Comparing supervised and semi-supervised machine learning approaches in NTCP modeling to predict complications in head and neck cancer patients

•Supervised and semi-supervised machine learning approaches to predict toxicities in head and neck cancer patients were compared.•Similar performance of the models was observed both in terms of discrimination and calibration.•Varying the amount of data for development or the confidence threshold did not impact the similarity in performance.•The (supervised and semi-supervised) models involving ridge regression outperformed the logistic regression models for the dysphagia outcomes.