Related Experiment Video
Updated: Aug 13, 2026
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
A retrospective cohort study integrating invasive mucinous adenocarcinoma into the IASLC grading system for lung
Hanyue Li1, Haoran Liu1, Hui Shi1
1Department of Thoracic Surgery, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Background:
The current International Association for the Study of Lung Cancer (IASLC) grading system for invasive pulmonary adenocarcinoma excludes invasive mucinous adenocarcinoma (IMA) and mixed IMA, limiting its prognostic scope. We aimed to refine the IASLC grading system by incorporating IMA and mixed IMA, and to validate it in large-scale cohorts.
Methods:
This single-institutional study included 692 patients with stage I-III lung invasive adenocarcinoma from Shanghai Chest Hospital (training cohort) and 7,862 from the Surveillance, Epidemiology, and End Results (SEER) database (validation cohort). We introduced IMA and reclassified the IASLC grading system. Prognostic performance was assessed using Harrell C-index, time-dependent receiver operating characteristic (ROC) curves and areas under the curve (AUCs). Overall survival (OS) curves were estimated via the Kaplan-Meier method, with log-rank test for difference comparison.
Results:
Mucinous predominant tumors with <20% of high-grade patterns (solid, micro papillary, complex glandular patterns) were classified as the Grade 2 (moderately differentiated). The proposed expanded grading system demonstrated improved prognostic accuracy, with C-index and AUC values of 0.713 and 0.739 in the training cohort, and 0.707 and 0.742 in the validation cohort, respectively. The 5-year OS rates for Grade 1, Grade 2, and Grade 3 were 87.5%, 73.1%, and 55.5% in the training cohort (P<0.001), and 80.2%, 67.3%, and 60.0% in the validation cohort (P<0.001). The proposed expanded grading system demonstrated superior prognostic performance compared to the current IASLC grading system in both cohorts.
Conclusions:
The proposed expanded IASLC grading system was practical and prognostic for lung invasive adenocarcinoma, and the introduction of IMA could improve its applicability.