BMC Public Health (Jan 2024)

Validity across four common street-crossing distraction indicators to predict pedestrian safety

  • Peishan Ning,
  • Cifu Xie,
  • Peixia Cheng,
  • Li Li,
  • David C. Schwebel,
  • Yang Yang,
  • Jieyi He,
  • Jie Li,
  • Guoqing Hu

DOI
https://doi.org/10.1186/s12889-024-17756-y
Journal volume & issue
Vol. 24, no. 1
pp. 1 – 11

Abstract

Read online

Abstract Background Multiple distraction indicators have been applied to measure street-crossing distraction but their validities in predicting pedestrian safety are poorly understood. Methods Based on a video-based observational study, we compared the validity of four commonly used distraction indicators (total duration of distraction while crossing a street, proportion of distracted time over total street-crossing time, duration of the longest distraction time, and total number of distractions) in predicting three pedestrian safety outcomes (near-crash incidence, frequency of looking left and right, and speed crossing the street) across three types of distraction (mobile phone use, talking to other pedestrians, eating/drinking/smoking). Change in Harrell’s C statistic was calculated to assess the validity of each distraction indicator based on multivariable regression models including only covariates and including both covariates and the distraction indicator. Results Heterogeneous capacities in predicting the three safety outcomes across the four distraction indicators were observed: 1) duration of the longest distraction time was most predictive for the occurrence of near-crashes and looks left and right among pedestrians with all three types of distraction combined and talking with other pedestrians (Harrell’s C statistic changes ranged from 0.0310 to 0.0335, P < 0.05), and for the occurrence of near-crashes for pedestrians involving mobile phone use (Harrell’s C statistic change: 0.0053); 2) total duration of distraction was most predictive for speed crossing the street among pedestrians with the combination and each of the three types of distraction (Harrell’s C statistic changes ranged from 0.0037 to 0.0111, P < 0.05), frequency of looking left and right among pedestrians distracted by mobile phone use (Harrell’s C statistic change: 0.0115), and the occurrence of near-crash among pedestrians eating, drinking, or smoking (Harrell’s C statistic change: 0.0119); and 3) the total number of distractions was the most predictive indicator of frequency of looking left and right among pedestrians eating, drinking, or smoking (Harrell’s C statistic change: 0.0013). Sensitivity analyses showed the results were robust to change in grouping criteria of the four distraction indicators. Conclusions Future research should consider the pedestrian safety outcomes and type of distractions to select the best distraction indicator.

Keywords