Development of a clinical prediction model for interstitial lung disease in patients receiving durvalumab for unresectable stage III NSCLC

Early detection of interstitial lung disease including radiation pneumonitis (ILD/RP) is crucial in consolidative durvalumab therapy after chemoradiotherapy (CRT) in unresectable stage III non-small cell lung cancer (NSCLC). A multicenter, noninterventional pilot study in Japan was designed to develop a clinical prediction model for grade ≥ 2 ILD/RP following durvalumab treatment, by using machine learning algorithms on continuously collected automatic measurement from a wearable device and cough-counting smartphone application, as well as electronic medical record data. Eight algorithms were applied to develop the prediction model. After performing 4-fold cross-validation, the prediction model was evaluated using the ROC-AUC. Of 145 registered patients, 123 were analyzed (median age 68.0 years; range 39-85; 80% male). Grade ≥ 2 ILD/RP occurred in 46 patients. The best performing prediction model (‘XGBoost’) had an ROC-AUC of 0.789 (95% CI 0.724-0.854). The model using patient background and wearable device data (excluding the cough app) showed accuracy comparable with the model using all data sources, with an ROC-AUC of 0.794 (95% CI 0.730-0.859). The authors conclude that these findings show the feasibility of developing a clinical prediction model for grade ≥ 2 ILD/RP in patients undergoing durvalumab treatment after CRT for unresectable stage III NSCLC.