HUST Team Develops Model to Predict High-Risk NSCLC Status

Chinese Medical Journals Publishing House Co., Ltd.

Lung cancer is a globally prevalent malignant tumor, with non-small cell lung cancer (NSCLC) being its predominant subtype. For patients with resectable NSCLC, surgical resection remains a cornerstone of curative-intent treatment. However, postoperative outcomes remain heterogeneous, even among patients with similar clinicopathological stages, highlighting the need for improved biomarkers and risk stratification strategies. Programmed death-ligand 1 (PD-L1) expression and CD8⁺ T-cell infiltration represent two complementary aspects of the tumor immune microenvironment, and their combined assessment may improve prognostic stratification compared with either marker alone. This study systematically elucidates the impact of combined PD-L1 expression and CD8-positive T-cell infiltration (PD-L1/CD8 status) in NSCLC tumor tissue on patient prognosis. Furthermore, the authors innovatively developed a machine learning algorithm-based model using preoperative blood indicators to predict tumor tissue PD-L1/CD8 status.

This study enrolled 844 patients with NSCLC who underwent surgical treatment at the Thoracic Surgery Departments of Wuhan Union Hospital and Renmin Hospital of Wuhan University between March 2012 and November 2022. Patients were stratified into four groups based on tumor tissue PD-L1/CD8 status. Kaplan–Meier analysis showed significant differences in overall survival (OS) among the four PD-L1/CD8 subgroups (P = 0.001). Given the substantial impact of pathological type, tumor stage, and grade on prognosis, hierarchical analysis was performed to evaluate the prognostic significance of PD-L1/CD8 status across subgroups. Although the PD-L1+ CD8− subgroup showed the shortest OS among stage I patients, the difference did not reach statistical significance among the four groups (P = 0.063). In contrast, a significant difference in OS was observed among the four PD-L1/CD8 subgroups in patients with stage II–IV disease (P = 0.014).

For patients with adenocarcinoma, the PD-L1+ CD8− group had the worst prognosis (P = 0.001). At the T1 stage, OS differed significantly among the four PD-L1/CD8 subgroups (P = 0.001), while no significant differences were observed among the four groups in T2–T4-stage

patients. In analyses stratified by clinical N category, significant differences in OS were found among the four PD-L1/CD8 subgroups in patients with N0 disease and those with N1–3 disease (P = 0.032 and P = 0.033, respectively). Univariate and multivariate analyses further confirmed PD-L1+ CD8− status as an independent and pervasive adverse prognostic factor.

Given the clinical significance of PD-L1+ CD8− status, we developed predictive models to identify patients with this immunophenotype using preoperative indicators. After matching for sex and age, patients were divided into training (N = 382), test (N = 82), internal validation (N = 82), and external validation (N = 298) sets. By comparing five machine learning models—logistic regression, extreme gradient boosting (XGBoost), decision tree, random forest, and light gradient boosting machine (LightGBM)—alongside a stacked model integrating these algorithms, the stacked model demonstrated optimal performance. It exhibited exceptional discriminative ability across all datasets, with area under the curve (AUC) values of 0.998 (training), 0.700 (test), 0.853 (internal validation), and 0.783 (external validation).

Our study had some limitations. First, the sample size was modest, and the retrospective design makes selection bias and residual confounding unavoidable. Second, although external validation was performed, both cohorts were derived from hospitals within the same region, and additional multicenter validation is required to establish the generalizability of the model. Third, the identified predictors should be interpreted as contributors to model performance rather than as mechanistic determinants of PD-L1+ CD8− status, and the biological basis of these associations warrants further investigation.

Reference

Titles of original papers: Predicting PD-L1+ CD8− status in non-small cell lung cancer tissue from clinical indicators using machine learning

Journal: Chinese Medical Journal

DOI: https://doi.org/10.1097/CM9.0000000000004257

About Jin Yang, Professor at Huazhong University of Science and Technology, China

Dr. Jin Yang is a Level II Professor, Chief Physician, and doctoral supervisor in the Department of Respiratory and Critical Care Medicine at Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, China. He is a recipient of the Chinese Physician Award. Professor Yang serves on the Respiratory Branch and the Scientific Research Management Branch of the Chinese Medical Association, and on the Standing Committee of the Respiratory Physician Branch of the Chinese Medical Association. His professional contributions and academic appointments reflect his involvement in respiratory medicine and clinical research.

Funding information

This work was supported by the National Key Research and Development Program of China (Nos. 2022YFF1203300 and 2023YFC3043505), the National Natural Science Foundation of China (No. 82330003), the Natural Science Foundation of Hubei Province (Nos. 2022CFB238 and 2026AFB247), and the Hubei Provincial Key Research and Development Program (No. 2022BCA016).

/Public Release. This material from the originating organization/author(s) might be of the point-in-time nature, and edited for clarity, style and length. Mirage.News does not take institutional positions or sides, and all views, positions, and conclusions expressed herein are solely those of the author(s).View in full here.