Lymph node metastasis (LNM) is an independent prognostic factor for patients with gastric cancer (GC), and an accurate lymph node (LN) staging system is crucial for guiding adjuvant therapy and assessing patient prognosis. The most commonly used staging systems for GC are the tumor-node-metastasis (TNM) system developed by the Union for International Cancer Control (UICC) and the American Joint Committee on Cancer (AJCC), as well as the Japanese classification system. The N staging system in both classification methods has undergone multiple revisions and improvements. Early versions classified N stage based on the distance between the tumor margin and metastatic LNs. Over time, this shifted to a system based on the number of metastatic LNs, significantly improving staging precision. To further enhance the accuracy of N staging, the researchers have introduced new concepts such as the metastatic lymph nodes ratio (LNR), the log odds of positive lymph nodes (LODDS), and the negative lymph node count (NLNC). These new parameters have demonstrated better prognostic accuracy than the eighth edition of the UICC/AJCC N staging system. In addition, artificial intelligence (AI) has emerged as a rapidly evolving domain, demonstrating exponential growth in algorithmic sophistication and computational applications. Machine learning (ML) models and deep learning (DL) models have demonstrated superior performance in assessing LNM, aiding in staging, and predicting prognosis in GC. This review provides a systematic overview of the historical evolution, current practices, and recent innovations in GC lymph node staging, aiming to inform the development of next-generation prognostic frameworks.
Lin et al. (Wed,) studied this question.