The role of oxidative stress in the susceptibility of noise-impaired cochleae to synaptic loss induced by intracochlear electrical stimulation

Predicting Acoustic Hearing Preservation Following Cochlear Implant Surgery Using Machine Learning

OBJECTIVES

The aim of the study was to train and test supervised machine-learning classifiers to predict acoustic hearing preservation after CI using preoperative clinical data.

STUDY DESIGN

Retrospective predictive modeling study of prospectively collected single-institution CI dataset.

METHODS

One hundred and seventy-five patients from a REDCap database including 761 patients >18 years who underwent CI and had audiometric testing preoperatively and one month after surgery were included. The primary outcome variable was the lowest quartile change in acoustic hearing at one month after CI using various formulae (standard pure tone average, SPTA; low-frequency PTA, LFPTA). Analysis involved applying multivariate logistic regression to detect statistical associations and training and testing supervised learning classifiers. Classifier performance was assessed with numerous metrics including area under the receiver operating characteristic curve (AUC) and Matthews correlation coefficient (MCC).

RESULTS

Lowest quartile change (indicating hearing preservation) in SPTA was positively associated with a history of meningitis, preoperative LFPTA, and preoperative SPTA. Lowest quartile change in SPTA was negatively associated with sudden hearing loss, noise exposure, aural fullness, and abnormal anatomy. Lowest quartile change in LFPTA was positively associated with preoperative LFPTA. Lowest quartile change in LFPTA was negatively associated with tobacco use. Random forest demonstrated the highest mean classification performance on the validation dataset when predicting each of the outcome variables.

CONCLUSIONS

Machine learning demonstrated utility for predicting preservation of residual acoustic hearing in patients undergoing CI surgery, and the detected associations facilitated the interpretation of our machine-learning models. The models and statistical associations together may be used to facilitate improvements in shared clinical decision-making and patient outcomes.

LEVEL OF EVIDENCE

3 Laryngoscope, 134:926-936, 2024.

Redox homeostasis dysregulation in noise-induced hearing loss: oxidative stress and antioxidant treatment

Noise exposure is an important cause of acquired hearing loss. Studies have found that noise exposure causes dysregulated redox homeostasis in cochlear tissue, which has been recognized as a signature feature of hearing loss. Oxidative stress plays a pivotal role in many diseases via very complex and diverse mechanisms and targets. Reactive oxygen species are products of oxidative stress that exert toxic effects on a variety of physiological activities and are considered significant in noise-induced hearing loss (NIHL). Endogenous cellular antioxidants can directly or indirectly counteract oxidative stress and regulate intracellular redox homeostasis, and exogenous antioxidants can complement and enhance this effect. Therefore, antioxidant therapy is considered a promising direction for NIHL treatment. However, drug experiments have been limited to animal models of NIHL, and these experiments and related observations are difficult to translate in humans; therefore, the mechanisms and true effects of these drugs need to be further analyzed. This review outlines the effects of oxidative stress in NIHL and discusses the main mechanisms and strategies of antioxidant treatment for NIHL.