ESTRO 2020 Abstract Book

S147 ESTRO 2020

Department of Radiation Oncology, Zürich, Switzerland ; 3 Léon Bérard Cancer Center, Radiation Oncology Department, Lyon, France ; 4 Aarhus University Hospital, Department of Experimental Clinical Oncology, Aarhus, Denmark ; 5 Catharina Hospital, Department of Radiation Oncology, Eindhoven, The Netherlands Purpose or Objective A logistic regression NTCP model has been previously developed to extract predictive variables and corresponding regression coefficients for incidence of grade 3 oral mucositis 1 . This model, however, has not been externally validated. Regarding the significance of external validation of NTCP models, especially using independent, unseen datasets, our goal was to evaluate the performance of a logistic regression model using the EORTC HNCG-ROG 1219 DAHANCA trial as the validation cohort. Material and Methods The training cohort was composed of 253 patients who received radiation alone or chemoradiation and treated with SIB-IMRT technique for head and neck squamous cell carcinoma. Logistic regression with bootstrapping was performed to extract the model’s predictive factors. The final logistic regression model revealed that the incidence of grade 3 oral mucositis was only dependent on the mean dose to oral mucosa. Model performance was assessed by area under the receiver operating characteristics (AUC- ROC) curve. The EORTC HNCG-ROG 1219 DAHANCA validation cohort consisted of 192 randomized patients. After removing missing data from validation cohort, toxicity data and radiotherapy plans were available for 169 patients. Acute toxicity was defined based on CTCAE v.3.0. Results Sixty/169 patients developed grade 3 oral mucositis in the validation cohort. The mean predicted probability of toxicity was 32%, while the observed probability was 35.5%. The original logistic regression function was in the form of:

respectively). First, we trained the CNN with early stopping. Second, we evaluated how good our model fitted the data in the test set and searched for the presence of any potential outlier using the sum of residuals method to measure the discrepancy between the predicted and the clinical approved DVH; we defined an outlier as any prediction having a sum of residuals greater than one standard deviation from the population mean value. Finally, we repeated this two-step process using different partitions, until all the patients contained in the first training set were once in the test set. At every iteration, we initialized all the CNN parameters to avoid information bleeding. Once we selected all potential outliers, one researcher (M.L.) proceeded to re-optimized all the plans. We recalculated the sum of residuals for them and elaborated a confusion matrix with the model results. Results Our CNN model detected a total of 23 out of 195 patients as having a suboptimal plan. After the reoptimization step, all patients but one were not considered as an outlier anymore. Our false-positive result was of a patient with an IMN chain. We consequently excluded this patient from our dataset since having an IMN was an exclusion criterion. Figure I shows the clinically approved, replanned, and predicted, with confidence intervals, lung and heart DVHs for three patients where the model was applied.

where β 0

demonstrates a constant, β n

were the regression

coefficients and x n were the predictive variables. The regression coefficients of the original model were: β 0 = - 1.8 and β 1 = 0.03 and the AUC was reported to be 0.62. Applying the original model to the validation dataset, the predicted NTCP was calculated for each single patient. Predicted probabilities were then arranged from lowest to highest probabilities and categorized into equally sized bins. The mean observed probabilities per each bin were plotted versus mean predicted probabilities to visualize calibration. Pearson’s correlation coefficient was 0.83, indicating a high correlation between predicted and observed probabilities. ROC curve was also plotted and AUC was 0.67 for the validation cohort.

Conclusion We validated our CNN model as a reliable method to account for outliers within a dataset. We developed an accurate model for DVH prediction in breast cancer patients. This work will allow us to discriminate beforehand which patients will not fulfill dose constraints with 3DCRT and would benefit from other techniques. PH-0288 Independent external validation of a logistic regression NTCP model for grade 3 oral mucositis M. Sharabiani 1 , E. Clementel 1 , N. Andratschke 2 , C. Fortpied 1 , V. Grégoire 3 , J. Overgaard 4 , J. Willmann 1 , C. Hurkmans 5 1 European Organization for Research and Treatment of Cancer EORTC, Headquarters, Brussels, Belgium ; 2 University Hospital Zürich- University of Zurich,