RATIONALE: Pediatric obstructive sleep apnea (OSA) is common, and a delay in diagnosis can lead to significant morbidity. Polysomnography (PSG) is the gold standard for the diagnosis of OSA. However, difficulty accessing PSG due to the relative shortage of sleep centers with pediatric expertise can lead to a delay in the diagnosis and management of OSA. OBJECTIVES: To assess the utility of Mallampati score (sitting and supine) in predicting the presence and severity of OSA in children. METHODS: A retrospective study of 158 children from a single pediatric sleep center. All patients had a PSG and a physical examination documenting Mallampati score. The Mallampati score, tonsillar size, age, sex, and apnea hypopnea index (AHI) were analyzed. Odds ratio of having pediatric OSA (AHI > 1) with increase in Mallampati score and tonsillar size were calculated. MEASUREMENTS AND MAIN RESULTS: A significant correlation was found between Mallampati score, tonsillar size, and AHI. For every point increase in the Mallampati score, the odds ratio of having OSA increased by more than 6-fold. For every point increase in tonsillar size, the odds ratio of having OSA increased by more than 2-fold. CONCLUSIONS: Mallampati score and tonsillar size are independent predictors of OSA. Oral examination including Mallampati score and tonsillar size should be considered when evaluating a patient for OSA. They can be used to prioritize children who may need PSG.