To Conduct Multi-omics Integrated Studies in Peripheral Blood, Such as Fragment Omics, Metabolomics and Epigenetics, and Establish Non-invasive Dynamic Follow-up Monitoring Programs During Perioperative and Postoperative Periods (Observational Study)

To Conduct Multi-omics Integrated Studies in Peripheral Blood, Such as Fragment Omics, Metabolomics and Epigenetics, and Establish Non-invasive Dynamic Follow-up Monitoring Programs During Perioperative and Postoperative Periods (Observational Study)

This project aims to innovatively integrate multi-omics data, including plasma metabolomics, radiomics, and cfDNA multi-level information, combined with survival data (e.g., RFS), to establish a novel multidimensional approach for noninvasive postoperative recurrence monitoring in lung cancer using artificial intelligence algorithms. The goal is to develop a new noninvasive recurrence monitoring system for lung cancer.

This project is a prospective observational study designed to comprehensively integrate plasma metabolomic, radiomic, and epigenomic data to develop a predictive model for postoperative recurrence risk in lung cancer. The study will retrospectively enroll 200 patients who underwent radical surgery after neoadjuvant therapy, and prospectively enroll 100 additional post-radical-surgery lung cancer patients who received neoadjuvant treatment as a validation cohort. Peripheral blood samples will be collected at multiple timepoints for metabolomic profiling. Unsupervised clustering, random forest algorithms, and Wilcoxon tests will be applied to identify recurrence-related features and construct a recurrence prediction model.Additionally, using preoperative and first postoperative follow-up CT imaging data, a deep learning-based 3D ResNet will be employed to generate radiomic recurrence risk scores for each patient. Plasma cfDNA will undergo low-pass whole-genome sequencing and methylation analysis to extract multi-dimensional recurrence-associated features. Finally, the study will innovatively utilize the DeepProg deep learning framework to integrate radiomic, cfDNA, and plasma metabolomic data into a non-invasive multi-omics model. Combined with survival data, this model will predict recurrence risk, ultimately achieving high-accuracy stratification of patients' postoperative recurrence probability.

Inclusion Criteria:

1. Signed written informed consent.
2. Male or female, aged ≥ 18 and < 85 years.
3. Radical resection performed, pathologic stage IB-IIIA (8th TNM) non-small-cell lung cancer.
4. Tumor tissue and blood samples obtainable at all protocol-specified time-points.
5. No pure ground-glass nodule on imaging.
6. Completed standard neoadjuvant immunotherapy combined with platinum-based chemotherapy.

Exclusion Criteria:

1. Postoperative pathology shows other than NSCLC, including but not limited to benign lesions, small-cell carcinoma, metastasis, or indeterminate/inadequate histology.
2. Insufficient or poor-quality blood or tissue samples.
3. Pure ground-glass nodule on imaging.
4. History of any malignancy within the past 5 years.
5. Contraindication to surgery preventing radical resection.
6. Non-radical (R2) resection.
7. Pathologic stage IIIB-N3, IIIC, or IV on paraffin sections.
8. Refusal or withdrawal of informed consent.
9. Any condition deemed unsuitable by the investigator (e.g., perioperative blood transfusion, severe psychiatric disorder precluding follow-up).