The use of clinical prediction formulas in the evaluation of obstructive sleep apnea

Study Objectives: To prospectively study the utility of four clinical predi ction models for either predicting the presence of obstructive sleep apnea (OSA, apnea-hypopnea index [AHI] greater than or equal to 10/hour), or prio ritizing patients for a split-night protocol (AHI (3)20/hour). Design: All patients presenting for OSA evaluation completed a research que stionnaire that included questions from previously developed clinical predi ction models. The probability of sleep apnea for each patient for each mode l was calculated based upon the equation used in the model. Based upon two cutoffs of apnea-hypopnea index, 10 and 20, the sensitivity, specificity, a nd positive predictive value were calculated. For the cutoffs AH greater th an or equal to 10 and greater than or equal to 20, receiver operating chara cteristic curves were generated and the areas under the curves calculated. Comparisons of demographic information and symptom response were compared b etween patients with and without OSA, and men vs. women. Setting: Urban, accredited sleep disorders center. Patients or Participants: All patients referred for evaluation of OSA who u nderwent polysomnography. Interventions: N/A Results: 370 patients (191 men, 179 women) completed the study. 248 of the 370 (67%) patients had an AHI(3)10; 180 of the 370 (49%) had an AHI greater than or equal to 20. For AHI greater than or equal to 10, the sensitivitie s ranged from 76 to 96%, specificities from 13%-54%, positive predictive va lues from 69%-77% using the probability cutoff of the original investigator s; the areas under the curve from 0.669 to 0.736. For AHI(3)20, the areas u nder the ROC curves ranged from 0.700 to 0.757; using cutoffs to maximized specificity, the sensitivities ranged from 33%-39%, specificities from 87%- 93%, and positive predictive values from 72%-85%. All the models performed better for men. Conclusions: The clinical prediction models tested are not be sufficiently accurate to discriminate between patients with or without OSA but could be useful in prioritizing patients for split-night polysomnography.