New model uses blood tests to predict lung cancer prognosis

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.

Source:
Journal reference:

Song, S., et al. (2026). Predicting PD-L1+ CD8− status in non-small cell lung cancer tissue from clinical indicators using machine learning. Chinese Medical Journal. DOI: 10.1097/CM9.0000000000004257. https://www.ovid.com/jnls/cmj/fulltext/10.1097/cm9.0000000000004257~predicting-pd-l1-cd8-status-in-non-small-cell-lung-cancer

Comments

The opinions expressed here are the views of the writer and do not necessarily reflect the views and opinions of News Medical.
Post a new comment
Post

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.

You might also like...
Targeting two cancer cell defenses may offer new treatment strategy