Predicting poor school performance in children suspected for sleep-disordered breathing

Area of Science:

• Pediatric Sleep Medicine
• Neurocognition
• Child Health

Background:

• Habitual snoring in children is linked to poor school performance (PSP).
• Assessing sleep-disordered breathing (SDB) is crucial for identifying children at risk of PSP.
• Conventional SDB measures may lack sufficient predictive power.

Purpose of the Study:

• To evaluate the predictive ability of conventional sleep-disordered breathing (SDB) measures for poor school performance (PSP) in habitually snoring children.
• To determine if a prediction model combining SDB factors can improve PSP prediction.

Main Methods:

• Retrospective analysis of the Hannover Study on Sleep Apnea in Childhood (HASSAC) dataset.
• Inclusion of habitually snoring primary school children, categorized by school performance.
• Evaluation of SDB measures (questionnaire, oximetry, polysomnography) using receiver operating characteristic curves and area under the curve (AUC).

Main Results:

• All individual SDB measures demonstrated low predictive accuracy (AUC < 0.8).
• The highest AUC for single measures was 0.686 (questionnaire), 0.565 (oximetry), and 0.624 (polysomnography).
• A prediction model combining five significant predictors achieved an adjusted AUC of 0.851.

Conclusions:

• Conventional SDB measures alone are insufficient for predicting PSP in children with suspected SDB.
• A clinical prediction model integrating multiple factors significantly enhances the prediction of PSP.
• Improved prediction can guide interventions for neurocognitive impairment in children with SDB.