A pilot study for investigating the feasibility of supervised machine learning approaches for the classification of pedestrians struck by vehicles

This research focuses on the application of Artificial Intelligence (AI) methodologies to the problem ofclassifying vehicles involved in lethal pedestrian collisions. Specifically, the vehicle type is predicted on thebasis of traumatic injury suffered by casualties, exploiting machine learning algorithms. In the present study,AI-assisted diagnosis was shown to have correct prediction about 70% of the time. In pedestrians struck bytrucks, more severe injuries were appreciated in the facial skeleton, lungs, major airways, liver, and spleen aswell as in the sternum/clavicle/rib complex, whereas the lower extremities were more affected by fracturesin pedestrians struck by cars. Although the distinction of the striking vehicle should develop beyond autopsyevidence alone, the presented approach which is novel in the realm of forensic science, is shown to be effectivein building automated decision support systems. Outcomes from this system can provide valuable informationafter the execution of autoptic examinations supporting the forensic investigation. Preliminary results fromthe application of machine learning algorithms with real-world datasets seem to highlight the efficacy of theproposed approach, which could be used for further studies concerning this topic.