Rationale: Serial smear analysis to guide respiratory isolation (RI) of tuberculosis (TB) suspects, the majority of whom will be found not to not have TB, leads to expensive and unnecessary isolation, and may potentially result in decreased vigilance of subjects with respiratory compromise. Objective: To compare the performance of a single first-sputum, TB Mycobacterium tuberculosis-specific nucleic acid amplification (NAA) test to three sputum smears for assessing the need for RI. Methods: Prospective evaluation of 493 TB suspects (74% HIV-positive) admitted to RI toin a major county hospital in the United States, who had at least 3 sputum smears and material available from the first sample for additional NAA testing. Measurements: Accuracy of the first sputum NAA result and serial smears for identifying potentially infectious TB patients and the need for RI. Main Results: 46 patients (9.3%) had TB confirmed by culture. First-sputum NAA test detected all TB patients who had a positive smear (n = 35), even when the first of the three specimens was smear-negative. In addition, when compared with serial smears, the first-sputum NAA had a higher sensitivity (0.87, 95%CI 0.74-0.95) and specificity (1.0) in the detection of subjects with positive M. tuberculosis cultures (smear sensitivity 0.76, 95% CI 0.61-0.87 and specificity 0.96, 95%CI 0.94-0.98). Conclusions: A single first-sputum NAA testing can rapidly and accurately identify the subset of TB suspects who require RI according to serial sputum smears. Its potential use to shorten RI time does not preclude the need to obtain subsequent specimens for culture.