Checkpoint Inhibitor Pneumonitis in Patients with Advanced NSCLC on Nivolumab Monotherapy is Underreported and Associated with Prior Radiotherapy History

For patients with advanced non-small cell lung cancer (NSCLC) treated with Immunotherapy (ImT), checkpoint inhibitor pneumonitis (CIP) is an uncommon and sometimes life-threatening adverse event that may be underreported. Recent studies suggest that radiomic analysis of pre-ImT imaging can predict CIP. We hypothesized that for patients with advanced NSCLC treated with Nivolumab monotherapy, pre-ImT radiotherapy (RT) is predictive of CIP and that radiomics features can identify CIP that has been clinically misclassified. From an IRB-approved database (DB) of 159 patients with advanced NSCLC treated with Nivolumab, chart review identified 9 patients diagnosed with CIP of any grade (6%). 40 additional patients from the same DB without diagnosis of CIP were randomly selected for analysis. For all patients, baseline characteristics including pre-ImT RT were collected for comparison between CIP and non-CIP groups. Both lungs were contoured semi-automatically through thresholding on the last pre-ImT CT imaging studies, with intrathoracic lesions subtracted from the lung volumes prior to radiomics analysis. A logistic regression model incorporating radiomics assigned a CIP probability score to every patient. Six radiomics features correlated with CIP (p-values range from 0.02 to 0.03). Each feature had an AUC of ∼0.79 (range 0.789 to 0.794) showing large effect size, with odds ratios greater than 3.50 (4 features) or less than 0.3 (2 features). While pre-ImT thoracic RT was not predictive of pneumonitis, pre-ImT RT irrespective of treatment location was borderline predictive with high effect size (p = 0.09, OR 0.27). The radiomics-based probability model assigned 7/42 patients (16.7%) without clinical diagnosis of CIP a greater than 50% probability of CIP. Chart and imaging review revealed that 6/7 “misclassified” patients exhibited symptoms or radiographic features highly suggestive of CIP. These findings originally were attributed to disease progression or clinically overshadowed by other symptoms. For patients with advanced NSCLC treated with Nivolumab, the incidence of checkpoint-inhibitor pneumonitis (CIP) is underreported and radiomics features can help identify CIP that has been clinically misclassified. Preliminary findings suggest that pre-ImT RT irrespective of treatment location may be predictive of CIP, and therefore that immunomodulatory effects of RT-ImT synergy are not restricted to the local irradiated area. Future directions include expansion of this study across the full database, correlation of radiomics features with blood and tissue biomarkers, and the inclusion of tumor burden as an additional covariate in the analysis.