TY - JOUR AU - Reuter, Lukas M AU - Kraus, Kim AU - Fischer, Stefan M AU - Pletzer, Danai AU - Bernhardt, Denise AU - Combs, Stephanie E AU - Schnabel, Julia A AU - Peeken, Jan C TI - Prediction of Symptomatic Radiation Pneumonitis in Lung Cancer Patients: A Radiomics and Dosiomics Machine Learning Approach Using the Prospective Multicenter RTOG 0617 and REQUITE trials. JO - International journal of radiation oncology, biology, physics VL - nn SN - 0360-3016 CY - Amsterdam [u.a.] PB - Elsevier Science M1 - DKFZ-2026-00417 SP - nn PY - 2026 N1 - epub AB - Radiation-induced pneumonitis (RP) is a side effect after thoracic radiotherapy (RT). The ability to predict RP would facilitate treatment modifications. This study investigates the predictive capacity for symptomatic RP (CTCAE≥2) employing Radiomics and Dosiomics models.Computed tomography (CT) scans, along with physical and 2-Gy equivalent dose volumes (EQD2), dose-volume histograms (DVH), and clinical parameters, were evaluated for 708 multicenter lung cancer patients, among whom 89 developed RP≥2. The training cohort consisted of 441 patients from the prospective RTOG 0617 trial. External validation was carried out on 267 patients from the prospective REQUITE study. A Random Forest classifier was employed, with feature selection executed within the inner loop of a 10x5-fold nested cross-validation (nCV) utilizing the minimum-redundancy-maximum-relevance algorithm. To address class imbalances, synthetic oversampling and undersampling were implemented using SMOTE-Tomek. The QUANTEC Normal Tissue Complication Probability (NTCP) model served as a reference. Additionally, the experiments were stratified by subgroups (standard/high-dose and 3D-conformal RT (3D-CRT)/intensity-modulated RT (IMRT)).The best radiomics model identified in the nCV was trained on the standard-dose subgroup achieved a test ROC-AUC of 0.56. The baseline NTCP model showed a predictive performance with a ROC-AUC of 0.56, which was largely dependent on radiation technique (ROC-AUCS: 3D-CRT: 0.75, IMRT: 0.50). The DosiomicsEQD2 model, trained on the full training cohort, attained the second-best performance in the nCV, demonstrating the same technique-dependence (ROC-AUC of 0.75 vs. 0.39). Using a DosiomicsEQD2 ensemble model trained separately on 3D-CRT and IMRT subgroups increased overall performance to a testing ROC-AUC of 0.61, outperforming other modeling strategies for IMRT, while being outperformed by clinical models for 3D-CRT.This prospective trial-based study reveals an overall limited predictive capacity of radiomics and dosiomics models and a large influence of radiation technique. IMRT-specific models should be investigated further. KW - Dosiomics (Other) KW - Lung Cancer (Other) KW - NTCP (Other) KW - Radiation pneumonitis (Other) KW - Radiomics (Other) KW - Side Effects (Other) LB - PUB:(DE-HGF)16 C6 - pmid:41720170 DO - DOI:10.1016/j.ijrobp.2026.01.031 UR - https://inrepo02.dkfz.de/record/310004 ER -