Early screening and diagnosis of lung nodules using non-invasive biomarkers and imaging.

Research on Precise Early Screening and Diagnosis of Pulmonary Nodules Based on a Novel Multidimensional Non-invasive Approach

This project will test whether combining breath and blood metabolite profiles with CT image features and blood DNA can better detect early lung cancer in adults with small pulmonary nodules.

Quick facts

• Study type: Observational
• Enrollment: 1800 (estimated)
• Ages: 18 Years and up
• Sex: All
• Sponsor: Peking University People's Hospital (Academic / other)
• Drugs / interventions: chemotherapy
• Locations: 1 site (Beijing, Beijing Municipality)
• Trial ID: NCT07370077 on ClinicalTrials.gov

What this trial studies

This is a prospective observational effort enrolling patients with pulmonary nodules who undergo surgical resection and definitive pathology, along with matched benign-nodule subjects and healthy controls. The protocol collects exhaled breath and plasma metabolomics, CT radiomics, and liquid biopsy (ctDNA) samples within one month before biopsy or surgery. Large-sample multi-omics data will be integrated using machine learning and deep learning models (for example SVM, HRNet, PAResNet) to build a multi-dimensional, sequential decision system that uses metabolomics for primary screening and radiomics/ctDNA for subsequent differentiation and diagnosis. The goal is to reduce false positives from CT screening and provide a non- or minimally-invasive pathway to more accurate early diagnosis.

Who should consider this trial

Good fit: Adults over 18 with pulmonary nodules under 3 cm who can provide exhaled breath, blood, and raw CT data collected within one month before planned biopsy or surgical resection and who have no prior anti-tumor treatment are ideal candidates.

Not a fit: Patients with active infection, severe comorbidities, abnormal liver or kidney function, prior malignancy, or without resected lesions and definitive pathology are unlikely to benefit from this protocol.

Why it matters

Potential benefit: If successful, this approach could lower CT false positives, reduce unnecessary surgeries, and enable earlier, more precise detection of lung cancer.

How similar studies have performed: Individual components such as ctDNA, radiomics, and metabolomics have shown promise in prior research, but combining them into a sequential multi-omics diagnostic pathway remains relatively novel.

Eligibility criteria

Inclusion Criteria

1. Age \>18 years old.
2. Availability of both exhaled breath and peripheral blood samples, and raw CT image data; the collection time is within one month before biopsy or surgical resection, and the subject has not received any treatment in between.
3. Pulmonary nodular lesions identified by chest CT with a diameter \< 3 cm.
4. Pulmonary nodular lesions must be surgically resected and have complete, definitive pathological information regarding their benign or malignant nature.
5. No prior history of malignant tumors.
6. Has not received anti-tumor treatments such as radiotherapy, chemotherapy, or targeted therapy.
7. Signed informed consent.

Exclusion Criteria

1. Missing clinical data or incomplete sample collection.
2. Presence or suspicion of active infection or other severe co-morbidities.
3. Abnormal liver or kidney function.
4. Indefinite or inconclusive postoperative pathological results.

Where this trial is running

Beijing, Beijing Municipality

• Peking University People's Hospital — Beijing, Beijing Municipality, China (Recruiting)

Study contacts

• Study coordinator: Fan Yang, Chief Physician

Conditions Lung Cancer; lung cancer; Early Diagnosis；Metabolomics；Genomics