We use cookies necessary to giving you a better online experience. By using our website you consent to all cookies in accordance with our Privacy Policy.
Yes, I accept
Menu
Search Opener

Session Item

Physics track: Radiation protection, secondary tumour induction and low dose
9320
Poster
Physics
09:25 - 09:33
Independent external validation of a logistic regression NTCP model for grade 3 oral mucositis
PH-0288

Abstract

Independent external validation of a logistic regression NTCP model for grade 3 oral mucositis
Authors: Sharabiani|, Marjan(1)*[marjan.sharabiani@eortc.org];Clementel|, Enrico(1);Andratschke|, Nicolaus(2);Fortpied|, Catherine(1);Grégoire|, Vincent(3);Overgaard|, Jens(4);Willmann|, Jonas(1);Hurkmans|, Coen(5);
(1)European Organization for Research and Treatment of Cancer EORTC, Headquarters, Brussels, Belgium;(2)University Hospital Zürich- University of Zurich, 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;
Show Affiliations
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 mucositis1. 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:   

where β0 demonstrates a constant, βn were the regression coefficients and xn were the predictive variables. The regression coefficients of the original model were: β0 = -1.8 and β1 = 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

Mean dose to oral cavity was suggested to be a significant predictor of grade 3 oral mucositis for patients receiving IMRT with or without chemoradiation. The calibration plot demonstrated model’s external validity in an independent, plausibly related patient cohort. Considering a relatively low AUC, the future goal of our group would be to develop better discriminating models, by considering hidden, relevant predictors.

References

  1. Otter, Sophie, et al. "Evaluation of the risk of grade 3 oral and pharyngeal dysphagia using atlas-based method and multivariate analyses of individual patient dose distributions." International Journal of Radiation Oncology* Biology* Physics 93.3 (2015): 507-515.