Masahiko Sumii

Introduction: Pneumonitis represents one of the clinically significant adverse events observed in patients with non-small-cell lung cancer (NSCLC) who receive durvalumab as consolidation therapy after chemoradiotherapy (CRT). Although clinical factors such as radiation dose (e.g., V20) and interstitial lung abnormalities (ILAs) have been reported as risk predictors, accurate and objective prognostication remains difficult. This study aimed to develop a radiomics-based machine learning model to predict grade ≥ 2 pneumonitis. Methods: This retrospective study included patients with unresectable NSCLC who received CRT followed by durvalumab. Radiomic features, including first-order and texture and shape-based features with wavelet transformation were extracted from whole-lung regions on pre-durvalumab computed tomography (CT) images. Machine learning models, support vector machines, k-nearest neighbor, neural networks, and naïve Bayes classifiers were developed and evaluated using a testing cohort. Model performance was assessed using five-fold cross-validation. Conventional predictors, including V20 and ILAs, were also assessed using logistic regression and receiver operating characteristic analysis. Results: Among 123 patients, 44 (35.8%) developed grade ≥ 2 pneumonitis. The best-performing model, a support vector machine, achieved an AUC of 0.88 and accuracy of 0.81, the conventional model showed lower performance with an AUC of 0.71 and accuracy of 0.64. Conclusions: Radiomics-based machine learning demonstrated superior performance over clinical parameters in predicting pneumonitis. This approach may enable individualized risk stratification and support early intervention in patients with NSCLC.

Introduction/Background: Chemoradiotherapy (CRT) followed by durvalumab, an immune checkpoint inhibitor, is the standard treatment for locally advanced non-small-cell lung cancer (NSCLC). Interstitial lung disease (ILD) is a life-threatening toxicity caused by these treatments; however, risk factors for the ILD have not yet been established. Interstitial lung abnormalities (ILAs) are computed tomography (CT) findings which manifest as minor interstitial shadows. We aimed to investigate whether ILAs could be risk factors for grade-two or higher ILD during durvalumab therapy. Patients and Methods: Patients with NSCLC who received durvalumab after CRT from July 2018 to June 2021 were retrospectively enrolled. We obtained patient characteristics, laboratory data, radiotherapeutic parameters, and chest CT findings before durvalumab therapy. Results: A total of 148 patients were enrolled. The prevalence of ILAs before durvalumab treatment was 37.8%. Among 148 patients, 63.5% developed ILD during durvalumab therapy. The proportion of patients with grade-two or higher ILD was 33.8%. The univariate logistic regression analysis revealed that older age, high dose-volume histogram parameters, and the presence of ILAs were significant risk factors for grade-two or higher ILD. The multivariate analysis showed that ILAs were independent risk factors for grade-two or higher ILD (odds ratio, 3.70; 95% confidence interval, 1.69–7.72; p < 0.001). Conclusions: We showed that pre-existing ILAs are risk factors for ILD during durvalumab treatment after CRT. We should pay attention to the development of grade-two or higher ILD during durvalumab treatment in patients with ILAs.