Instruments to assess secondhand smoke exposure in large cohorts of never smokers: the smoke scales

Abstract

(i) to develop questionnaires that can identify never-smoking children and adults experiencing increased exposure to secondhand smoke (SHS+), (ii) to determine their validity against hair nicotine, and (iii) assess their reliability. A sample of 191 children (85 males; 106 females; 7-18 years) and 95 adult (23 males; 72 females; 18-62 years) never-smokers consented to hair nicotine analysis and answered a large number of questions assessing all sources of SHS. A randomly-selected 30% answered the questions again after 20-30 days. Prevalence of SHS+ in children and adults was 0.52±0.07 and 0.67±0.10, respectively (p<0.05). The Smoke Scale for Children (SS-C) and the Smoke Scale for Adults (SS-A) were developed via factor analysis and included nine questions each. Positivity criteria for SS-C and SS-A via receiver operating characteristics curve analysis were identified at >16.5 and >16, respectively. Significant Kappa agreement (p<0.05) was confirmed when comparing the SS-C and SS-A to hair nicotine concentration. Reliability analyses demonstrated that the SS-C and SS-A scores obtained on two different days are highly correlated (p<0.001) and not significantly different (p>0.05). Area under the curve and McNemar's Chi-square showed no pair-wise differences in sensitivity and specificity at the cutoff point between the two different days for SS-C and SS-A (p>0.05). We conclude that the SS-C and the SS-A represent valid, reliable, practical, and inexpensive instruments to identify children and adult never-smokers exposed to increased SHS. Future research should aim to further increase the validity of the two questionnaires.

Figure 1. Receiver operating characteristics (ROC) curves for SS-C (A) and SS-A (B) indicating the designated cut off points at 16.5 and 16, respectively.

The points at the ROC curve at the designated cut offs for SS-C (C) and SS-A (D) forms 1 and 2 are also illustrated.