Purpose: A nomogram model was constructed to assist in early prediction of idiopathic sudden sensorineural hearing loss (ISSHL) prognosis. Additionally, this study contributed to evaluating and analyzing the usefulness of the nomogram model in ISSHL clinical intervention.
Methods: A retrospective analysis was performed concerning 355 ISSHL patients who were hospitalized between June 2021 and August 2022. Single-factor analysis was used to filter variables, which were subsequently used for multivariate analysis to construct a nomogram. The discriminative capability and clinical usefulness of the predictive model were estimated by calculating the area under the curve (AUC), calibration curve, and decision curve analysis (DCA).
Results: Hearing loss type, duration from onset to treatment, vertigo, periauricular paresthesia, and batroxobin use were included in the nomogram for ISSHL. The predictive model showed fair discrimination values (AUC =0.764; 95%CI: 0.715-0.813) and was well-calibrated, the C-index was 0.746 (95%CI: 0.715-0.793) in the internal validation. DCA indicated that the model was also clinically beneficial when the threshold range was between 0.246 and 0.840.
Conclusions: The nomogram prediction model may have potential clinical practicability in effectively assisting clinicians in predicting ISSHL prognosis and optimizing treatment protocols.
Keywords: Idiopathic sudden sensorineural hearing loss; Nomogram; Prediction; Prognosis.
Copyright © 2022 Elsevier Inc. All rights reserved.