A study published in Otolaryngology-Head and Neck Surgery found that a machine learning model based on pure-tone audiometry features can diagnose Meniere disease (MD) and predict endolymphatic hydrops (EH). Researchers collected data through gadolinium-enhanced magnetic resonance imaging sequences and engineered features from air conduction thresholds of pure-tone audiometry. The winning light gradient boosting (LGB) machine learning model showed excellent performance in diagnosing MD and predicting EH with an accuracy of 87%, sensitivity of 83%, and specificity of 90%. The study highlights the potential of machine learning as a screening method for MD based on pure-tone audiometry results.
Source link