Oxford Led Study Evaluates AI-Tool To Aid Traumatic Brain Injury Forensic Investigations

Study in UK: Research led by scientists at Oxford University has developed an AI tool for aiding traumatic brain injury forensic investigations.

The researchers at Oxford University have led a study that developed an AI-driven tool for use in law enforcement and forensics investigations of traumatic brain injury (TBI) cases.

The researchers have said that the new tool does not intend to replace clinical experts and human forensics. It is to provide an estimate of the probability that the assault was a case of reported injury.

Antoine Jérusalem, Professor of Mechanical Engineering in the Department of Engineering Science at the University of Oxford is the lead researcher of the study.

"Our framework will never be able to identify without doubt the culprit who caused an injury. All it can do is tell you whether the information provided to it is correlated with a certain outcome. Since the quality of the output depends on the quality of the information fed into the model, having detailed witness statements is still crucial," said Antoine.

Dr Michael Jones, Researcher at Cardiff University, and Forensics Consultant, said, "An “Achilles heel” of forensic medicine is the assessment of whether a witnessed or inferred mechanism of injury, often the force, matches the observed injuries. With the application of machine learning, each additional case contributes to the overall understanding of the association between the mechanism of cause, primary injury, pathophysiology and outcome."

AI-Tool For Traumatic Brain Injury Investigation: More Details

The AI framework has been trained on real forensic data and anonymised police reports. Moreover, the study has achieved remarkable prediction accuracy for TBI injuries. It showed 79% accuracy for intracranial haemorrhage and loss of consciousness, and 94% accuracy for skull fractures.

The scientists trained the AI framework on 53 anonymized assault cases and real police reports. Each report included many factors which could affect the injury severity eg- age, body fluid and sex of the victim/offender.

"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," Sonya Baylis, Senior Manager at the National Crime Agency.

Read more:

• University of Sussex Introduces UK's First Climate Justice Undergraduate Degree
• Strathclyde Business School Offers Glasgow 850 International Masters Scholarship