Improving lung cancer diagnosis from exhaled-breath analysis by adding clinical parameters to the artificial neural network

IntroductionExhaled-breath analysis of volatile organic compounds could detect lung cancer earlier, possibly leading to improved outcomes. Combining exhaled-breath data with clinical parameters may improve lung cancer diagnosis.MethodsBased on data from a previous multi-centre study, this article reports additional analyses. 138 subjects with non-small cell lung cancer (NSCLC) and 143 controls without NSCLC breathed into the Aeonose. The diagnostic accuracy, presented as area under the receiver operating characteristic curve (AUC-ROC), of the Aeonose itself was compared with 1) performing a multivariate logistic regression analysis of the distinct clinical parameters obtained, and 2) using this clinical information beforehand in the training process of the artificial neural network (ANN) for the breath analysis.ResultsNSCLC patients (mean±sd age 67.1±9.1 years, 58% male) were compared with controls (62.1±7.0 years, 40.6% male). The AUC-ROC of the classification value of the Aeonose itself was 0.75 (95% CI 0.69–0.81). Adding age, number of pack-years and presence of COPD to this value in a multivariate regression analysis resulted in an improved performance with an AUC-ROC of 0.86 (95% CI 0.81–0.90). Adding these clinical variables beforehand to the ANN for classifying the breath print also led to an improved performance with an AUC-ROC of 0.84 (95% CI 0.79–0.89).ConclusionsAdding readily available clinical information to the classification value of exhaled-breath analysis with the Aeonose, either post hoc in a multivariate regression analysis or a priori to the ANN, significantly improves the diagnostic accuracy to detect the presence or absence of lung cancer.

Download Full-text

Combined sputum hypermethylation and eNose analysis for lung cancer diagnosis

Journal of Clinical Pathology ◽

10.1136/jclinpath-2014-202414 ◽

2014 ◽

Vol 67 (8) ◽

pp. 707-711 ◽

Cited By ~ 33

Author(s):

A Jasmijn Hubers ◽

Paul Brinkman ◽

Remco J Boksem ◽

Robert J Rhodius ◽

Birgit I Witte ◽

...

Keyword(s):

Lung Cancer ◽

Cancer Patients ◽

Cancer Diagnosis ◽

Breath Analysis ◽

Exhaled Breath ◽

Dna Hypermethylation ◽

Lung Cancer Patients ◽

Lung Cancer Diagnosis ◽

Exhaled Breath Analysis ◽

Validation Set

AimsThe aim of this study is to explore DNA hypermethylation analysis in sputum and exhaled breath analysis for their complementary, non-invasive diagnostic capacity in lung cancer.MethodsSputum samples and exhaled breath were prospectively collected from 20 lung cancer patients and 31 COPD controls (Set 1). An additional 18 lung cancer patients and 8 controls only collected exhaled breath as validation set (Set 2). DNA hypermethylation of biomarkers RASSF1A, cytoglobin, APC, FAM19A4, PHACTR3, 3OST2 and PRDM14 was considered, and breathprints from exhaled breath samples were created using an electronic nose (eNose).ResultsBoth DNA hypermethylation markers in sputum and eNose were independently able to distinguish lung cancer patients from controls. The combination of RASSF1A and 3OST2 hypermethylation had a sensitivity of 85% with a specificity of 74%. eNose had a sensitivity of 80% with a specificity of 48%. Sensitivity for lung cancer diagnosis increased to 100%, when RASSF1A hypermethylation was combined with eNose, with specificity of 42%. Both methods showed to be complementary to each other (p≤0.011). eNose results were reproducible in Set 2.ConclusionsWhen used in concert, RASSF1A hypermethylation in sputum and exhaled breath analysis are complementary for lung cancer diagnosis, with 100% sensitivity in this series. This finding should be further validated.

Download Full-text