Quantifying the life-saving impact of seatbelt usage: A random forest analysis of unobserved heterogeneity and latent risk factors in vehicular fatalities

Abstract

Seatbelt use significantly reduces the severity of injuries and fatalities in vehicular accidents. This study leverages the Random Forest algorithm to evaluate the impact of seatbelt usage on fatality probabilities in Thailand, with a novel focus on drivers who caused the accidents. The model demonstrated high accuracy, correctly identifying 95.10 % of non-fatal cases and 91.60 % of fatal cases, though some misclassifications were observed. A key contribution of this research is the identification of hidden risk factors influencing fatality rates, including temporal patterns that revealed a surge in fatalities after 17:00, with increased risks associated with non-seatbelt use during late evening and early morning hours. Younger drivers, particularly active at night, were found to exhibit higher rates of non-seatbelt usage and were more likely to be involved in severe accidents. These findings highlight the critical need for targeted seatbelt enforcement and safety interventions during high-risk periods, especially among younger drivers who are at fault in accidents.