Preoperative Neuroanatomical Features Outperform Non-Neural Features in Predicting Auditory Skills in Chinese-Learning Children After Cochlear Implantation

Children with cochlear implants (CIs) exhibit significant variations in terms of auditory and language development. Therefore, it is crucial to predict individual-level post-CI outcomes and provide early interventions to those who may experience limited benefits from CIs. Our study used preoperative neuroanatomical features to predict auditory development in Chinese-learning children with CIs. The whole-brain structure of Chinese-learning pediatric CI candidates was examined by voxel-based morphometry analysis. Machine learning was employed using neuroanatomical features to predict children’s auditory skills up to 24 months after CI. The whole-brain neural model and auditory/visual cortex neural model were compared with a non-neural model using gender, age at CI activation, and preoperative residual hearing as predictors. Model performance was quantified using the mean squared error between predicted values and observations. The preoperative neuroanatomical features outperformed the non-neural features in predicting auditory skills in children with CIs. Specifically, the auditory-related area played an important role in predicting post-CI outcomes. These results indicate that neural structure holds the potential to serve as an objective and effective feature for predicting post-CI outcomes.