ENHANCING SURGICAL EFFICIENCY THROUGH ARTIFICIAL INTELLIGENCE IN THE SURGICAL MANAGEMENT OF CONGENITAL EXTERNAL AUDITORY CANAL ATRESIA

Abstract

Congenital external auditory canal atresia is a complex developmental malformation of the external and middle ear that causes conductive hearing loss and presents substantial surgical challenges because of aberrant anatomy of the ossicular chain, facial nerve, middle ear space, tegmen, sigmoid sinus, and adjacent temporal bone structures. High-resolution temporal bone CT remains the cornerstone of preoperative assessment, while candidacy for atresiaplasty is commonly guided by grading systems such as the Jahrsdoerfer score. Contemporary surgical reviews state that surgery is generally not recommended for patients with Jahrsdoerfer scores of 6 or lower, whereas patients with scores of 7 or higher often achieve favorable short-term hearing outcomes, with 80% to 90% reaching a postoperative speech reception threshold of 30 dB HL or better. At the same time, newer evidence shows that the Jahrsdoerfer score alone does not adequately capture all surgically relevant temporal bone abnormalities, including low tegmen position, anterior sigmoid sinus displacement, and vascular variants.