Objective: To estimate the predictive ability of current obstructive sleep apnea (OSA) screening tools and the individual questions in these tools at identifying pregnant women who have OSA. Methods: A total of 293 third-trimester patients were enrolled between 2010 and 2012, and 248 patients had sleep monitor results. Recruited participants completed a questionnaire consisting of six OSA screening tools and overnight portable sleep monitoring. Predictive ability of the screening tools for OSA compared with results of the diagnosis from overnight sleep monitoring was estimated using the area under receiver operating characteristic curves. Results: Two hundred eighteen (88%) of the patients were OSA-negative, and 30 patients (12%) were OSA-positive based on sleep monitoring results. Compared with OSA-negative patients, OSA-positive patients had greater body mass indices and neck circumferences as well as significantly higher rates of hypertension (chronic and gestational), pregestational diabetes mellitus, asthma, and preeclampsia. The overall predictive ability of the screening tools for OSA was modest (area under receiver operating characteristic curves 0.62-0.695). However, individual components of the questionnaire were strongly associated with OSA. Conclusion: We found that none of the studied OSA screening tools accurately detected OSA in pregnant women in the third trimester. We have identified proposed elements of a new screening tool based on promising components from several tools that may more accurately detect patients with OSA.