Automated, Radiation-Free Detection of Cochlear Implant Electrode Array Migration Using Routine Impedance Telemetry

Abstract Electrode array migration is a rare condition after cochlear implantation that can impair auditory outcomes but often remains undetected during routine follow-up. We evaluated the clinical utility of an electrical impedance-based, machine learning method for detecting postoperative electrode array migration using routinely acquired telemetry data. In this retrospective analysis, we evaluated impedance telemetry data from 32 cochlear implant cases (16 with radiologically confirmed electrode array migration and 16 matched stable controls). A random forest regression model was trained to estimate the longitudinal position of the most basal electrode based on transimpedance matrices, cochlear dimensions, and implant parameters. Model predictions were compared against radiological ground truth, and migration was detected using a defined threshold of 1 mm. Electrode array migration was detected with a sensitivity of 88% and a specificity of 100%. Migration was identified in clinically inconspicuous cases with largely unremarkable impedance trajectories and across long-term follow-up. In addition to electrode emigration, postoperative imaging revealed non-surgically induced electrode immigration, a phenomenon not previously reported. Impedance-based machine learning could enable radiation-free detection of cochlear implant electrode array migration during routine follow-up. This low-burden approach has the potential to support earlier clinical review and intervention, particularly in pediatric patients. While this study represents a first proof-of-concept, validation on larger cohorts could allow this low-burden approach to be readily integrated into standard post-implantation care. The approach could enable earlier intervention and reduce revision surgeries in pediatric CI patients.