Development and Validation of a Risk Prediction Model for Sudden Sensorineural Hearing Loss Based on a Nomogram

Objective: To establish and validate a namogram for predicting the risk of sudden sensorineural hearing loss (SSNHL). Methods: A retrospective analysis was conducted on 119 patients diagnosed with SSNHL in the Department of Otolaryngology-Head and Neck Surgery at Shaanxi Provincial People’s Hospital between October 1, 2022, and November 1, 2023 (observation group), as well as 70 healthy controls (control group), to create a modeling set. Additionally, 51 patients diagnosed with SSNHL and 30 healthy controls were collected from the same department during the same period as a validation set. Patient information, including gender, age, education level, marital status, occupation, living situation, history of hypertension, fasting blood glucose, triglycerides, rhinitis, pharyngitis, ear fullness, dizziness, headache, VAS scores for auditory hypersensitivity, SAS scores for anxiety, SDS scores for depression, THI scores for tinnitus, tinnitus duration, and sleep quality, were collected. Univariate and multivariate logistic regression analyses were performed to compare the clinical parameters of the modeling and validation sets, and a nomogram for predicting the risk of SSNHL was constructed and evaluated. Results: There were no statistically significant differences in general characteristics between the modeling and validation sets (P>0.05). Using univariate and multivariate logistic regression, six variables were selected for inclusion in the final predictive model: gender, education level, marital status, living situation, pharyngitis (VAS score), and tinnitus duration. A nomogram was constructed based on these variables. The H-L goodness-of-fit tests yielded P values of 0.5349 and 0.6763 for the modeling and validation sets, respectively. The C-index values were 0.963 and 0.980, indicating excellent predictive accuracy. The AUC values of the ROC curves were 0.970 (95% CI: 0.951-0.990) and 0.992 (95% CI: 0.981-1) for the modeling and validation sets, respectively, demonstrating excellent discriminative ability. Conclusion: Male gender, lower education level, unmarried status, living alone, absence of pharyngitis, and presence of persistent tinnitus were identified as independent risk factors for SSNHL in the western part of China. The nomogram based on these risk factors can effectively assess and quantify the risk of SSNHL.