Validation of the Clinician-Graded Electronic Facial Paralysis Assessment

Background: Facial paralysis remains a debilitating condition despite advances in medical, surgical, and adjunctive interventions. Established grading systems used to assess facial paralysis and interventional outcomes have well-described limitations. The Electronic Facial Paralysis Assessment, a clinician-graded zone-based facial function scale, has recently emerged as a grading tool that may provide greater sensitivity when assessing incomplete paralysis and post-surgical improvement. The authors perform the first comprehensive validation of this tool. Methods: Video recordings of 83 facial paralysis patients were assessed. Grading was performed in two sittings by three individuals with varying degrees of experience in assessing facial paralysis. Interobserver reliability; intraobserver reliability; administration time; and agreement with the Facial Disability Index, House-Brackmann, Sunnybrook, and Sydney facial grading systems were assessed. Results: The Electronic Facial Paralysis Assessment demonstrated high intraobserver and interobserver reliability (intraclass correlation coefficient, 0.84 to 0.91 and 0.81 to 0.83, respectively). It correlated well with the House-Brackmann, Sunnybrook, and Sydney facial grading systems (Spearman rho, 0.73, 0.77 and 0.77, respectively). In subdomain analysis, it correlated well with the Sunnybrook and Sydney systems in dynamic movement (Spearman rho, 0.90 and 0.89, respectively) and synkinesis (Spearman rho, range 0.74 and 0.72, respectively). It had poor agreement with the Facial Disability Index (Spearman rho, 0.25). The mean time to complete the tool was 116 +/- 61 seconds. Conclusions: The Electronic Facial Paralysis Assessment is a valid facial assessment tool with high reliability and correlation with the established facial paralysis grading systems. It also provides an efficient and detailed analysis of paralysis according to each facial zone.