Recognition of breathprints of lung cancer and chronic obstructive pulmonary disease using the Aeonose® electronic nose.

OBJECTIVES: There is a high unmet need in a non-invasive screening of lung cancer (LC). We conducted this single-center trial to evaluate the effectiveness of the electronic nose Aeonose ® in LC recognition. MATERIALS AND METHODS: Exhaled volatile organic compound (VOC) signatures were collected by Aeonose ® in 42 incident and 78 prevalent LC patients, of them 29 LC patients in complete remission (LC CR), 33 healthy controls (HC) and 23 COPD patients. By dichotomous comparison of VOC's between incident LC and HC, a discriminating algorithm was established and also applied to LC CR and COPD subjects. Area under Curve (AUC), sensitivity, specificity and Matthews's correlation coefficient (MC) were used to interpret the data. RESULTS: The established algorithm of Aeonose ® signature allowed safe separation of LC and HC, showing an AUC of 0.92, sensitivity of 0.84 and a specificity of 0.97. When tested in a blinded fashion, the device recognized 19 out of 29 LC CR patients (=65.5%) as LC-positive, of which only five developed recurrent LC later on (after 18.6 months [Formula: see text]; mean value [Formula: see text]). Unfortunately, the algorithm also recognized 11 of 24 COPD patients as being LC positive (with only one of the 24 COPD patients developing LC 56 months after the measurement). CONCLUSION: The Aeonose ® revealed some potential in distinguishing LC from HC, however, with low specificity when applying the algorithm in a blinded fashion to other disease cohorts. We conclude that relevant VOC signals originating from comorbidities in LC such as COPD may have erroneously led to the separation between LC and controls. CLINICAL TRIAL REGISTRATION: (NCT02951416).

Exploring the Ability of Electronic Nose Technology to Recognize Interstitial Lung Diseases (ILD) by Non-Invasive Breath Screening of Exhaled Volatile Compounds (VOC): A Pilot Study from the European IPF Registry (eurIPFreg) and Biobank.

BACKGROUND: There is an increasing interest in employing electronic nose technology in the diagnosis and monitoring of lung diseases. Interstitial lung diseases (ILD) are challenging in regard to setting an accurate diagnosis in a timely manner. Thus, there is a high unmet need in non-invasive diagnostic tests. This single-center explorative study aimed to evaluate the usefulness of electronic nose (Aeonose®) in the diagnosis of ILDs. METHODS: Exhaled volatile organic compound (VOC) signatures were obtained by Aeonose® in 174 ILD patients, 23 patients with chronic obstructive pulmonary disease (COPD), and 33 healthy controls (HC). RESULTS: By dichotomous comparison of VOC's between ILD, COPD, and HC, a discriminating algorithm was established. In addition, direct analyses between the ILD subgroups, e.g., cryptogenic organizing pneumonia (COP, n = 28), idiopathic pulmonary fibrosis (IPF, n = 51), and connective tissue disease-associated ILD (CTD-ILD, n = 25) were performed. Area under the Curve (AUC) and Matthews's correlation coefficient (MCC) were used to interpret the data. In direct comparison of the different ILD subgroups to HC, the algorithms developed on the basis of the Aeonose® signatures allowed safe separation between IPF vs. HC (AUC of 0.95, MCC of 0.73), COP vs. HC (AUC 0.89, MCC 0.67), and CTD-ILD vs. HC (AUC 0.90, MCC 0.69). Additionally, to a case-control study design, the breath patterns of ILD subgroups were compared to each other. Following this approach, the sensitivity and specificity showed a relevant drop, which results in a poorer performance of the algorithm to separate the different ILD subgroups (IPF vs. COP with MCC 0.49, IPF vs. CTD-ILD with MCC 0.55, and COP vs. CT-ILD with MCC 0.40). CONCLUSIONS: The Aeonose® showed some potential in separating ILD subgroups from HC. Unfortunately, when applying the algorithm to distinguish ILD subgroups from each other, the device showed low specificity. We suggest that artificial intelligence or principle compound analysis-based studies of a much broader data set of patients with ILDs may be much better suited to train these devices.