Identification of Multiple Pulmonary Diseases Using Volatile Organic Compounds Biomarkers in Human Exhaled Breath

Recruiting

• Conditions: Lung Cancer; Pulmonary Tuberculosis; Emphysema; Lung Infection; Pulmonary Fibrosis; Bronchial Asthma; Cystic Fibrosis of the Lung; Interstitial Lung Disease; Bronchitis; Pulmonary Embolism
• Interventions: Other: Gas chromatography-mass spectrometry(GC-MS) and micro Gas Chromatography-photoionisation detector (μGC-PID) system

• Registration Number: NCT06528418
• Lead Sponsor: ChromX Health

Brief Summary

The goal of this observational study is to develop an advanced expiratory algorithm model utilizing exhaled breath volatile organic compound (VOC) marker molecules. This model aims to accurately diagnose mutiple pulmonary diseases. The primary objectives it strives to accomplish are:

1. To assess the diagnostic accuracy of an exhaled breath VOC-assisted diagnostic artificial intelligence (AI) model in diagnose several common pulmonary diseases.

2. To assess the diagnostic accuracy of an exhaled breath VOC-assisted diagnostic artificial intelligence (AI) model in diagnose more pulmonary diseases.

Detailed Description

This is a prospective, cross-sectional, observational cohort study aimed at recruiting 10,000 participants with multiple pulmonary disease, including lung cancer, lung infection, chronic obstructive pulmonary disease (COPD), bronchitis, pulmonary fibrosis, pulmonary embolism, pulmonary arterial hypertension, tuberculosis, lung abscess, emphysema, radioactive lung injury, cystic fibrosis of the lung, Bronchial Asthma, Bronchiectasis, interstitial lung disease (ILD), preserved ratio impaired spirometry (PRISm) etc . Exhaled breath samples from these participants will be collected and analyzed using Gas chromatography-mass spectrometry(GC-MS) and micro Gas Chromatography-photoionisation detector (μGC-PID) system. Upon obtaining the μGC-PID results, a comprehensive evaluation of the diagnostic capabilities of exhaled breath samples in differentiating various pulmonary diseases will be performed, leveraging clinical diagnostic results, CT examination data, and clinical data.

Study Timeline

• Study Start: 2024-06-30
• Study First Submitted: 2024-07-18
• Study First Submitted QC: 2024-07-25
• Study First Posted: 2024-07-30
• Status Verified: 2025-03
• Last Update Submitted: 2025-03-23
• Last Update Posted: 2025-03-26
• Primary Completion: 2026-12-30
• Study Completion: 2027-06-30

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 10000

Inclusion Criteria

• Males or females, age must be 18 years old or above.
• Patients must meet the CT imaging diagnostic criteria for different lung diseases, and patients must be able to provide electronic versions of CT image data.
• Patients must have a clear clinical diagnosis.
• All participants must sign a written informed consent form.

Exclusion Criteria

• Pregnant women.
• Individuals with a history of cancer other than lung disease.
• Individuals who have undergone organ transplants or non-autologous (allogeneic) bone marrow or stem cell transplants.
• Individuals with other severe organic diseases or mental illnesses.
• Individuals with metabolic diseases such as diabetes, hyperlipidemia, etc.
• Any other condition that researchers deem unsuitable for participation in this clinical trial.

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
pulmonary disease	Gas chromatography-mass spectrometry(GC-MS) and micro Gas Chromatography-photoionisation detector (μGC-PID) system	Individuals with abnormalities in lung CT imaging and clinically diagnosed with lung cancer, lung infection, chronic obstructive pulmonary disease (COPD), bronchitis, pulmonary fibrosis, pulmonary embolism, pulmonary arterial hypertension, tuberculosis, lung abscess, emphysema, radioactive lung injury, cystic fibrosis of the lung, Bronchial Asthma, Bronchiectasis, interstitial lung disease (ILD), preserved ratio impaired spirometry (PRISm) etc .
normal individual	Gas chromatography-mass spectrometry(GC-MS) and micro Gas Chromatography-photoionisation detector (μGC-PID) system	Individuals with no abnormalities detected in lung CT imaging.

Primary Outcome Measures

Name	Time	Method
The diagnostic accuracy of an exhaled breath VOC-assisted diagnostic artificial intelligence (AI) model in the diagnosis of several common pulmonary diseases.	2 years	The diagnostic performance of the exhaled breath VOC-assisted diagnostic artificial intelligence (AI) model will be compared with clinical diagnosis and CT/LDCT diagnosis, including sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV).

Secondary Outcome Measures

Name	Time	Method
The diagnostic accuracy of an exhaled breath VOC-assisted diagnostic artificial intelligence (AI) model in the diagnosis of more pulmonary diseases.	2 years	The diagnostic performance of the exhaled breath VOC-assisted diagnostic artificial intelligence (AI) model will be compared with clinical diagnosis and CT/LDCT diagnosis, including sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV).

Trial Locations

Locations (1)

The First Affiliated Hospital of Guangzhou Medical University; 🇨🇳 Guangzhou, Guangdong, China