Automobile safety innovations and road crash trends: A data-driven analytical approach

In this study, empirical road crashes data (2011–2020) of total accidents, persons killed, and injured from Ministry of Road Transport and Highways (MORTH), India with risk factors is analyzed and evaluated with Pareto charts, Pearson correlation matrix, and ANOVA General Linear model (GLM) using Minitab 18.0 software. Our results show that road environment (weather conditions, traffic control type, junction type, and road type) and human behavior related factors are the dominant causes for accident occurrences and its severity. Two wheeler, vehicle age of <5 and 5–10 years are contributed for more number of accidents. Also, 25–35 years age group of male and female causes more fatal accidents than other age group. Finally, 77 unique factors are filtered from 55 recent studies, and 146 risk factors are observed from MORTH database. In total, 223 factors are identified and grouped into 23 categories to enhance road safety and accident database management system for reducing the crash injury severity. These findings contribute to the advancement of automotive safety technologies, intelligent transportation systems, and data-driven accident prevention strategies. This research also underscores the urgent need for integrating AI-powered safety features, improving vehicle structural resilience, and optimizing in-vehicle monitoring systems to mitigate road crash severity and enhance automobile safety innovations.