The increasing frequency of transportation accidents, both on the road and in aviation, highlights the urgent need for improved safety measures. In the UK, 1.35 million annual road traffic deaths and millions of injuries emphasise the necessity for enhanced road safety, especially for children and youths aged 5–29 years. With registered cars expected to reach 45 million by 2045, digital highways offer a crucial opportunity to enhance safety. This study uses Bayesian networks (BNs) to analyse risk factors for road traffic accidents, addressing a research gap. BNs are valuable for determining causal relationships and managing uncertainties through joint probability distributions. Our methodology involves thorough data preprocessing and feature selection for reliable results. The BN model uses probability and graph theory to represent variable interdependencies and calculates conditional probabilities with Bayes’ theorem. Findings show a strong link between vehicle speed and accident severity, with a 52.56% increase in fatality risk for those aged 66–75 years. These insights demonstrate the potential of BNs to improve road safety and reduce accident-related casualties. While we used road transport data as an example, this BN-based methodology is also applicable to aviation management, assessing safety risks and developing effective prevention measures within civil aviation airports.