OBJECTIVES: Increased upper airway resistance during sleep, or snoring, is a risk factor for sleep disordered breathing, and has been implicated in the development of adverse cardiovascular outcomes as well as components of the metabolic syndrome such as obesity, insulin resistance, and dyslipidemia. Despite increasing awareness of the health risks associated with frequent snoring, many patients remain untreated and may be unaware of snoring, especially if living alone.  For this reason, we examined whether data available in routinely administered physiological and laboratory exams would prove useful in developing predictive models of habitual snoring. METHODS: A total of 10,482 respondents from the 2005-2008 National Health and Nutrition Examination Survey (NHANES), for which individual sleep survey, demographic, and physiological data were available, and who were not previously diagnosed with sleep apnea, were classified as frequent snorers (5 or more nights per week, n= 3222), or control (n=7260).  Sample data were partitioned into training (45%), validation (35%), and testing (30%) data sets using an equal stratification criterion for development of logistic regression, decision tree, and neural network predictive models using SAS Enterprise Miner. RESULTS: All three predictive modeling methods employed in this study were found to have similar misclassification rates, ranging from 34.24% for a neural network model to 34.96% for logistic regression, with waist circumference, body mass index, and gender as the primary risk factors for frequent snoring. Logistic regression also indicated that frequent snoring was associated with changes in levels of the liver damage marker serum gamma glutamyl transferase. CONCLUSIONS:  Our findings provide additional support for the hypothesis that frequent snorers may be at increased risk for the development of cardiovascular disease, metabolic dysfunction, and liver damage, and indicate that demographic, physiological, and medical data obtained in routine medical examinations can be useful to predict the risk of frequent snoring.