Comparing the effects of infrastructure on bicycling injury at intersections and non-intersections using a case-crossover design

Abstract

Background: This study examined the impact of transportation infrastructure at intersection and non-intersection locations on bicycling injury risk.

Methods: In Vancouver and Toronto, we studied adult cyclists who were injured and treated at a hospital emergency department. A case-crossover design compared the infrastructure of injury and control sites within each injured bicyclist's route. Intersection injury sites (N=210) were compared to randomly selected intersection control sites (N=272). Non-intersection injury sites (N=478) were compared to randomly selected non-intersection control sites (N=801).

Results: At intersections, the types of routes meeting and the intersection design influenced safety. Intersections of two local streets (no demarcated traffic lanes) had approximately one-fifth the risk (adjusted OR 0.19, 95% CI 0.05 to 0.66) of intersections of two major streets (more than two traffic lanes). Motor vehicle speeds less than 30 km/h also reduced risk (adjusted OR 0.52, 95% CI 0.29 to 0.92). Traffic circles (small roundabouts) on local streets increased the risk of these otherwise safe intersections (adjusted OR 7.98, 95% CI 1.79 to 35.6). At non-intersection locations, very low risks were found for cycle tracks (bike lanes physically separated from motor vehicle traffic; adjusted OR 0.05, 95% CI 0.01 to 0.59) and local streets with diverters that reduce motor vehicle traffic (adjusted OR 0.04, 95% CI 0.003 to 0.60). Downhill grades increased risks at both intersections and non-intersections.

Conclusions: These results provide guidance for transportation planners and engineers: at local street intersections, traditional stops are safer than traffic circles, and at non-intersections, cycle tracks alongside major streets and traffic diversion from local streets are safer than no bicycle infrastructure.

Figure 1

Process by which injury and control sites were matched based on whether injuries occurred at intersections or not in a case–crossover study conducted in Vancouver and Toronto (Canada).

Figure 2

Intersections: results of conditional logistic regression analyses of associations between infrastructural characteristics and bicycling injury in a case–crossover study conducted in Vancouver and Toronto (Canada). Shown are the effects for single variables (left) and for all these variables together in the final multiple regression model (right), with final variables selected via a backward selection (comparison of N=210 injury sites and N=272 control sites, all at intersections). Closed circles represent the reference category for each variable.

Figure 3

Non-intersections: results of conditional logistic regression analyses of associations between infrastructural characteristics and bicycling injury in a case–crossover study conducted in Vancouver and Toronto (Canada). Shown are the effects for single variables (left) and for all these variables together in the final multiple regression model (right), with final variables selected via a backward selection (comparison of N=478 injury sites and N=801 control sites, all at non-intersection locations). Closed circles represent the reference category for each variable.

Figure 4

A typical traffic circle found in residential areas of Vancouver, designed to calm motor vehicle traffic, but found to increase risk at intersections of local streets in this study. (A) Photograph as viewed from the perspective of an approaching cyclist. (B) Design dimensions of traffic circle (derived from measurements taken throughout the city). The dashed arrow shows the route a cyclist is required to take when turning left.