Prediction of Grade 4 radiation-induced lymphopenia during chemoradiation therapy for lung cancer patients: Insights from two past trials

Background and Purpose: Radiation-induced lymphopenia (RIL) is a significant side effect associated with radiation therapy (RT) with important prognostic implications. We developed and tested a normal tissue complication probability (NTCP) model for Grade 4 (G4) RIL in patients with locally advanced Non-Small-Cell Lung Cancer (NSCLC) who underwent concurrent chemotherapy and RT, analyzing data from patients enrolled in two clinical trials. Materials and Methods: We retrospectively analyzed the data from NCT00915005 (MDA-cohort) and NCT00533949 (RTOG0617-cohort) trials. After finding the candidate predictors of G4-RIL, defined as absolute lymphocyte count (ALC) at nadir < 0.2*109 cells/l during RT, we trained an NTCP model on the MDA-cohort and tested it on the RTOG-cohort, based on common available variables in the two cohorts. Model performance was assessed in terms of discrimination and calibration. Results: In the MDA-cohort, 55 out of 161 (34%) patients developed G4-RIL, while in the RTOG-cohort 16 out of 227 (7%) developed this condition. The relative volume of healthy lungs receiving at least 5 Gy (V5Gy) and baseline ALC were selected as predictors in an NTCP model, with good discriminative performances (cross validated ROC-AUC: 0.68). The predictive value of V5Gy was confirmed in the RTOG0917-cohort (ROC-AUC: 0.67), although its validation was limited with suboptimal calibration, potentially due to discrepancies between cohorts. Conclusions: Baseline ALC and lung V5Gy were identified as predictors for G4-RIL, consistent with findings from previous studies. Treatment plan optimization aiming at reducing low-dose bath in the lungs could be an effective strategy for severe RIL mitigation.