A paper titled Investigation of hit-and-run crash severity through explainable machine learning authored by Stella Roussou, Apostolos Ziakopoulos and George Yannis, as been published in Transportation Letters. This study, uses a 5-year dataset from Victoria, Australia and analyzed with CatBoost algorithms and SHAP values using explainable machine learning techniques, to highlight key severity factors. Findings suggest that the presence of police at the crash scene emerges as the most critical determinant, underscoring the importance of law enforcement in mitigating severe crash outcomes. Furthermore crashes involving passenger vehicles and those on weekends were also linked to higher severity. These novel findings offer valuable insights for targeted interventions and policy-making to mitigate the impact of severe hit-and-run crashes and enhance road safety.