ABSTRACT
PURPOSE: To propose a new objective, video recording method for the classification of unilateral peripheral facial palsy (UPFP) that relies on mathematical algorithms allowing the software to recognize numerical points on the two sides of the face surface that would be indicative of facial nerve impairment without positioning of markers on the face. METHODS: Patients with UPFP of different House-Brackmann (HB) degrees ranging from II to V were evaluated after video recording during two selected facial movements (forehead frowning and smiling) using a software trained to recognize the face points as numbers. Numerical parameters in millimeters were obtained as indicative values of the shifting of the face points, of the shift differences of the two face sides and the shifting ratio between the healthy (denominator) and the affected side (numerator), i.e., the asymmetry index for the two movements. RESULTS: For each HB grade, specific asymmetry index ranges were identified with a positive correlation for shift differences and negative correlation for asymmetry indexes. CONCLUSIONS: The use of the present objective system enabled the identification of numerical ranges of asymmetry between the healthy and the affected side that were consistent with the outcome from the subjective methods currently in use.
