Qiuying Chen1,2, Lu Zhang1,2, Xiaokai Mo1, Jingjing You1,2, Luyan Chen1,2, Jin Fang1, Fei Wang1, Zhe Jin1,2, Bin Zhang3,4, Shuixing Zhang5,6. 1. Department of Radiology, The First Affiliated Hospital, Jinan University, No. 613, Huangpu West Road, Tianhe District, Guangzhou, 510627, Guangdong, People's Republic of China. 2. Graduate College, Jinan University, Guangzhou, Guangdong, People's Republic of China. 3. Department of Radiology, The First Affiliated Hospital, Jinan University, No. 613, Huangpu West Road, Tianhe District, Guangzhou, 510627, Guangdong, People's Republic of China. xld_Jane_Eyre@126.com. 4. Graduate College, Jinan University, Guangzhou, Guangdong, People's Republic of China. xld_Jane_Eyre@126.com. 5. Department of Radiology, The First Affiliated Hospital, Jinan University, No. 613, Huangpu West Road, Tianhe District, Guangzhou, 510627, Guangdong, People's Republic of China. shui7515@126.com. 6. Graduate College, Jinan University, Guangzhou, Guangdong, People's Republic of China. shui7515@126.com.
Abstract
PURPOSE: Prediction of immunotherapy response and outcome in patients with non-small cell lung cancer (NSCLC) is challenging due to intratumoral heterogeneity and lack of robust biomarkers. The aim of this study was to systematically evaluate the methodological quality of radiomic studies for predicting immunotherapy response or outcome in patients with NSCLC. METHODS: We systematically searched for eligible studies in the PubMed and Web of Science datasets up to April 1, 2021. The methodological quality of included studies was evaluated using the phase classification criteria for image mining studies and the radiomics quality scoring (RQS) tool. A meta-analysis of studies regarding the prediction of immunotherapy response and outcome in patients with NSCLC was performed. RESULTS: Fifteen studies were identified with sample sizes ranging from 30 to 228. Seven studies were classified as phase II, and the remaining as discovery science (n = 2), phase 0 (n = 4), phase I (n = 1), and phase III (n = 1). The mean RQS score of all studies was 29.6%, varying from 0 to 68.1%. The pooled diagnostic odds ratio for predicting immunotherapy response in NSCLC using radiomics was 14.99 (95% confidence interval [CI] 8.66-25.95). In addition, radiomics could divide patients into high- and low-risk group with significantly different overall survival (pooled hazard ratio [HR]: 1.96, 95%CI 1.61-2.40, p < 0.001) and progression-free survival (pooled HR: 2.39, 95%CI 1.69-3.38, p < 0.001). CONCLUSIONS: Radiomics has potential to noninvasively predict immunotherapy response and outcome in patients with NSCLC. However, it has not yet been implemented as a clinical decision-making tool. Further external validation and evaluation within clinical pathway can facilitate personalized treatment for patients with NSCLC.
PURPOSE: Prediction of immunotherapy response and outcome in patients with non-small cell lung cancer (NSCLC) is challenging due to intratumoral heterogeneity and lack of robust biomarkers. The aim of this study was to systematically evaluate the methodological quality of radiomic studies for predicting immunotherapy response or outcome in patients with NSCLC. METHODS: We systematically searched for eligible studies in the PubMed and Web of Science datasets up to April 1, 2021. The methodological quality of included studies was evaluated using the phase classification criteria for image mining studies and the radiomics quality scoring (RQS) tool. A meta-analysis of studies regarding the prediction of immunotherapy response and outcome in patients with NSCLC was performed. RESULTS: Fifteen studies were identified with sample sizes ranging from 30 to 228. Seven studies were classified as phase II, and the remaining as discovery science (n = 2), phase 0 (n = 4), phase I (n = 1), and phase III (n = 1). The mean RQS score of all studies was 29.6%, varying from 0 to 68.1%. The pooled diagnostic odds ratio for predicting immunotherapy response in NSCLC using radiomics was 14.99 (95% confidence interval [CI] 8.66-25.95). In addition, radiomics could divide patients into high- and low-risk group with significantly different overall survival (pooled hazard ratio [HR]: 1.96, 95%CI 1.61-2.40, p < 0.001) and progression-free survival (pooled HR: 2.39, 95%CI 1.69-3.38, p < 0.001). CONCLUSIONS: Radiomics has potential to noninvasively predict immunotherapy response and outcome in patients with NSCLC. However, it has not yet been implemented as a clinical decision-making tool. Further external validation and evaluation within clinical pathway can facilitate personalized treatment for patients with NSCLC.
Authors: Suzanne L Topalian; F Stephen Hodi; Julie R Brahmer; Scott N Gettinger; David C Smith; David F McDermott; John D Powderly; Richard D Carvajal; Jeffrey A Sosman; Michael B Atkins; Philip D Leming; David R Spigel; Scott J Antonia; Leora Horn; Charles G Drake; Drew M Pardoll; Lieping Chen; William H Sharfman; Robert A Anders; Janis M Taube; Tracee L McMiller; Haiying Xu; Alan J Korman; Maria Jure-Kunkel; Shruti Agrawal; Daniel McDonald; Georgia D Kollia; Ashok Gupta; Jon M Wigginton; Mario Sznol Journal: N Engl J Med Date: 2012-06-02 Impact factor: 91.245
Authors: Tony S K Mok; Yi-Long Wu; Iveta Kudaba; Dariusz M Kowalski; Byoung Chul Cho; Hande Z Turna; Gilberto Castro; Vichien Srimuninnimit; Konstantin K Laktionov; Igor Bondarenko; Kaoru Kubota; Gregory M Lubiniecki; Jin Zhang; Debra Kush; Gilberto Lopes Journal: Lancet Date: 2019-04-04 Impact factor: 79.321
Authors: Mark A Socinski; Robert M Jotte; Federico Cappuzzo; Francisco Orlandi; Daniil Stroyakovskiy; Naoyuki Nogami; Delvys Rodríguez-Abreu; Denis Moro-Sibilot; Christian A Thomas; Fabrice Barlesi; Gene Finley; Claudia Kelsch; Anthony Lee; Shelley Coleman; Yu Deng; Yijing Shen; Marcin Kowanetz; Ariel Lopez-Chavez; Alan Sandler; Martin Reck Journal: N Engl J Med Date: 2018-06-04 Impact factor: 91.245