Abstract

All over the world, lung cancer is one of the most widespread causes of cancer-associated deaths, and this problem is largely supported by the late diagnosis of this disease and the shortcomings of the currently used screening method like low-dose computed tomography (LDCT). Breath analysis has become an emerging diagnostic option that is non-invasive, fast, and economically efficient in identifying the disease specific volatile organic compounds (VOCs) in the exhaled air. The review gives a concise summary of the recent developments in electronic nose (E-Nose) devices, nanomaterial sensors, and deep learning (DL) algorithms in the early detection and risk prediction of lung cancer. The paper clearly explains how E-Nose architectures have evolved over the years beginning with the traditional metal oxide semiconductor (MOS) arrays to the current plasmonic nanostructures and graphene and the hybrid nanostructures, and how they have increased sensitivity and selectivity towards VOCs biomarkers at the trace level. The use of convolutional and recurrent neural networks as advanced DL frameworks has also seen a dramatic increase in the accuracy of breathprint classification and real-time inference in portable point-of-care (POC) devices. Meta-analyses and clinical trials have shown a high diagnostic accuracy of > 90 and high chances of early-stage (Stage I) diagnosis. Nevertheless, there are obstacles to the attainment of a standardized breath collection, cross-cohort validation, and sensor reproducibility in real-life settings. The conclusion of the review lays out future directions about the research on multimodal integration, Explainable AI (XAI) to promote clinical interpretability, and large-scale clinical validation. Taken together, these inventions make POC breath analyzers a disruptive technology in the field of individual, convenient, and proactive lung cancer diagnosis.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Manonmani Vadivel
AU  - Devi Chokkalingam
AU  - S. Balamurugan
AU  - R. Priyadharshini
AU  - V. Cyril Raj
AU  - S. Pushpavanam
PY  - 2025
DA  - 2025/12/29
TI  - A Comprehensive Review on Breath Analyzer as a Point-of-Care Device for VOC-Based Lung Cancer Risk Prediction using Deep Learning
BT  - Proceedings of the International Conference on Intelligent Information Systems Design and Indian Knowledge System Applications (ICISDIKSA 2026)
PB  - Atlantis Press
SP  - 120
EP  - 132
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-976-6_8
DO  - 10.2991/978-94-6463-976-6_8
ID  - Vadivel2025
ER  -