Adapting federated radiomics models for radiation pneumonitis prediction in patients receiving thoracic radiotherapy with immunotherapy
Open Access
- 7 April 2026
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 17, 1793039
Abstract
Background and purpose: Radiation pneumonitis (RP) is one of the major dose-limiting toxicities of thoracic radiotherapy. Although multiple studies have attempted to predict RP, robust multicenter model development is often hindered by privacy regulations and data-transfer constraints, and many existing models are primarily derived from radiotherapy-alone populations, limiting applicability to contemporary regimens that incorporate immunotherapy. Therefore, this study aimed to develop an RP prediction model within a federated learning framework, incorporating sequential transfer learning strategies to enable separate risk assessment for radiotherapy patients with and without immunotherapy. Methods: Multicenter cohorts of lung cancer patients treated with definitive thoracic radiotherapy with or without immunotherapy were retrospectively collected and stratified by immunotherapy exposure. Radiomics features were extracted from whole-lung regions on pretreatment planning CT scans to construct RP prediction models. A federated learning framework was first applied to non-immunotherapy patients to learn common features of radiation pneumonitis without sharing raw data. The pretrained federated model was then sequentially transferred to immunotherapy treatment cohorts, with targeted fine-tuning to adapt to treatment specific RP patterns. Model performance was evaluated through internal validation and independent external validation, with SHAP analysis exploring feature importance differences across treatment settings. Results: A total of 610 patients were included from five multicenter cohorts. Using patients without immunotherapy for model development, the federated baseline model showed stable discrimination in external validation across non-immunotherapy cohorts (AUC = 0.77). When this baseline model was directly applied to the immunotherapy cohort without adaptation, performance dropped markedly (AUC = 0.43). After fine-tuning on immunotherapy data, the immunotherapy-adapted model achieved improved performance within the immunotherapy cohort (AUC = 0.76) and remained robust in an independent external immunotherapy validation cohort (AUC = 0.75). Feature attribution analysis showed a shift in model coefficients between immunotherapy-treated and non-immunotherapy patients. Conclusion: A federated modeling framework with treatment adaptation improves RP risk prediction across heterogeneous treatment settings under multicenter data constraints, particularly in immunotherapy-treated patients.Keywords
Funding Information
- National Natural Science Foundation of China (82303672, 82573437)
This publication has 29 references indexed in Scilit:
- Advancing breast, lung and prostate cancer research with federated learning. A systematic reviewnpj Digital Medicine, 2025
- Distinguishing immune checkpoint inhibitor-related pneumonitis from radiation pneumonitis by CT radiomics features in non-small cell lung cancerInternational Immunopharmacology, 2024
- Computed tomography and radiation dose images-based deep-learning model for predicting radiation pneumonitis in lung cancer patients after radiation therapyRadiotherapy and Oncology, 2023
- Computed tomography-based radiomics for the differential diagnosis of pneumonitis in stage IV non-small cell lung cancer patients treated with immune checkpoint inhibitorsEuropean Journal of Cancer, 2023
- Safety and Efficacy of PD‐1/PD‐L1 inhibitors combined with radiotherapy in patients with non‐small‐cell lung cancer: a systematic review and meta‐analysisCancer Medicine, 2021
- Radiomic prediction of radiation pneumonitis on pretreatment planning computed tomography images prior to lung cancer stereotactic body radiation therapyScientific Reports, 2020
- Toxicity in combination immune checkpoint inhibitor and radiation therapy: A systematic review and meta-analysisRadiotherapy and Oncology, 2020
- Three-Year Overall Survival with Durvalumab after Chemoradiotherapy in Stage III NSCLC—Update from PACIFICJournal of Thoracic Oncology, 2019
- The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information RepositoryJournal of Digital Imaging, 2013
- Clinical radiation pneumonitis and radiographic changes after thoracic radiation therapy for lung carcinomaCancer, 1998