In many major cities, bicycle usage is on the increase and cycling safety is becoming a critical issue. Most of the existing studies are based on police data which understate both single-bicycle accidents as well as cyclist victims. In France, an estimation based on a road trauma database reveals that cyclists are 8 times more likely to be injured per hour spent on the road compared to motorists. To give a full picture of cycling accidents, as well as to understand how cyclist behavior interacts with other factors in causing accidents, we sur-veyed all injured cyclists in the period 2009-2011, as identified in a medical database of road trauma victims in a French territorial 'départment' (the Rhône, capital city Lyon). Using classification methods we build a typology of 17 recurring configurations of cycling collisions and single-bicycle accidents: 7 concern utilitarian riding (commuting ...), 3 concern recreational riding and 7 concern cycling as a sporting activity. A Multiple Correspondence Analysis (MCA) is then used to check the consistency of this typology, and to gain additional insight on road user behavior by projection of supplementary variables. External factors contributing to cycling accidents, such as 'bad weather' (13%) or 'riding at night' (14%), roadway configuration such as 'cycling infrastructure' (16%) or 'intersections' (25%), and cyclist behavior such as 'alcohol consumption' (5%) or 'speed' (25%) are discriminatory variables that interact in many accident configurations. This study shows how road user behavior-influences each step in the chain of events leading to an accident. In the discussion of study results, some recommendations are made to public authorities aimed at improving cyclist safety.