Frontiers in oncology · 2025
Early prediction of immunotherapy efficacy for advanced NSCLC based on clinical and pre-treatment contrast-enhanced CT radiomics features.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Hou Yue, Zhang Tianming, Zhu Kaibo, Jiang Jing, Wang Hong
Аннотация
BACKGROUND AND PURPOSE: To explore the predictive value of a model based on clinical and contrast-enhanced computed tomography (CT) radiomic features for the early prediction of immunotherapy efficacy in patients with advanced non-small cell lung cancer (NSCLC).
METHODS: This retrospective study included 144 patients with advanced NSCLC who received immunotherapy at Lanzhou University Second Hospital between January 2023 and December 2024. Clinical data and CT images were collected from each patient. All patients underwent imaging examinations to evaluate the efficacy of immunotherapy after the second treatment cycle. Patients who achieved complete response (CR) or partial response (PR) were considered to be in the reactive group, while those who experienced stable disease (SD) or progressive disease (PD) were considered to be in the non-reactive group. The participants were randomly divided into a training set (n = 115) and a testing set (n = 29) at a ratio of 8:2. Radiomic features were extracted from pre-treatment contrast-enhanced CT venous phase images. Feature reduction was performed using the Spearman rank correlation coefficient and the least absolute shrinkage and selection operator (LASSO) algorithm. The best radiomics signature was built using multiple machine learning algorithms and combined with clinical features to build a nomogram model. The area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA) were used to evaluate the model's predictive performance, calibration, and clinical net benefit.
RESULTS: Three clinical features (C-reactive protein, baseline tumor size, and programmed death receptor ligand 1) and seven radiomics features (one first-order feature and six texture features) were selected for the model. The radiomic signature performed best based on the Extreme Random Tree algorithm. The radiomic signature and the nomogram model demonstrated superior predictive performance and clinical net benefit compared to the clinical model in both training and testing sets (AUCs: radiomics: 0.926 vs. 0.848; nomogram: 0.953 vs. 0.788; clinical: 0.882 vs. 0.742), with statistically significant differences (P < 0.05).
CONCLUSION: The integrated clinical-radiomics nomogram establishes a robust framework for early prediction of immunotherapy efficacy in advanced NSCLC, offering valuable support for personalized treatment decisions.
METHODS: This retrospective study included 144 patients with advanced NSCLC who received immunotherapy at Lanzhou University Second Hospital between January 2023 and December 2024. Clinical data and CT images were collected from each patient. All patients underwent imaging examinations to evaluate the efficacy of immunotherapy after the second treatment cycle. Patients who achieved complete response (CR) or partial response (PR) were considered to be in the reactive group, while those who experienced stable disease (SD) or progressive disease (PD) were considered to be in the non-reactive group. The participants were randomly divided into a training set (n = 115) and a testing set (n = 29) at a ratio of 8:2. Radiomic features were extracted from pre-treatment contrast-enhanced CT venous phase images. Feature reduction was performed using the Spearman rank correlation coefficient and the least absolute shrinkage and selection operator (LASSO) algorithm. The best radiomics signature was built using multiple machine learning algorithms and combined with clinical features to build a nomogram model. The area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA) were used to evaluate the model's predictive performance, calibration, and clinical net benefit.
RESULTS: Three clinical features (C-reactive protein, baseline tumor size, and programmed death receptor ligand 1) and seven radiomics features (one first-order feature and six texture features) were selected for the model. The radiomic signature performed best based on the Extreme Random Tree algorithm. The radiomic signature and the nomogram model demonstrated superior predictive performance and clinical net benefit compared to the clinical model in both training and testing sets (AUCs: radiomics: 0.926 vs. 0.848; nomogram: 0.953 vs. 0.788; clinical: 0.882 vs. 0.742), with statistically significant differences (P < 0.05).
CONCLUSION: The integrated clinical-radiomics nomogram establishes a robust framework for early prediction of immunotherapy efficacy in advanced NSCLC, offering valuable support for personalized treatment decisions.