Coronary heart disease is responsible for one of every five deaths in the United States. Recent epidemiological studies have shown an association between periodontal disease and coronary heart disease. The purpose of this cross-sectional study was to verify this association using data from the third National Health and Nutrition Examination Survey (NHANES III). Data for 5564 people 40 years of age and older who had complete periodontal assessments and information on heart attack were evaluated. The outcome was the self-reported history of heart attack (yes vs. no). The main independent variable was the percent of periodontal sites per person with attachment loss of 3 mm or greater (categorized as 0%, > 0-33%, > 33-67%, and > 67%). Periodontal attachment loss was measured at two sites per tooth in randomly assigned half-mouths, one upper and one lower quadrant. The covariables included sociodemographic variables and established risk factors for cardiovascular disease. Relative to the 0% category, the unadjusted odds of heart attack increased with each higher category of attachment loss-2.2 (95% confidence interval = 1.3-3.8), 5.5 (3.4-9.1), and 9.8 (4.5-21.0), respectively. Adjustment for age, sex, race, poverty, smoking, diabetes, high blood pressure, body mass index, and serum cholesterol decreased these odds to 1.4 (0.8-2.5), 2.3 (1.2-4.4), and 3.8 (1.5-9.7), respectively. This study supports findings from previous studies of an association between periodontal disease and coronary heart disease.