Early prediction of immune checkpoint inhibitor-related pneumonitis in advanced non-small cell lung cancer based on primary tumor Delta-radiomics features - Takeaways - MDSpire

Early prediction of immune checkpoint inhibitor-related pneumonitis in advanced non-small cell lung cancer based on primary tumor Delta-radiomics features

  • By

  • Xie, Dong

  • Xu, Lingang

  • Xu, Jinxia

  • Chen, Haifeng

  • Yu, Jinna

  • He, Cong

  • Qiu, Yonggang

  • Fu, Linfeng

  • Han, Qiu

  • Kong, Lingting

  • Wu, Fangye

  • May 15, 2026

  • 0 min

Share

  • 1

    The study aimed to predict immune checkpoint inhibitor-related pneumonitis in advanced NSCLC using Delta radiomics from CT images.

  • 2

    A total of 131 patients were analyzed, with 35.1% developing ICIP, including 17.4% with grade 3–5 ICIP.

  • 3

    Twenty-two key Delta radiomics features were identified from 2153 initial features for model construction.

  • 4

    The Delta radiomics model using the LR algorithm achieved an AUC of 0.85 in validation, indicating strong predictive performance.

  • 5

    The combined model with clinical features improved AUC to 0.86, suggesting potential for early risk stratification of ICIP.

Original Source(s)

Early prediction of immune checkpoint inhibitor-related pneumonitis in advanced non-small cell lung cancer based on primary tumor Delta-radiomics features

  • by Xie, Dong , Xu, Lingang , Xu, Jinxia , Chen, Haifeng , Yu, Jinna , He, Cong , Qiu, Yonggang , Fu, Linfeng , Han, Qiu , Kong, Lingting , Wu, Fangye

  • May 15, 2026

Related Content

Potential targets for boron transport in boron neutron capture therapy

Emerging applications of artificial intelligence for risk stratification in head and neck cancer: a scoping review

Immune biomarker landscape and fusion partner–phenotype associations in thoracic and head-and-neck NUT carcinoma