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

Clinical Scorecard: Prognostic Assessment of Immune Checkpoint Inhibitor-Induced Pneumonitis in Advanced Non-Small Cell Lung Cancer Using Delta Radiomics from Tumor Imaging

At a Glance

CategoryDetail
ConditionImmune checkpoint inhibitor-related pneumonitis (ICIP)
Key MechanismsDelta radiomics features derived from pre-and post-treatment enhanced CT images
Target PopulationPatients with advanced non-small cell lung cancer (NSCLC), stage IIIB-IV
Care SettingSingle-center retrospective study

Key Highlights

  • 35.1% of patients developed ICIP, with 17.4% experiencing grade 3-5 ICIP
  • 22 key Delta radiomics features selected for model construction
  • Delta radiomics model using Logistic Regression showed best performance with AUCs of 0.92 and 0.85
  • Combined model with clinical features achieved an AUC of 0.94 in training and 0.86 in validation sets
  • External validation in independent cohorts is required for clinical application

Guideline-Based Recommendations

Diagnosis

  • Use Delta radiomics features for predicting ICIP in advanced NSCLC patients

Management

  • Integrate Delta radiomics model with clinical features for improved prediction

Monitoring & Follow-up

  • Assess model performance using five-fold cross-validation

Risks

  • Limited evaluation of high-grade ICIP due to low event numbers

Patient & Prescribing Data

131 patients with stage IIIB-IV NSCLC receiving immune checkpoint inhibitors

Delta radiomics may serve as an imaging-based biomarker for early risk stratification of ICIP

Clinical Best Practices

  • Utilize enhanced CT imaging for Delta radiomics feature extraction
  • Employ LASSO regression for feature selection
  • Consider clinical history and laboratory parameters in predictive models

Related Resources & Content

    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

    Outcomes of critically ill pediatric patients after haploidentical stem cell transplantation

    Beyond inhibition: harnessing the DRD2–VEGF-A feedback loop for precision anti-angiogenesis therapy in cancer

    Stimuli-responsive nanoplatforms for sonodynamic immunotherapy: opportunities and challenges in cancer treatment