Investigation of Severe Injury Probability Prediction Models by Body Parts Through Decision Tree-Based Machine Learning Approach

Abstract

The quick and accurate prediction of occupant injuries in motor vehicle collisions helps emergency services respond more effectively and reduce casualties. Existing studies have mainly concentrated on predicting overall injury severity rather than examining injuries to specific body parts, which limits the precision of injury assessment and targeted emergency response. In this study, we developed a random forest-based model to predict injury severity in different body parts, including the head, face, neck, chest, abdomen, spine, and limbs. This enables emergency services to deliver precise and targeted responses after collisions. Furthermore, it facilitates a correlation analysis between various collision-contributing factors and body part-specific injuries.