Research concerning the impact of earthquake victims’ individual behavior and its association with earthquake-related injuries is lacking. This study examined this relationship along with effectiveness of earthquake rescue measures. The six most severely destroyed townships during the Lushan earthquake were examined; 28 villages and three earthquake victims’ settlement camp areas were selected as research areas. Inclusion criteria comprised living in Lushan county for a longtime, living in Lushan county during the 2013 Lushan earthquake, and having one’s home destroyed. Earthquake victims with an intellectual disability or communication problems were excluded. The earthquake victims (N (number) = 5165, male = 2396) completed a questionnaire (response rate: 94.7%). Among them, 209 were injured (5.61%). Teachers (p < 0.0001, OR (odds ratios) = 3.33) and medical staff (p = 0.001, OR = 4.35) were more vulnerable to the earthquake than were farmers. Individual behavior was directly related to injuries, such as the first reaction after earthquake and fear. There is an obvious connection between earthquake-related injury and individual behavior characteristics. It is strongly suggested that victims receive mental health support from medical practitioners and the government to minimize negative effects. The initial reaction after an earthquake also played a vital role in victims’ trauma; therefore, earthquake-related experience and education may prevent injuries. Self-aid and mutual help played key roles in emergency, medical rescue efforts.

The demand for large-scale analysis and research of data on trauma from modern warfare is increasing day by day, but the amount of existing data is not sufficient to meet such demand. In this study, an integrated modeling approach incorporating a war trauma severity scoring algorithm (WTSS) and deep neural networks (DNN) is proposed. First, the proposed WTSS, which uses multiple non-linear regression based on the characteristics of war trauma data and the medical evaluation by an expert panel, performed a standardized assessment of an injury and predicts its trauma consequences. Second, to generate virtual injury, based on the probability of occurrence, the injured parts, injury types, and complications were randomly sampled and combined, and then WTSS was used to assess the consequences of the virtual injury. Third, to evaluate the accuracy of the predicted injury consequences, we built a DNN classifier and then trained it with the generated data and tested it with real data. Finally, we used the Delphi method to filter out unreasonable injuries and improve data rationality. The experimental results verified that the proposed approach surpassed the traditional artificial generation methods, achieved a prediction accuracy of 84.43%, and realized large-scale and credible war trauma data augmentation.