Research on Early Screening and Diagnosis of Pulmonary Nodules Based on Novel Non-invasive Technologies.

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

This is a prospective observational study designed to address the clinical challenge posed by the high false-positive rate associated with CT imaging in early lung cancer screening.

The primary objective is to develop a multi-omics technology for early lung cancer screening, leveraging **exhaled breath metabolomics, plasma metabolomics, radiomics, and liquid biopsy. Based on large-sample detection data, the study aims to construct a **multi-dimensional, sequential decision-making system**. This system utilises the high accessibility of metabolomics for primary screening, combined with radiomics and ctDNA technologies for subsequent **differentiation and definitive diagnosis.

The research plans to prospectively enrol 300 patients with non-small cell lung cancer, along with corresponding subjects with benign nodules and healthy controls. By optimising the model using machine learning and deep learning algorithms (such as SVM, HRNet, and PAResNet), the ultimate goal is to establish a novel lung cancer early screening system characterised by **high sensitivity, high accuracy, and high accessibility**, enabling the precise differentiation and screening of healthy individuals, benign pulmonary nodules, and early-stage lung cancer.

Study Overview

• Status: Recruiting
• Conditions: Lung Cancer
• Intervention / Treatment: Diagnostic test: Employing multi-omics diagnostic approaches to enhance diagnostic efficacy

Detailed Description

Lung cancer is one of the malignant tumours with a poor prognosis. Data from 61 countries globally show that the 5-year survival rate for lung cancer patients is only 10.0% to 20.0%. Since 2005, China has launched several major national public health service projects, including lung cancer screening initiatives such as the Rural Cancer Early Diagnosis and Treatment Program and the Urban Cancer Early Diagnosis and Treatment Program, gradually establishing a national network for lung cancer screening and early diagnosis/treatment. Although China has made significant progress in the diagnosis and treatment of lung cancer, the 5-year survival rate for the Chinese population was 19.7% between 2012 and 2015. The prognosis for lung cancer remains poor, making early diagnosis and treatment an essential guide for our research to improve patient survival.

CT scanning has become the recognised standard tool for lung cancer screening and early diagnosis. However, the false-positive rate for highly suspected nodules remains high, at 30% to 40%, and the accuracy of preoperative lesion assessment needs improvement. Therefore, establishing a highly sensitive, highly specific, minimally invasive, or even non-invasive, precise diagnostic method for early lung cancer, thereby avoiding unnecessary surgery, is a critical clinical problem urgently needing resolution, and is of great significance for advancing China's level of early lung cancer diagnosis.

This study will first systematically evaluate the efficacy and accessibility of **exhaled breath metabolomics, plasma metabolomics, and radiomics in early lung cancer screening and diagnosis using a prospective database. Based on large-sample detection data, we will construct a novel multi-dimensional stereo lung cancer early screening system. This system uses exhaled breath metabolomics and plasma metabolomics for initial screening. Then it integrates multiple omics technologies, including radiomics, cfDNA methylation and fragmentomics, and the original metabolomics data, for differentiation and definitive diagnosis. Modelling algorithms will be optimised using methods such as cross-validation, internal validation, and stratified validation to form a stable lung cancer screening system.

• Study Type: Observational
• Enrollment (Estimated): 1800

Contacts and Locations

• Study Contact: Name: Fan Yang, Chief Physician; Phone Number: 0086-88326657; Email: yangfan@pkuph.edu.cn
• Study Contact Backup: Name: zhong Ke Chen; Phone Number: +86-010-88325983; Email: mdkzchen@163.com

Study Locations

• China
  • Beijing Municipality
    • Beijing, Beijing Municipality, China, 10010
      • Recruiting
      • Peking University People's Hospital
      • Contact: Kezhong Chen; Phone Number: 86-13488752289; Email: chenkezhong@pkuph.edu.cn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

This study proposes to prospectively recruit participants with early-stage non-small cell lung cancer, benign pulmonary lesions (including tuberculosis, hamartomas, inflammatory conditions, etc.), and healthy individuals undergoing medical examinations at Peking University People's Hospital, Rongcheng County People's Hospital in Xiong'an, Tangshan Workers' Hospital, Union Hospital affiliated with Tongji Medical College of Huazhong University of Science and Technology, and the 731 Hospital of China Aerospace Science and Industry Corporation.

Description

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.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

Healthy, Benign, Malignant; Incorporating healthy individuals, benign nodules, and malignant nodules into the study population to reflect real-world screening scenarios.

Diagnostic test: Employing multi-omics diagnostic approaches to enhance diagnostic efficacy; The study will first systematically evaluate the efficacy and accessibility of metabolomics and radiomics in the early screening and diagnosis of lung cancer through retrospective data analysis of prospective databases and prospective cohort validation. Based on large-scale detection data, a novel multidimensional early-stage lung cancer screening system will be established. This system will employ metabolomics as the initial screening method, supplemented by multi-omics approaches including radiomics, cfDNA methylation fragment detection, TCR detection, and metabolomics for differential diagnosis and confirmation.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
diagnostic sensitivity	The primary research indicators in this study focus on evaluating the diagnostic efficacy of multi-omics models for early-stage lung cancer. Firstly, diagnostic sensitivity serves as the core metric to assess the model's ability to correctly identify lung cancer patients, with a target value set at no less than 85%. Diagnostic specificity measures the model's capacity to correctly exclude non-lung cancer individuals, with a target value set at no less than 90%. The area under the receiver operating characteristic curve serves as a comprehensive indicator of the model's discriminative capability, with a target value exceeding 0.90 to ensure robust overall diagnostic performance. Regarding early detection capability, the detection rate for stage I lung cancer represents a key primary indicator in this study, specifically encompassing the detection of stage IA and IB lung cancer. This is because patients at this stage typically present with the optimal surgical resection opportunities an	From enrollment to the end of treatment at 6-8 weeks

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Positive predictive value; negative predictive value and et al.	Supplementary assessments of model performance were conducted across multiple dimensions. Regarding supplementary diagnostic efficacy metrics, the positive predictive value reflects the proportion of subjects with positive screening results who genuinely have lung cancer, a crucial indicator for evaluating the clinical utility of screening strategies. The negative predictive value assesses the reliability of excluding lung cancer when screening results are negative, providing significant reference value for reducing the risk of missed diagnoses. Positive likelihood ratios and negative likelihood ratios, as diagnostic performance metrics unaffected by prevalence, provide a more objective reflection of the model's diagnostic value. The Youden index, as a composite measure of sensitivity and specificity, is employed to determine the optimal diagnostic threshold.	35 months

Collaborators and Investigators

• Sponsor: Chen KeZhong
• Collaborators: Union Hospital, Tongji Medical College, Huazhong University of Science and Technology; Tangshan Workers' Hospital; School of Medical Science and Engineering, Beihang University; China Aerospace Science and Industry Corporation No. 731 Hospital; Rongcheng County People's Hospital

Study record dates

Study Major Dates

• Study Start (Actual): December 31, 2022
• Primary Completion (Estimated): June 30, 2026
• Study Completion (Estimated): June 30, 2026

Study Registration Dates

• First Submitted: January 19, 2026
• First Submitted That Met QC Criteria: January 19, 2026
• First Posted (Actual): January 27, 2026

Study Record Updates

• Last Update Posted (Actual): January 27, 2026
• Last Update Submitted That Met QC Criteria: January 19, 2026
• Last Verified: January 1, 2026

More Information

Terms related to this study

• Keywords: lung cancer; Early Diagnosis；Metabolomics；Genomics
• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Respiratory Tract Diseases; Lung Diseases; Respiratory Tract Neoplasms; Thoracic Neoplasms; Lung Neoplasms
• Other Study ID Numbers: 2023XAGG0071

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No