A paper titled Crash risk factors in the evolution from conventional to fully automated vehicles in urban environments authored by Maria Oikonomou and George Yannis has been published in Case Studies on Transport Policy. This Paper investigates the evolution of crash risk in urban road networks as the market penetration of Autonomous Vehicles (AVs) increases across different levels of automation, using microscopic traffic simulations in a dense metropolitan area of Athens, Greece. The Study integrates conventional vehicles, partially automated (SAE Level 2-3), fully automated (SAE Level 4-5) and aggressively behaving AVs across 15 progressive deployment scenarios, employing an XGBoost machine learning model combined with SHAP explainability to identify the most influential traffic and behavioural features associated with crash risk. The findings suggest that automation influences crash risk in a way that is neither uniform nor isolated, with fully automated vehicles reducing crash risk as their share grows, while partially automated vehicles slightly increase it in mixed-traffic conditions. Aggressively behaving AVs were found to have minimal impact, mostly at high penetration rates, while traffic density, stop sign-controlled sections and queue length emerged as the most influential factors overall. These findings underscore the need for network-specific planning and offer guidance for AV deployment, infrastructure upgrades and regulatory frameworks to support a safer transition to automated mobility.