A predictive model for dysphagia following IMRT for head and neck cancer: introduction of the EMLasso technique.

BACKGROUND AND PURPOSE: Design a model for prediction of acute dysphagia following intensity-modulated radiotherapy (IMRT) for head and neck cancer. Illustrate the use of the EMLasso technique for model selection. MATERIAL AND METHODS: Radiation-induced dysphagia was scored using CTCAE v.3.0 in 189 head and neck cancer patients. Clinical data (gender, age, nicotine and alcohol use, diabetes, tumor location), treatment parameters (chemotherapy, surgery involving the primary tumor, lymph node dissection, overall treatment time), dosimetric parameters (doses delivered to pharyngeal constrictor (PC) muscles and esophagus) and 19 genetic polymorphisms were used in model building. The predicting model was achieved by EMLasso, i.e. an EM algorithm to account for missing values, applied to penalized logistic regression, which allows for variable selection by tuning the penalization parameter through crossvalidation on AUC, thus avoiding overfitting. RESULTS: Fifty-three patients (28%) developed acute ≥ grade 3 dysphagia. The final model has an AUC of 0.71 and contains concurrent chemotherapy, D2 to the superior PC and the rs3213245 (XRCC1) polymorphism. The model's false negative rate and false positive rate in the optimal operation point on the ROC curve are 21% and 49%, respectively. CONCLUSIONS: This study demonstrated the utility of the EMLasso technique for model selection in predictive radiogenetics.

Development of a multicomponent prediction model for acute esophagitis in lung cancer patients receiving chemoradiotherapy.

PURPOSE: To construct a model for the prediction of acute esophagitis in lung cancer patients receiving chemoradiotherapy by combining clinical data, treatment parameters, and genotyping profile. PATIENTS AND METHODS: Data were available for 273 lung cancer patients treated with curative chemoradiotherapy. Clinical data included gender, age, World Health Organization performance score, nicotine use, diabetes, chronic disease, tumor type, tumor stage, lymph node stage, tumor location, and medical center. Treatment parameters included chemotherapy, surgery, radiotherapy technique, tumor dose, mean fractionation size, mean and maximal esophageal dose, and overall treatment time. A total of 332 genetic polymorphisms were considered in 112 candidate genes. The predicting model was achieved by lasso logistic regression for predictor selection, followed by classic logistic regression for unbiased estimation of the coefficients. Performance of the model was expressed as the area under the curve of the receiver operating characteristic and as the false-negative rate in the optimal point on the receiver operating characteristic curve. RESULTS: A total of 110 patients (40%) developed acute esophagitis Grade ≥2 (Common Terminology Criteria for Adverse Events v3.0). The final model contained chemotherapy treatment, lymph node stage, mean esophageal dose, gender, overall treatment time, radiotherapy technique, rs2302535 (EGFR), rs16930129 (ENG), rs1131877 (TRAF3), and rs2230528 (ITGB2). The area under the curve was 0.87, and the false-negative rate was 16%. CONCLUSION: Prediction of acute esophagitis can be improved by combining clinical, treatment, and genetic factors. A multicomponent prediction model for acute esophagitis with a sensitivity of 84% was constructed with two clinical parameters, four treatment parameters, and four genetic polymorphisms.