Danny Eckert, PhD, Adelaide Institute for Sleep Health, Flinders University, Adelaide, Australia, discusses a recently developed physiological-based model that uses standard polysomnography and clinical data to predict oral appliance treatment outcomes in obstructive sleep apnea (OSA). This model uses machine learning to negate the requirement for comprehensive laboratory testing to measure disease endotypes, which is generally impractical for clinical purposes. The application has demonstrated an 80% accuracy rate in predicting patient response to oral appliance therapy, compared to about 50% when using apnea hypoxia index (AHI) based phenotyping. This interview was recorded at the World Sleep Congress 2022 in Rome, Italy.