New Oxford University AI tool to improve forensic brain injury investigations

The physics-based AI-driven tool could be used to assist in TBI investigations for forensics and law enforcement. TBI is a significant public health concern, with severe and lasting neurological effects. In forensic investigations, determining whether an impact could have caused a reported injury is crucial for legal proceedings, yet there is currently no standardised, quantifiable approach to do this. The new study demonstrates how machine learning tools informed by mechanistic simulations could provide evidence-based injury predictions. This would help police and forensic teams to accurately predict TBI outcomes based on documented assault scenarios. The study’s AI framework, trained on real, anonymised police reports and forensic data, had a 94 per cent prediction accuracy for skull fractures, 79 per cent accuracy for loss of consciousness, and 79 per cent accuracy for intracranial haemorrhage, which is bleeding within the skull. In each case, a low rate of false positive and false negative results was recorded. Lead researcher Antoine Jérusalem, professor of mechanical engineering in the department of engineering science at the University of Oxford, said: "This research represents a significant step forward in forensic biomechanics. "By leveraging AI and physics-based simulations, we can provide law enforcement with an unprecedented tool to assess TBIs objectively." The framework uses a general computational mechanistic model of the head and neck, designed to simulate how different types of impacts affect various regions. This provides a basic prediction of whether an impact is likely to cause tissue deformation or stress, but it does not predict any risk of injury on its own. This is done by an upper AI layer which incorporates this information with any additional relevant metadata, such as the victim’s age and height, before providing a prediction for a given injury. The researchers trained the overall framework on 53 anonymised real police reports of assault cases. Each report included information about a range of factors which could affect the blow’s severity, such as the person's age, sex, and body build. This resulted in a model capable of integrating mechanical biophysical data with forensic details to predict the likelihood of different injuries occurring. Sonya Baylis, senior manager at the National Crime Agency, said: "Understanding brain injuries using innovative technology to support a police investigation, previously reliant on limited information, will greatly enhance the interpretation required from a medical perspective to support prosecutions." The research team insists the model is not intended to replace the involvement of human forensic and clinical experts in investigating assault cases, but will provide an objective estimate of the probability that a documented assault was the true cause of a reported injury.