Lung cancer detection by electronic nose analysis of exhaled breath: a multicentre prospective external validation study

Publication: Buma AIG, Muntinghe-Wagenaar MB, van der Noort V, de Vries R, Schuurbiers MMF, Sterk PJ, Schipper SPM, Meurs J, Cristescu SM, Hiltermann TJN, van den Heuvel MM. Lung cancer detection by electronic nose analysis of exhaled breath: a multicentre prospective external validation study. Annals of Oncology. 2025 March 30; In Press

Aim: To prospectively and externally validate a published eNose model for lung cancer detection in chronic obstructive pulmonary disease (COPD) patients and assess its diagnostic performance alongside a new eNose model, specifically tailored to the target population, in a more general outpatient population.

Highlights
• ENose analysis of exhaled breath shows potential for accurate and timely lung cancer diagnosis.
• Its clinical adoption, though, is mainly hindered by the absence of prospective external validation studies.
• This multicentre prospective external validation study confirms accurate lung cancer detection at thoracic oncology outpatient clinics.
• Sub-analyses showed no influence of tumour characteristics, disease stage, diagnostic centres, or clinical characteristics.
• Future research should focus on determining its clinical utility in current diagnostic pathways.

Introduction

Electronic nose (eNose) analysis of exhaled breath shows potential for accurate and timely lung cancer diagnosis, yet prospective external validation studies are lacking. Our study primarily aimed to prospectively and externally validate a published eNose model for lung cancer detection in chronic obstructive pulmonary disease (COPD) patients and assess its diagnostic performance alongside a new eNose model, specifically tailored to the target population, in a more general outpatient population.

Methods

This multicentre prospective external validation study included adults with clinical and/or radiological suspicion of lung cancer who were recruited from thoracic oncology outpatient clinics of two sites in the Netherlands. Breath profiles were collected using a cloud-connected eNose (SpiroNose®). The diagnostic performance of the original and new eNose models was assessed in various population subsets based on receiver operating characteristic-area under the curve (ROC-AUC), specificity, positive predictive value (PPV), and negative predictive value (NPV), targeting 95% sensitivity. For the new eNose model, a training cohort and a validation cohort were used.

Predicted probability of lung cancer

Results

Between March 2019 and November 2023, 364 participants were included. The original eNose model detected lung cancer with an ROC-AUC of 0.92 [95% confidence interval (CI) 0.85-0.99] in COPD patients (n = 98/116; 84%) and 0.80 (95% CI 0.75-0.85) in all participants (n = 216/364; 59%). At 95% sensitivity, the specificity, PPV, and NPV, were 72% and 51%, 95% and 74%, and 72% and 88%, respectively. In the validation cohort, the new eNose model identified lung cancer across all participants (n = 72/121; 60%) with an ROC-AUC of 0.83 (95% CI 0.75-0.91), sensitivity of 94%, specificity of 63%, PPV of 79%, and NPV of 89%. Notably, accurate detection was consistent across tumour characteristics, disease stage, diagnostic centres, and clinical characteristics.

Discussion

This multicentre prospective external validation study confirms that eNose analysis of exhaled breath enables accurate lung cancer detection at thoracic oncology outpatient clinics, irrespective of tumour characteristics, disease stage, diagnostic centre, and clinical characteristics.