Early-Stage Lung Cancer, NSCLC, Pulmonary Nodule
Conditions
Keywords
Early-Stage Lung Cancer, Pulmonary Nodule, Urine Proteomics, Non-Invasive Diagnosis, Artificial Intelligence
Brief summary
Brief Summary: The goal of this observational study is to develop a non-invasive urine proteomic diagnostic model to improve early-stage lung cancer detection. The study aims to answer the following main questions: Can urine proteomics reliably differentiate early-stage lung cancer from benign conditions? How does the diagnostic model compare to current clinical and imaging methods in accuracy? Participants will: Provide preoperative urine samples. Undergo proteomic analysis of urine samples. Have clinical, imaging, and proteomic data integrated into an AI-assisted diagnostic model. The study will evaluate the sensitivity and specificity of this innovative diagnostic approach.
Detailed description
Detailed Description: This study focuses on developing a urine proteomic-based diagnostic model to improve the early detection of lung cancer. It leverages non-invasive urine sampling, proteomic analysis, and artificial intelligence to create a high-sensitivity, high-specificity diagnostic tool. The study will recruit 480 participants with suspected early-stage lung cancer (I-IIIA, non-N2). Urine samples will be collected before surgery, and participants will undergo standard imaging and diagnostic evaluations, including chest CT, abdominal ultrasound or CT, brain MRI or CT, and bone scans. The primary objectives of the study include: 1. Biomarker Identification: Identifying differentially expressed urine proteins associated with early-stage lung cancer. 2. Diagnostic Model Construction: Combining proteomic findings with clinical and imaging data to construct a diagnostic model using AI-based algorithms. 3. Validation: Evaluating the model's diagnostic accuracy compared to current clinical practices. Participants will contribute to the advancement of a novel diagnostic method that aims to minimize unnecessary invasive procedures and improve lung cancer prognosis through early and accurate detection.
Interventions
None listed
Sponsors
Beijing Chao Yang Hospital
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to 75 Years
Healthy volunteers
No
Inclusion criteria
1. Male or female participants aged 18 to 75 years. 2. Diagnosed or highly suspected early-stage (I-IIIA, non-N2) non-small cell lung 3.cancer (NSCLC) based on imaging or clinical assessment. 4.No prior anti-cancer treatment, including surgery, chemotherapy, radiotherapy, targeted therapy, or immunotherapy. 5.Able to provide informed consent and willing to comply with the study protocol, including urine sample collection before surgery. 6.Diagnosis confirmed within 42 days post-imaging or preoperative assessment through biopsy or surgical specimen.
Exclusion criteria
1. History of any cancer treatment prior to study enrollment. 2. Presence of metastatic disease (N2 or more advanced staging). 3. Severe comorbid conditions or organ dysfunctions (e.g., renal failure) that could affect urine sample quality or interpretation. 4. Pregnancy or lactation. 5. Participation in another clinical study that could interfere with the outcomes of this study. 6. Inability to comply with the study protocol, including language barriers or cognitive impairments.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Prediction Accuracy of Diagnostic Models | Within 2 weeks post-surgery. | The primary outcome measure is the accuracy of preoperative predictions (sensitivity and specificity) for early-stage non-small cell lung cancer (NSCLC) diagnosis. Predictions are based on: 1. Urine proteomics in the experimental group. 2. Chest CT imaging in the control group. Accuracy will be assessed by comparing preoperative predictions with postoperative pathological findings, including tumor histopathological subtypes, lymph node metastasis, and other pathological factors. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Cut-off Value for Urine Proteomics Diagnostic Test | Within 1 month after data analysis. | Determination of the optimal cut-off value for urine proteomic markers to maximize diagnostic sensitivity and specificity for early-stage non-small cell lung cancer (NSCLC). |
| Comparative Performance of Diagnostic Models | Within 2 months post-surgery. | Evaluation of the diagnostic performance (sensitivity, specificity, and area under the curve \[AUC\]) of the urine proteomic model versus chest CT imaging for predicting tumor histopathological subtypes, lymph node metastasis, and staging. |
| Long-term Diagnostic Effectiveness | Up to 2 years post-surgery. | Evaluation of the correlation between preoperative diagnostic accuracy and 2-year postoperative clinical outcomes (e.g., recurrence rates, survival outcomes). |
Countries
China
Contacts
Primary ContactBin Hu, MD
Outcome results
None listed