Morris KL, et al. - Authors evaluated if decision-based modeling can be used to identify patterns of sun-protective behaviors related to the likelihood of sunburn. They also compared the predictive value of this method with traditional (ie, composite score) measurement approaches. The interactive and sometimes counterintuitive effects of multiple sun-protective behaviors on likelihood of sunburn were shown by this innovative application of a decision tree analytic approach. Findings demonstrated the limitations of traditional measurement approaches of behavior and importance of linking behavior to a clinically relevant outcome was suggested. Improving efforts in skin cancer prevention have the potential for a significant effect on public health based on the scope of those affected and enormous associated health care costs.

Methods

• Researchers evaluated whether decision-based modeling can be used to identify patterns of sun-protective behaviors associated with the likelihood of sunburn and compared the predictive value of this method with traditional (ie, composite score) measurement approaches.
• In this cross-sectional study, they used a nationally representative sample of 31,162 US adults from the 2015 National Health Interview Survey, consisting of household interviews conducted in person and completed by telephone when necessary.
• Civilian noninstitutionalized US adults were the participants.
• They collected the data from January 1 through December 31, 2015.
• They evaluated the associations among sun sensitivity, multiple sun-protective behaviors (ie, using sunscreen, seeking shade, wearing a hat, and wearing protective clothing), and sunburn using a χ² automatic interaction detection method for decision tree analysis.
• A comparison of the results was done with a composite score approach.

Results

• Findings suggested that in this study population of 28,558 respondents with complete data (54.1% women; mean [SD] age, 49.0 [18.0] years), 20 patterns of sun protection were identified.
• Among 15,992 sun-sensitive individuals, the highest likelihood of sunburn (62.4%) was seen in those who used only sunscreen.
• As per data, the group with the lowest likelihood of sunburn did not report using sunscreen but engaged in the other 3 protective behaviors (24.3% likelihood of sunburn).
• Among 12,566 non–sun-sensitive individuals, the lowest likelihood of sunburn (6.6%) was seen in those who engaged in all 4 protective behaviors.
• Those who only reported sunscreen use (26.2%), had the highest likelihood of sunburn.
• Results demonstrated that the decision tree model and the composite score approach correctly classified a similar number of cases; nonetheless in classifying cases with sunburn the decision tree model was superior (44.3% correctly classified in the decision tree vs 25.9% with the composite score).