Radiomics Models Predict Tumor Response and Pneumonitis in Non-Small Cell Lung Cancer Patients

Strategic Insights -

Researchers from Northwestern University have presented fresh data on the use of artificial intelligence (AI) algorithms to analyze radiomic features in non-small cell lung cancer (NSCLC) patients undergoing immunotherapy. The study analyzed data from 159 stage III-IV NSCLC patients and found that radiomics models could predict the occurrence of checkpoint inhibitor-associated pneumonitis (CIP) with an accuracy of 0.60 (95% CI 0.55-0.66). The models also exhibited high predictability for tumor responses to immunotherapy, with AUCs of 0.63 (95% CI 0.59-0.67) in irRECIST and 0.66 (95% CI 0.61-0.70) in RECIST 1.1.

Key Takeaways:

  • Researchers at Northwestern University leveraged AI algorithms to analyze radiomic features and predict the occurrence of CIP and tumor responses in NSCLC patients treated with immunotherapy.
  • The study analyzed data from 159 stage III-IV NSCLC patients, of which 31 experienced CIP, with most having grade 1 (17/31, 54.8%) or 2 (12/31, 38.7%) pneumonitis.
  • Patients who developed pneumonitis were more likely to be male (64.5% vs. 38.3%, p = 0.014), have less adenocarcinoma histology (54.8% vs. 78.9%, p = 0.032), and exhibit a higher tumor mutational burden (57.1% vs. 24.5%, p = 0.047).
  • The radiomics analysis reported predictability for CIP with an AUC of 0.60 (95% CI 0.55-0.66), and the radiomics features also exhibited AUCs of 0.63 (95% CI 0.59-0.67) in irRECIST and 0.66 (95% CI 0.61-0.70) in RECIST 1.1 in terms of tumor responses to immunotherapy.
  • The study provides insights into the potential role of radiomic models in predicting CIP and tumor responses from pre-treatment CT images of NSCLC patients treated with immunotherapy.

Statistics:

  • 159 stage III-IV NSCLC patients were analyzed in the study.
  • 31 patients experienced CIP, with most having grade 1 (17/31, 54.8%) or 2 (12/31, 38.7%) pneumonitis.
  • The accuracy of radiomics models in predicting CIP was 0.60 (95% CI 0.55-0.66).
  • The five-year overall and progression-free survival rates were 24.7% (95% CI 15.2-35.5%) and 9.7% (95% CI 4.4-17.4%), respectively.

Sources:

  • Radiomics Models To Predict Tumor Response and Pneumonitis In Non-small Cell Lung Cancer Patients Treated With Immunotherapy. Journal of Clinical Medicine, 2025;14(12):4330.
  • Young Kwang Chae, Monica Yadav, Seyoung Lee, Taegyu Um, Maria Jose Aguilera Chuchuca, Liam Il-Young Chung, Nicolo Gennaro, Sungmi Yoon, Yuchan Kim, Yury S. Velichko, Wongi Woo, Jeeyeon Lee, Peter Haseok Kim, Salie Lee, Trie Arni Djunadi, Jisang Yu, Leeseul Kim, Myungwoo Nam, Youjin Oh, Zunairah Shah, Cecilia Nam, Ilene Hong, Jessica Jang, Grace Kang, Amy Cho, Timothy Hong, and Soowon Lee.