Prospective Detection of Early Lung Cancer in Patients With COPD in Regular Care by Electronic Nose Analysis of Exhaled Breath
Aim: To determine the diagnostic accuracy of exhaled breath analysis by eNose for (1) the discrimination between patients with COPD and those with lung cancer in a training and validation set and (2) the prospective prediction of early lung cancer in COPD.
Take home message: eNose technology shows promising accuracy in detecting early lung cancer in COPD patients through non-invasive breath analysis. Enose could support routine screening and early intervention in high-risk populations, potentially improving patient outcomes.
Introduction
This study investigates the potential of electronic nose (eNose) technology for the early detection of lung cancer in patients with chronic obstructive pulmonary disease (COPD), who are at an elevated risk for developing lung cancer. Traditional screening for lung cancer often involves invasive procedures or imaging that may not be feasible or precise for routine use in high-risk populations like COPD patients. eNose technology, which analyzes volatile organic compounds (VOCs) in exhaled breath, offers a non-invasive method for detecting metabolic changes associated with early lung cancer.
Methods
The study included 682 COPD patients and 211 lung cancer patients across multiple clinical centers. Each patient performed a standardized measurement maneuver using the SpiroNose®. Data were analyzed using principal component analysis (PCA) and linear discriminant analysis to differentiate breath profiles of lung cancer patients from those with COPD. All COPD patients were followed for two years to observe if they developed lung cancer, allowing researchers to assess eNose’s accuracy in predicting early-stage cancer.
Results
ENose technology accurately distinguished between lung cancer and COPD in both training and validation sets, with areas under the ROC curve (AUC) of 0.89 and 0.86, respectively. Among COPD patients who developed lung cancer within two years, 89% were correctly classified by eNose analysis at baseline, achieving an AUC of 0.90. The technology demonstrated a sensitivity of 86% and specificity of 89% for detecting early lung cancer, showing strong promise as a non-invasive diagnostic tool.
Discussion
The findings highlight eNose technology as a valuable approach for the early detection of lung cancer in COPD patients. The ability to identify lung cancer-specific VOC patterns in breath profiles may enable eNose technology to support or complement current screening methods. Given COPD’s high association with lung cancer, the eNose could become an important tool for routine monitoring in this high-risk population, allowing for timely intervention and potentially improving patient outcomes. Further research is recommended to validate eNose’s clinical applicability and refine its use for different lung cancer stages.
