A common clinical dilemma faced by sleep physicians is in deciding the level of severity at which patients with obstructive sleep apnea (OSA) should be treated. There is particular uncertainty about the need for, and the effectiveness of, treatment in mild cases. To help define the role of nasal continuous positive airway pressure (CPAP) treatment in mild OSA we undertook a randomized controlled cross-over trial of CPAP in patients with an apnea- hypopnea index (AHI) of 5 - 30 (mean, 12.9 +/- 6.3 SD). Twenty-four-hour blood pressure and neurobehavioral function were measured at baseline, after 8 wk of treatment with CPAP, and after 8 wk of treatment with an oral placebo tablet. Twenty-eight of 42 patients enrolled in the study completed both treatment arms. Baseline characteristics were not different between those who completed the study and those who did not complete the study. Patients used CPAP for a mean (SD) of 3.53 (2.13) h per night and the mean AHI on the night of CPAP implementation was 4.24 (2.9). Nasal CPAP improved self-reported symptoms of OSA, including snoring, restless sleep, daytime sleepiness, and irritability (in-house questionnaire), more than did placebo, but did not improve objective (Multiple Sleep Latency Test) or subjective (Epworth Sleepiness Scale) measures of daytime sleepiness. We found no benefit of CPAP over placebo in any tests of neurobehavioral function, generic SF-36 (36-item Short Form Medical Outcomes Survey) or sleep-specific (Functional Outcomes of Sleep Questionnaire) quality of life questionnaires, mood score (Profile of Moods States and Beck Depression Index), or 24-h blood pressure. However, the placebo tablet resulted in a significant improvement in a wide range of functional variables compared with baseline. This placebo effect may account for some of the treatment responses to CPAP observed previously in patients with mild OSA.