Machine Learning-Based Prediction of the Outcomes of Cochlear Implantation in Patients With Cochlear Nerve Deficiency and Normal Cochlea: A 2-Year Follow-Up of 70 Children

Abstract

Cochlear nerve deficiency (CND) is often associated with variable outcomes of cochlear implantation (CI). We assessed previous investigations aiming to identify the main factors that determine CI outcomes, which would enable us to develop predictive models. Seventy patients with CND and normal cochlea who underwent CI surgery were retrospectively examined. First, using a data-driven approach, we collected demographic information, radiographic measurements, audiological findings, and audition and speech assessments. Next, CI outcomes were evaluated based on the scores obtained after 2 years of CI from the Categories of Auditory Performance index, Speech Intelligibility Rating, Infant/Toddler Meaningful Auditory Integration Scale or Meaningful Auditory Integration Scale, and Meaningful Use of Speech Scale. Then, we measured and averaged the audiological and radiographic characteristics of the patients to form feature vectors, adopting a multivariate feature selection method, called stability selection, to select the features that were consistent within a certain range of model parameters. Stability selection analysis identified two out of six characteristics, namely the vestibulocochlear nerve (VCN) area and the number of nerve bundles, which played an important role in predicting the hearing and speech rehabilitation results of CND patients. Finally, we used a parameter-optimized support vector machine (SVM) as a classifier to study the postoperative hearing and speech rehabilitation of the patients. For hearing rehabilitation, the accuracy rate was 71% for both the SVM classification and the area under the curve (AUC), whereas for speech rehabilitation, the accuracy rate for SVM classification and AUC was 93% and 94%, respectively. Our results identified that a greater number of nerve bundles and a larger VCN area were associated with better CI outcomes. The number of nerve bundles and VCN area can predict CI outcomes in patients with CND. These findings can help surgeons in selecting the side for CI and provide reasonable expectations for the outcomes of CI surgery.

A Positive Response around 4.6 ms in Auditory Brainstem Response in Cochlear Nerve Deficiency Infants

“…The copyright holder for this preprint this version posted January 7, 2023. ; https://doi.org/10.1101/2023.01.05.22283540 doi: medRxiv preprint vestibulocochlear nerve to facial nerve (Han et al 2019), vestibulocochlear nerve area and the number of nerve bundles (Lu et al 2022) were applied. However, all those indicators are based on imaging examinations.…”

“…For the same reason, once the infants are diagnosed with unilateral CND, if the hearing of the other ear is within normal, CI is just an alternative. To create an objective predictive model for the outcome of CI in patients with CND, indicators such as BCNC width (Chung et al 2018), the area ratio of 12 vestibulocochlear nerve to facial nerve (Han et al 2019), vestibulocochlear nerve area and the number of nerve bundles (Lu et al 2022) were applied. However, all those indicators are based on imaging examinations.…”

“…For the same reason, once the infants are diagnosed with unilateral CND, if the hearing of the other ear is within normal, CI is just an alternative. Many researchers are looking for objective predictive models for the outcome of CI in patients with CND 16,[28][29][30] . However, all those indicators are based on imaging examinations.…”

“…It was suggested that expected benefit can be dependent on the status of the CN. As a result, researchers have looking for the predictive role of the status of the cochlear nerve in radiographic images for CI outcomes in CND patients, such as the diameter of the internal auditory canal 12,15 , internal auditory meatus nerve grading system 11 , number of nerve bundles and vestibulocochlear nerve area 16 . Kari et al concluded that current imaging modalities cannot accurately depict the status of the cochleovestibular nerve or predict a child's benefit with a CI 15 .…”