Association of artiﬁcial intelligence-based immunoscore with the efﬁcacy of chemoimmunotherapy in patients with advanced non-squamous non-small cell lung cancer - a multicentre retrospective study

Sep 22, 2026

Upload by Eden

Chemoimmunotherapy benefits only a subset of patients with advanced non-squamous non-small cell lung cancer, making reliable biomarkers essential for identifying responders. This study develops an artificial intelligence–based immunoscore and evaluates its patho-immunoscore value for predicting clinical outcomes. The analyzer is trained on 1,333 TCGA-LUAD whole-slide images and validated in CPTAC-LUAD and ORIENT-11 cohorts, where high patho-immunoscore associates with longer progression-free survival under chemoimmunotherapy.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Purpose

Methods

Results

Conclusion

Introduction

Background on lung cancer and NSCLC

Rationale for immunoscore and predictive biomarkers

TYPE Original Research PUBLISHED 06 November 2024 DOI 10.3389/fimmu.2024.1485703 OPEN ACCESS EDITED BY Yanqing Liu, Columbia University, United States REVIEWED BY Li Li, University of California, San Francisco, United States Meizi Liu, Washington University in St. Louis, United States Yuan Liu, University of Illinois at Urbana-Champaign, United States *CORRESPONDENCE Yunpeng Yang [yangyp@sysucc.org.cn](yangyp@sysucc.org.cn)[ ](yangyp@sysucc.org.cn)Li Zhang [zhangli6@mail.sysu.edu.cn](zhangli6@mail.sysu.edu.cn) †These authors have contributed equally to this work RECEIVED 24 August 2024 ACCEPTED 17 October 2024 PUBLISHED 06 November 2024 CITATION Liu J, Sun D, Xu S, Shen J, Ma W, Zhou H, Ma Y, Zhang Y, Fang W, Zhao Y, Hong S, Zhan J, Hou X, Zhao H, Huang Y, He B, Yang Y and Zhang L (2024) Association of artiﬁcial intelligence-based immunoscore with the efﬁcacy of chemoimmunotherapy in patients with advanced non-squamous non-small cell lung cancer: a multicentre retrospective study. Front. Immunol. 15:1485703 . doi: 10.3389/fimmu.2024.1485703 COPYRIGHT © 2024 Liu, Sun, Xu, Shen, Ma, Zhou, Ma, Zhang, Fang, Zhao, Hong, Zhan, Hou, Zhao, Huang, He, Yang and Zhang. This is an openaccess article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Association of artiﬁcial intelligence-based immunoscore with the efﬁcacy of chemoimmunotherapy inpatients with advanced non-squamous non-small cell lung cancer: a multicentre retrospective study Jiaqing Liu 1,2,3,4†, Dongchen Sun 1,2,3,5†, Shuoyu Xu 6†, Jiayi Shen 1,2,3,7†, Wenjuan Ma 1,2,3,4†, Huaqiang Zhou 1,2,3,5, Yuxiang Ma 1,2,3,5, Yaxiong Zhang 1,2,3,5, Wenfeng Fang 1,2,3,5, Yuanyuan Zhao 1,2,3,5, Shaodong Hong 1,2,3,5, Jianhua Zhan 1,2,3,5, Xue Hou 1,2,3,5, Hongyun Zhao 1,2,3,5, Yan Huang 1,2,3,5, Bingdou He 6, Yunpeng Yang 1,2,3,5* and Li Zhang 1,2,3,5* 1State Key Laboratory of Oncology in South China, Guangzhou, China, 2Collaborative Innovation Center for Cancer Medicine, Guangzhou, China, 3Guangdong Provincial Clinical Research Center for Cancer, Guangzhou, China, 4 Department of Intensive Care Unit, Sun Yat-sen University Cancer Center, Guangzhou, China, 5 Department of Medical Oncology, Sun Yat-sen University Cancer Center, Guangzhou, China, 6 Bio-totem Pte Ltd, Suzhou, China, 7 Department of Anesthesiology, Sun Yat-sen University Cancer Center, Guangzhou, China Purpose: Currently, chemoimmunotherapy is effective only in a subset of patients with advanced non-squamous non-small cell lung cancer. Robust biomarkers for predicting the efﬁcacy of chemoimmunotherapy would be useful to identify patients who would beneﬁt from chemoimmunotherapy. The primary objective of our study was to develop an artiﬁcial intelligence-based immunoscore and to evaluate the value of patho-immunoscore in predicting clinical outcomes in patients with advanced non-squamous non-small cell lung cancer (NSCLC) . Methods: We have developed an artiﬁcial intelligence–powered immunoscore analyzer based on 1,333 whole-slide images from TCGA-LUAD. The predictive efﬁcacy of the model was further validated in the CPTAC-LUAD cohort and the biomarker cohort of the ORIENT-11 study, a randomized, double-blind, phase 3 study. Finally, the clinical signiﬁcance of the patho-immunoscore was evaluated using the ORIENT-11 study cohort. Results: Our immunoscore analyzer achieved good accuracy in all the three cohort mentioned above (TCGA-LUAD, mean AUC: 0.783; ORIENT-11 cohort, AUC: 0 .741; CPTAC-LUAD cohort, AUC: 0 .769) . In the 259 patients treated with chemoimmunotherapy, those with high patho-immu

FAQs

What is the main purpose of the study?

To develop an artificial intelligence-based immunoscore and assess the value of patho-immunoscore in predicting clinical outcomes in patients with advanced non-squamous NSCLC receiving chemoimmunotherapy.

How was the AI-based immunoscore developed and validated?

It was developed using 1,333 TCGA-LUAD whole-slide images, then its predictive performance was validated in the CPTAC-LUAD cohort and the biomarker cohort of ORIENT-11, with further evaluation of clinical significance in the ORIENT-11 study cohort.

What outcome differences were observed with chemoimmunotherapy?

Among 259 patients treated with chemoimmunotherapy, those with high patho-immunoscore had significantly longer median progression-free survival than those with low patho-immunoscore; no significant difference was observed for patients treated with chemotherapy only.

Sep 22, 2026

Upload by Eden