External Validation of Radiation-Induced Dyspnea Models on Esophageal Cancer Radiotherapy Patients
Purpose: Radiation-induced lung disease (RILD), such as dyspnea, is a risk for patients receiving high-dose thoracic irradiation. This study is a TRIPOD Type 4 validation of previously-published lung toxicity models via secondary analysis of esophageal cancer SCOPE1 trial data. We quantify the predictive performance of these two models for predicting dyspnea 6 months after high-dose chemo-radiotherapy for primary esophageal cancer.
Material and methods: We tested the performance of the earlier models using baseline, treatment and follow-up data on 258 esophageal cancer patients in the UK enrolled into the SCOPE1 multi-centre trial. The adverse event of interest was dyspnea ≥ Grade 2 within 6 months of the end of radiotherapy. External validation was performed using an automated, decentralized approach, without exchange of individual patient data.
Results: Out of 258 patients with esophageal cancer in SCOPE1 trial data, 38 patients developed radiation-induced dyspnea (≥ Grade 2) within 6 months of the end of radiotherapy. The discrimination performance of the models in esophageal cancer patients treated with high-dose external beam radiotherapy was moderate, AUC of 0.68 (95% CI 0.55 – 0.76) and 0.70 (95% CI 0.58 -0.77), respectively. The curves and AUCs derived by distributed learning were identical to the results from validation on a local host.
Conclusion: We have external validated previously published dyspnea models using an esophageal cancer dataset. Prediction performance was not statistically different from previous training and validation sets. The distributed learning approach gave the same answer as local validation, but is feasible without accessing a validation site’s individual patients-level data.