Differentiating interstitial lung diseases from other respiratory diseases using electronic nose technology

Area of Science:

• Pulmonary Medicine
• Biomedical Engineering
• Diagnostic Technology

Background:

• Interstitial lung disease (ILD) diagnosis is challenging due to overlapping symptoms with other respiratory diseases, often leading to delayed recognition and poorer outcomes.
• Early detection of ILD is crucial for improving patient prognosis.
• Electronic nose (eNose) technology offers a non-invasive method to analyze volatile organic compounds in exhaled breath for disease detection.

Purpose of the Study:

• To evaluate the accuracy of eNose technology in differentiating breath profiles of patients with ILD from those with asthma, chronic obstructive pulmonary disease (COPD), and lung cancer.
• To assess the potential of eNose as a point-of-care diagnostic tool for ILD.

Main Methods:

• A cross-sectional study included 161 patients with ILD and 161 patients with asthma, COPD, or lung cancer.
• Exhaled breath was analyzed using an eNose (SpiroNose) device.
• Data were analyzed using partial least squares discriminant and receiver operating characteristic analyses, with datasets split for training and independent validation.

Main Results:

• eNose breath profiles accurately differentiated ILD from all other studied respiratory diseases with an Area Under the Curve (AUC) of 0.99 in the test set.
• High AUC values were achieved when distinguishing ILD from asthma (1.00), COPD (0.96), and lung cancer (0.98).
• These findings remained consistent even after excluding patients who had never smoked.

Conclusions:

• eNose technology can accurately distinguish exhaled breath profiles of ILD patients from those with other common respiratory diseases.
• eNose demonstrates significant potential as an accessible, non-invasive point-of-care test for identifying ILD among patients presenting with respiratory symptoms.
• This technology could facilitate earlier referral and diagnosis for suspected ILD cases.