Electronic Nose and Lung Cancer - Electronic‑Nose Technology for Lung Cancer Detection: A Non‑Invasive Diagnostic Revolution

Sep 23, 2026

Uploaded by Rizky

Lung cancer remains a major cause of cancer-related mortality, especially when diagnosis occurs late and reliable early detection tools are limited. This review examines electronic nose systems for early lung cancer screening by outlining operating principles, recent technological progress, and practical constraints. It synthesizes evidence from studies using exhaled-breath volatile organic compounds, while emphasizing AI- and machine-learning-based pattern recognition. Key barriers include sensor stability, inconsistent breath collection, demographic effects, and the need for large training datasets for robust clinical translation.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Abstract

Background

Objective

Methods

Results

Conclusion

Introduction to Electronic Nose

Lung cancer burden and need for early detection

Limitations of existing diagnostic techniques

Promise of electronic-nose as a non-invasive alternative

Lung (2025) 203:76 [https://doi.org/10.1007/s00408-025-00828-0](https://doi.org/10.1007/s00408-025-00828-0) REVIEW ELECTRONIC NOSE AND LUNG CANCER Electronic‑Nose Technology for Lung Cancer Detection: A Non‑Invasive Diagnostic Revolution A. M. Dhanush Gowda1 · Akanksha D. Dessai1 · UshaY. Nayak1 Received: 30 April 2025 / Accepted: 12 June 2025 / Published online: 8 July 2025 © The Author(s) 2025 Abstract Background Lung cancer (LC) remains a leading cause of cancer-related mortality worldwide, primarily due to late-stage diagnosis and the absence of effective early detection methods. Objective This review aims to explore the principles, technological advancements, current limitations, and future prospects of electronic nose (E-nose) systems in the early detection of lung cancer. Methods The review analyzes recent literature on E-nose devices that detect volatile organic compounds (VOCs) in exhaled breath, focusing on their integration with artificial intelligence (AI) and machine learning for pattern recognition and diagnostic classification. Results E-noses have demonstrated high sensitivity and specificity in differentiating cancerous from non-cancerous breath samples. However, challenges such as sensor stability, lack of standardization in breath collection, demographic variability, and the need for large training datasets for AI models limit their clinical adoption. Conclusion Despite current limitations, E-nose technology shows strong potential as a rapid, non-invasive, and cost-effective tool for early LC screening. Enhancing sensor durability, improving data processing, and conducting large-scale validation studies are critical next steps. Integration with imaging and molecular biomarkers may further improve diagnostic accuracy and clinical utility. * Usha Y. Nayak [usha.nayak@manipal.edu](usha.nayak@manipal.edu) 1 Department of Pharmaceutics, Manipal College of Pharmaceutical Sciences, Manipal Academy of Higher Education, Manipal 576104, Karnataka, India Graphical Abstract Keywords E-nose · Lung cancer · Volatile organic compounds · Non-invasive · Lung cancer diagnosis Abbreviations LC Lung Cancer VOC Volatile Organic Compounds E-nose Electronic Nose AI Artificial Intelligence CT Computer-based Tomography GC-MS Gas Chromatography-Mass Spectrometry NPV Negative Predictive Value ROS Reactive Oxygen Species CYP450 Cytochrome P450 PUFA Poly-unsaturated Fatty Acids MEMS Micro-Electro-Mechanical Systems ANN Artificial Neural Network PCA Principal Component Analysis SVM Support Vector Machine MOS Metal Oxide Semiconductor SnO₂ Stannic Oxide ZnO Zinc Oxide WO₃ Tungsten Trioxide TiO₂ Titanium Dioxide SPR Surface Plasmon Resonance BAW SAW PC MOF QCM ML AUC DSP CNN RNN LSTM SoC NSCLC SCLC SCC ADC COPD GC-FAIMS KI KNN Bulk Acoustic Wave Surface Acoustic Wave Polycarbonate Metal-Organic Framework Quartz Crystal Microbalance Machine Learning Area Under Curve Digital Signal Processor Convolutional Neural Network Recurrent Neural Network Long Short-Term Memory System-on-Chip Non-Small Cell Lung Cancer Small Cell Lung Cancer Squamous Cell Carcinoma Adenocarcinoma Chronic Obstructive Pulmonary Disease Gas Chromatography—Field Asymmetric Ion Mobility Spectrometry Kovats Index K-Nearest Neighbors LDAWDELM GA XGBoost Linear Discriminant Analysis Weighted Discriminative Extreme Learning Machine Genetic Algorithm EXtreme Gradient Boosting Introduction to Electronic Nose Lung cancer (LC) is an aggressive and multifaceted disease and affects every patient differently. The disease grows quickly and can sometimes be challenging to treat, meaning that no case is alike from the next one [1] . According to GLOBOCAN 2020, there were approximately 2.2 million new cases of LC (11.4%) and nearly 1.8 million LCrelated deaths (18 .0%) in 2020 [2] . LC was the second most prevalent cancer diagnosis globally in

FAQs

What problem does the review address in lung cancer screening?

It focuses on lung cancer’s high mortality linked to late-stage diagnosis and the lack of effective early detection methods.

How do electronic nose systems support early lung cancer detection?

They analyze volatile organic compounds in exhaled breath and use AI or machine learning to recognize patterns and classify samples.

Why is clinical adoption of E-nose technology still limited?

Challenges include sensor stability, lack of standardized breath-collection procedures, demographic variability, and the requirement for large training datasets for AI models.

Sep 23, 2026

Uploaded by Rizky