Objectives: To present a comprehensive review of the current state of artificial intelligence (AI) applications in lung cancer management, spanning the preoperative, intraoperative, and postoperative phases.Methods: A review of the literature was conducted using PubMed, EMBASE and Cochrane, including relevant studies between 2002 and 2023 to identify the latest research on artificial intelligence and lung cancer.Conclusion: While AI holds promise in managing lung cancer, challenges exist. In the preoperative phase, AI can improve diagnostics and predict biomarkers, particularly in cases with limited biopsy materials. During surgery, AI provides real-time guidance. Postoperatively, AI assists in pathology assessment and predictive modeling. Challenges include interpretability issues, training limitations affecting model use and AI’s ineffectiveness beyond classification. Overfitting and global generalization, along with high computational costs and ethical frameworks, pose hurdles. Addressing these challenges requires a careful approach, considering ethical, technical, and regulatory factors. Rigorous analysis, external validation, and a robust regulatory framework are crucial for responsible AI implementation in lung surgery, reflecting the evolving synergy between human expertise and technology.

Oligometastatic non-small cell lung cancer (NSCLC) is defined anatomically by a threshold of five or fewer metastatic lesions across three or fewer organs. That definition is a proxy for a biological question it cannot answer: whether the metastatic process has been arrested at a stage where eradication of all detectable disease is curative. Randomized phase II trials of local consolidative therapy have shown median progression-free survival gains of 6.2 and 8.0 months and, in one trial, a median overall survival of 41.2 months vs. 17.0 months, yet median progression-free survival with local therapy did not exceed 14.2 months, and the phase II/III NRG-LU002 trial found no significant survival benefit from adding local therapy to maintenance therapy. Circulating tumor DNA (ctDNA) measures molecular disease burden. In resectable NSCLC, preoperative ctDNA detection is associated with a higher risk of relapse; in oligometastatic disease, the baseline sample is instead the quantitative reference for response. ctDNA kinetics during induction therapy track systemic response before any operation, although no response threshold has been validated, and postoperative molecular residual disease anticipates radiological relapse by a median of approximately 5 months. This review synthesizes the evidence linking liquid biopsy to surgical decision-making and proposes, as a hypothesis for prospective testing, a dynamic risk stratification framework anchored on five plasma sampling points. We separate established prognostic evidence from untested hypotheses, address oncogene-driven and other oligometastatic states, and define the assay requirements, confounders and trial designs needed before ctDNA can select patients for or against thoracic resection.

This unstructured narrative review appraises lymph node evaluation as an accountability measure in non-small cell lung cancer surgery. Commission on Cancer Operative Standard 5.8 requires assessment of at least three mediastinal and one hilar nodal station for every curative-intent resection, with accreditation consequences. We ask what the standard has been validated to measure, and at which level of attribution. Neither the count-based nor the station-based threshold was derived from interventional evidence. The reported value reflects surgeon technique, surgeon-led specimen process, pathologist effort, operative platform, and case mix together, which bears on attribution to individual surgeons rather than on the legitimacy of the measure. We separate two causal models linking nodal evaluation to survival and examine each against evidence identified by a reproducible search, including the biomarker-directed and neoadjuvant eras and sublobar resection. Anchored to the National Quality Forum and Donabedian criteria, we conclude that Standard 5.8 is well-supported as an institutional minimum standard for staging completeness, that the evidence identified does not yet support extension to individual-surgeon benchmarking, that compliance should be reported stratified by resection type, and that low sublobar compliance most plausibly identifies a real quality problem. Nothing here reduces the obligation to perform systematic nodal assessment.