Here at the UC Irvine Otolaryngology, we are leading a series of projects on the application of novel machine learning algorithms on clinical decision support. We have created statistical and mathematical models for predicting recurrence following vestibular schwannoma treatment, predicting length of hospitalization and discharge disposition following complex head and neck surgery, predicting post-thyroidectomy outcomes, and classifying otoscopic images based on the predicted diagnoses. In addition to creating novel machine learning algorithms, we have also published respective open-source interfaces (e.g., websites) where the predictive models can be tested in real-time by any user. For instance, the latter three projects’ algorithms are also accompanied by websites were hypothetical patient information or otoscopic images can be uploaded and the algorithm will provide predictions.