Based on the middle ear negative pressure and multimodal data to construct and externally validate the predictive model for pediatric obstructive sleep apnea.

PURPOSE: The aim of this study was to analyze negative middle ear pressure in children with obstructive sleep apnea (OSA) and establish and evaluate predictive models according to these findings.

METHODS

This retrospective study involved 931 children: 715 with OSA and 216 controls. Demographic, clinical, lateral head radiograph, and tympanometry data were collected. These characteristics of children with OSA were analyzed, with a particular focus on exploring the value of middle ear-related parameters for the diagnosis of pediatric OSA. Additionally, a logistic regression model incorporating optimal indicators was developed to predict pediatric OSA. The model was visualized via a nomogram and evaluated for discrimination, calibration, clinical effectiveness and external validation.

RESULTS

Children with OSA were younger and exhibited longer soft palates, larger tonsils and adenoids than non-OSA children. Additionally, children with OSA presented higher acoustic admittance (AC) and resonance frequency (RF), lower middle ear pressure (MEP), and narrower pressure gradient (PG) than non-OSA children. The external auditory canal volume (ECV), MEP, and PG were identified as independent predictors of childhood OSA. We constructed a foundational prediction model for childhood OSA (Model 0, AUC = 0.845, 95% CI: 0.813-0.878), and then added each tympanometric indicator to the model individually. After incorporating MEP into the model (Model 4), the AUC increased by 0.022 (p < 0.05).

CONCLUSIONS

Based on a large sample size and multivariate analysis of factors associated with pediatric OSA, we developed a predictive model incorporating middle ear negative pressure for pediatric OSA, which may assist clinicians in diagnosing pediatric OSA in complex clinical settings.