Public health surveillance has been defined as the ongoing systematic collection, analysis, interpretation, and dissemination of data regarding a health-related event for use in public health action to reduce morbidity and mortality and to improve health. Surveillance is an essential element of public health program infrastructure. The desirable attributes of public health surveillance systems are simplicity, flexibility, data quality, acceptability, sensitivity, predictive value positive, representativeness, timeliness, and stability. However, surveillance for periodontal diseases is nearly non-existent at state, county, or local levels in the United States. That void largely is the result of the current approach to monitoring periodontal diseases in populations, which generally requires resource-intensive primary collection of clinical data using relatively invasive methods. One potential alternative to that approach to periodontal disease surveillance is the use of self-reported data collected through population surveys. Seventeen identified studies have tested the validity of individual questionnaire items for their sensitivity, specificity, and predictive values positive and negative against a range of clinical operational definitions for periodontitis. No individual items seem to be robust or valid markers for clinically determined periodontitis. However, it is possible that a multivariable statistical modeling approach, which includes variables on signs, symptoms, and established risk factors, could improve the sensitivity and specificity of that approach. An example is given of a model-based approach to public health surveillance that has been effective in quantifying the impact of a public health problem, monitoring trends between and within states, and supporting advocacy and policy development by state and local governments.