Nomogram Prediction Model for the Prognosis of Idiopathic Sudden Sensorineural Hearing Loss

This study aimed to develop a nomogram-based predictive model for the prognosis of idiopathic sudden sensorineural hearing loss (SSNHL).

Retrospective data from 1108 patients with SSNHL who visited a tertiary center from January 2015 to May 2023 were analyzed. Hearing outcomes were categorized into recovery and nonrecovery groups based on Siegel criteria, and the final hearing level ranged from class A to D according to the American Academy of Otolaryngology-Head and Neck Surgery (AAO-HNS) classification. Both univariate and multivariate analyses were conducted to identify variables influencing hearing recovery. Subsequently, a nomogram was constructed to estimate the probability of complete recovery and class A.

Multivariate analysis revealed that age, presence of vertigo, time from symptom onset to presentation, initial hearing threshold on both affected and unaffected sides, and initial word recognition scores were significant risk factors for hearing recovery. The nomogram prediction model for complete recovery, based on Siegel criteria, demonstrated an accuracy of 0.788 and an area under the curve (AUC) of 0.858. In addition, the nomogram prediction model for class A according to the AAO-HNS classification showed an accuracy of 0.761 and an AUC of 0.844.

Age, presence of vertigo, time from symptom onset to presentation, and initial hearing status were identified as significant risk factors for hearing recovery. The nomogram prediction model may have the potential to contribute to clinicians making more informed decisions regarding the prognosis, counseling, and personalized management for idiopathic SSNHL.