Non-invasive prediction of NSCLC immunotherapy efficacy and tumor microenvironment through unsupervised machine learning-driven CT radiomic subtypes: a multi-cohort study

作者：Yusheng Guo, Bingxin Gong, Yi Li, Peng Mo, Yiqun Chen, Qianqian Fan, Qing Sun, Lianwei Miao, Yuanxi Li, Yunting Liu, Wei Tan, Lian Yang, Chuansheng Zheng · 发表于：International Journal of Surgery · 年份：2025 · DOI：10.1097/js9.0000000000002839 · 被引用次数：13 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Cancer Immunotherapy and Biomarkers、Ferroptosis and cancer prognosis

BACKGROUND: Radiomics analyzes quantitative features from medical images to reveal tumor heterogeneity, offering new insights for diagnosis, prognosis, and treatment prediction. This study explored radiomics based biomarkers to predict immunotherapy response and its association with the tumor microenvironment in non-small cell lung cancer (NSCLC) using unsupervised machine learning models derived from CT imaging. MATERIALS AND METHODS: This study included 1539 NSCLC patients from seven independent cohorts. For 1834 radiomic features extracted from 869 NSCLC patients, K-means unsupervised clustering was applied to identify radiomic subtypes. A random forest model extended subtype classification to external cohorts, model accuracy, sensitivity, and specificity were evaluated. By conducting bulk RNA sequencing (RNA-seq) and single-cell transcriptome sequencing (scRNA-seq) of tumors, the immune microenvironment characteristics of tumors can be obtained to evaluate the association between radiomic subtypes and immunotherapy efficacy, immune scores, and immune cells infiltration. RESULTS: Unsupervised clustering stratified NSCLC patients into two subtypes (Cluster 1 and Cluster 2). Principal component analysis confirmed significant distinctions between subtypes across all cohorts. Cluster 2 exhibited significantly longer median overall survival (35 vs. 30 months, P = 0.006) and progression-free survival (19 vs. 16 months, P = 0.020) compared to Cluster 1. Multivariate Cox regressio...