Early prediction of immune checkpoint inhibitor-related pneumonitis in advanced non-small cell lung cancer based on primary tumor Delta-radiomics features - Summary - MDSpire
Advertisement
Early prediction of immune checkpoint inhibitor-related pneumonitis in advanced non-small cell lung cancer based on primary tumor Delta-radiomics features
To investigate the effectiveness of predicting immune checkpoint inhibitor-related pneumonitis (ICIP) in patients with advanced non-small cell lung cancer (NSCLC) using Delta radiomics features derived from pre-and post-treatment enhanced CT images.
Key Findings:
131 patients included; 46 (35.1%) developed ICIP, with 8 patients (17.4%) experiencing grade 3–5 ICIP.
From 2153 initial features, 22 key Delta radiomics features selected for model construction.
Delta radiomics model based on LR algorithm showed best performance with AUCs of 0.92 (training) and 0.85 (validation).
Combined model with clinical features improved performance to AUC of 0.94 (training) and 0.86 (validation).
No statistically significant difference in AUC between combined model and LR model in validation set (P = 0.4691).
Interpretation:
The preliminary model offers a potential imaging-based biomarker for early risk stratification of any-grade ICIP in patients with advanced NSCLC.
Limitations:
Performance for high-grade (grade 3-5) ICIP could not be evaluated due to limited number of such events.
External validation in independent cohorts is required before clinical application.
Conclusion:
The study suggests a promising approach for predicting ICIP using Delta radiomics, pending further validation.
