Outcome evaluation using an artificial intelligence‐based facial measurement software for facial nerve grafting in head and neck and skull base surgery

Abstract

Interposition nerve grafting is an indispensable technique for facial nerve reconstruction in head and neck, and skull base surgery. The prognostic factors are inconclusive, partly due to limited objective assessment systems for facial nerve function. This study aimed to apply an artificial intelligence (AI)-based facial asymmetry measurement system to assess facial nerve grafting outcomes. We retrospectively reviewed data of 23 patients who underwent facial nerve grafting between 2011 and 2020. Oral asymmetry and synkinesis severity were measured using AI. Oral movement recovered at 12-18 months postoperatively. Postoperative radiotherapy and a larger number of anastomosed distal stumps were significantly associated with poor and good final oral symmetry, respectively. Synkinesis severity was weakly correlated with the degree of oral movement recovery. Oral function recovered without a strong correlation with synkinesis. Caution should be exercised in facial nerve grafting for cases with postoperative radiotherapy.