To evaluate the response of patients with chronic atrial fibrillation (AF) to exercise and to demonstrate if prognosis could be predicted, 200 male patients (64 +/- 1 years) with AF were identified retrospectively who underwent resting echocardiography and symptom-limited treadmill testing. They were classified by underlying disease into three subgroups: hypertension or no underlying disease (LONE; n = 102), ischemic heart disease (IHD; n = 45) and history of congestive heart failure or valvular disease (CHF-VD; n = 53). Maximal exercise capacities for LONE, IHD and CHF-VD were (mean +/- 1 SEM) 8.0 +/- 0.3, 6.4 +/- 0.4 and 6.0 +/- 0.3 metabolic equivalents, respectively (p < 0.01), and resting left ventricular ejection fractions were 61.7 +/- 1.6, 60.1 +/- 2.2 and 49.5 +/- 1.9%, respectively (p < 0.01). Stepwise multiple regression analysis demonstrated that, except for group classification (R2 = 0.13, p < 0.01), no clinical, exercise or morphologic variables could predict exercise capacity. After a mean 39.1-month follow-up (range 1-78), 17 of the 200 had died from cardiovascular causes. The rate of cardiac death using Kaplan-Meier survival analysis was significantly greater in CHF-VD patients (p < 0.01). However, Cox hazard function and Kaplan-Meier survival analysis demonstrated that neither echocardiographic measurements of cardiac size or function at rest, nor exercise or clinical variables were significant predictors of outcome. AF patients with a history of CHF and/or VD demonstrated a reduced exercise tolerance ad a worse prognosis than those without morphologic heart disease or those with IHD.(ABSTRACT TRUNCATED AT 250 WORDS)