Development and Validation of a Machine Learning-Based Model Using CT Radiomics for Predicting Immune Checkpoint Inhibitor-related Pneumonitis in Patients With NSCLC Receiving Anti-PD1 Immunotherapy: A Multicenter Retrospective Case- Control Study

作者全名：Zhang, Guo-yue; Du, Xian-zhi; Xu, Rui; Chen, Ting; Wu, Yue; Wu, Xiao-juan; Liu, Shui

作者地址：[Zhang, Guo-yue; Du, Xian-zhi; Xu, Rui; Wu, Yue; Wu, Xiao-juan] Chongqing Med Univ, Affiliated Hosp 2, Dept Resp Med, Chongqing 400010, Peoples R China; [Chen, Ting] Chongqing Med Univ, Affiliated Hosp 2, Dept Radiol, Chongqing 400010, Peoples R China; [Wu, Xiao-juan] Suining Cent Hosp, Dept Resp & Crit Care Med, Suining 629000, Sichuan, Peoples R China; [Liu, Shui] Peoples Hosp Fengjie, Dept Resp & Crit Care Med, Chongqing 404600, Peoples R China

通信作者：Zhang, GY (通讯作者)，Chongqing Med Univ, Affiliated Hosp 2, Dept Resp Med, Chongqing 400010, Peoples R China.

来源：ACADEMIC RADIOLOGY

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001240441200004

JCR分区：Q1

影响因子：3.8

年份：2024

卷号：31

期号：5

开始页：2128

结束页：2143

文献类型：Article

关键词：Computed tomography; Non-small cell lung cancer; Immunotherapy; Machine learning

摘要：Rationale and Objectives: This study aimed to develop and evaluate a radiomics-based model combined with clinical and qualitative radiological (semantic feature [SF]) features to predict immune checkpoint inhibitor-related pneumonitis (CIP) in patients with non-small cell lung cancer (NSCLC) treated with programmed cell death protein 1 inhibitors. Materials and Methods: This was a multicenter retrospective case -control study conducted from January 1, 2018, to December 31, 2022, at three centers. Patients with NSCLC treated with anti-PD1 were enrolled and randomly divided into two groups (7:3): training ( n = 95) and validation ( n = 39). Logistic regression (LR) and support vector machine (SVM) algorithms were used to transform features into the models. Results: The study comprised 134 participants from three independent centers (male, 114/134, 85%; mean [ +/- standard deviation] age, 63.92 [ +/- 7.9] years). The radiomics score (RS) models built based on the LR and SVM algorithms could accurately predict CIP (area under the receiver operating characteristics curve [AUC], 0.860 [0.780, 0.939] and 0.861 [0.781, 0.941], respectively). The AUCs for the RS -clinic -SF combined model were 0.903 (0.839, 0.967) and 0.826 (0.688, 0.964) in the training and validation cohorts, respectively. Decision curve analysis showed that the combined models achieved high clinical net benefit across the majority of the range of reasonable threshold probabilities. Conclusion: This study demonstrated that the combined model constructed by the identified features of RS, clinical features, and SF has the potential to precisely predict CIP. The RS -clinic -SF combined model has the potential to be used more widely as a practical tool for the noninvasive prediction of CIP to support individualized treatment planning.

基金机构：Chongqing Natural Science Foundation [cstc2021jcyj-msxmX0216]; Chongqing Medical Scientific Research Project (Joint project of Chongqing Health Commission and Science and Technology Bureau) [2022MSXM144]; Program for Youth Innovation in Future Medicine, Chongqing Medical University [W0118]

基金资助正文：This work was supported by the Chongqing Natural Science Foundation (cstc2021jcyj-msxmX0216) ; the Chongqing Medical Scientific Research Project (Joint project of Chongqing Health Commission and Science and Technology Bureau; 2022MSXM144); and the Program for Youth Innovation in Future Medicine, Chongqing Medical University (W0118).