Background: The STOP-BANG questionnaire screens for obstructive sleep apnoea (OSA) in surgical patients. In prior research, the association of STOP-BANG scores with comorbidities and outcomes was inconsistent. The objective of this study was to evaluate the validity of the STOP-BANG score. Methods: We conducted a retrospective cohort study of patients undergoing major elective noncardiac surgery at the University Health Network (Toronto, ON, Canada) between 2011 and 2015. Cross-sectional construct validity was evaluated based on proportions with diagnosed OSA across STOP-BANG strata. Concurrent construct validity was assessed based on the correlation of STOP-BANG with ASA Physical Status (ASA-PS), the Revised Cardiac Risk Index, and the Charlson Comorbidity Index. Predictive validity was assessed based on the adjusted associations of STOP-BANG risk with 30-day mortality (logistic regression), cardiac complications (logistic regression), and length-of-stay (negative binomial regression). Results: Of 26 068 patients in the cohort, 58% were in the low-risk STOP-BANG stratum, 23% in the intermediate-risk stratum, and 19% in the high-risk stratum. The proportion with previously diagnosed OSA was 4% (n¼615) in the low-risk stratum, 12% (n¼740) in the intermediate-risk stratum, and 44% (n¼2142) in the high-risk stratum. The correlations of STOP-BANG with ASA-PS (Spearman r¼0.28), Revised Cardiac Risk Index (r¼0.24), and Charlson Comorbidity Index (r¼0.10) were weak, albeit statistically significant (P<0.001). After risk-adjustment, STOP-BANG risk strata were not associated with 30-day mortality, cardiac complications, or length-of-stay. Conclusions: The STOP-BANG questionnaire has modest construct validity but did not predict postoperative mortality, hospital length-of-stay, or cardiac complications.