Violence Detection from Emergency Room Reports

This paper presents a work to discriminate emergency room reports containing violent injuries from those whose injuries are caused by other factors. Real-word clinical narratives from emergency room reports are analyzed. We report the results obtained by experimenting with multiple architectures and assess their sustainability in settings with limited computational resources and time constraints. Our best models showed to be robust to medical and clinical language, and to differences in reporting practices adopted by different hospitals, exhibiting high accuracy and running times suitable for implementation in real settings: in the violence detection task our system revealed thousands of records not previously annotated as containing injuries of violent origin; in the binary categorization task our best performing models obtained 97.7% F1 score; in the multiclass categorization task a 74.6% average F1 score in the categorization of violence perpetrators was found. Although further efforts are necessary to enable automatic systems to actively contribute to public health monitoring and clinical intervention, the obtained results can help bridge scientific research and everyday clinical practice.