Resumen
The standard protocol for distinguishing between benign and malignant lesions remains clinical judgment and histopathological confirmation by an experienced otolaryngologist. An additional tool is high-speed videoendoscopy (HSV), an accurate method for an objective assessment of vocal fold oscillations. The aim of the study was to utilize a quantitative assessment of the vibratory characteristics of vocal folds in diagnosing benign and malignant lesions of the glottis using HSV. The machine learning model identifying malignancy among organic lesions reached an AUC equal to 0.85 and presented with 80.6% accuracy, 100% sensitivity, and 71.1% specificity on the training set. Important predictive factors were frequency perturbation measures. The results suggested that advanced machine learning models based on HSV analysis could potentially indicate a heightened risk of cancerous mass. Therefore, this technology could, in future, aid in early cancer detection; however, further investigation and validation is needed.