BACKGROUND: An epidural test dose containing epinephrine may be incomplete marker of incidental intravenous injection or migration of the epidural catheter in adult patients under general anesthesia. This study tests the hypothesis that the efficacy of simulated epidural test doses in anesthetized adult can be used to predict the adequacy of correct catheter placement. METHODS: Seventy-five healthy adult patients were randomly assigned to inject intravenously one of 5 solutions, either 2% lidocaine 3ml and epinephrine 15 microgram(Group E15, n=15) or epinephrine 20 microgram (Group E20. n=15) or isoproterenol 3microgram (Group I3, n=15) or isoproterenol 5microgram (Group I5, n=15) and 0.9% saline(Group NS, n=15), which was anesthetized with isoflurane and nitrous oxide. After the injection, a blinded observer recorded systolic blood pressure(SBP) and heart rate(HR) every 30seconds for 4minutes and the changes were analyzed. RESULTS: Although none in the saline group developed a HR increase> or20bpm, 6, 10, 12 and 15 patients elicited positive reponses in group E15, I3, E20, and I5(40%, 67%, 80% and 100% sensitivities), respectively. Meanwhile, none in the saline group developed a SBP increase> or15mmHg and 11, 1, 14 and 4 patients elicited positive reponses in E15, I3, E20, and I5(73%, 7%, 93% and 27% sensitivities), respectively. CONCLUSIONS: We conclude that under isoflurane anesthesia, (a) epinephrine 15 microgram or isoproterenol 3microgram is not reliable marker for incidental intravenous injection or migration of the epidural catheter, (b) epinephrine 20 microgram is applicable on SBP criterion and, (c) isoproterenol 5 microgram is applicable on HR criterion.