A mechanics-informed machine learning framework for traumatic brain injury prediction in police and forensic investigations

Wei, Yuyang; Oldroyd, Jeremy; Haste, Phoebe; Jayamohan, Jayaratnam; Jones, Michael; Casey, Nicholas; Peña, Jose-Maria; Baylis, Sonya; Gilmour, Stan; Jérusalem, Antoine

Abstract

Police forensic investigations are not immune to our society’s ubiquitous search for better predictive ability. In the particular and very topical case of Traumatic Brain Injury (TBI), police forensic investigations aim at evaluating whether a given impact or assault scenario led to the clinically observed TBI. This question is traditionally answered by means of forensic biomechanics and neurosurgical expertise which cannot provide a fully objective probabilistic measure. To this end, we propose here a numerical framework-based solution coupling biomechanical simulations of a variety of injurious impacts to machine learning training of police reports provided by the UK’s Thames Valley Police and the National Crime Agency’s National Injury Database. In this approach, the biomechanical predictions of mechanical metrics such as strain and stress distributions are interpreted by the machine learning model by additionally considering assault specific metadata to predict brain injury outcomes. The framework, only taking as input information typically available in police reports, reaches prediction accuracies exceeding 94% for skull fracture, 79% for loss of consciousness and intracranial haemorrhage, and is able to identify the best predictive features for each targeted injury. Overall, the proposed framework offers new avenues for the prediction, directly from police reports, of any TBI related symptom as required by forensic law enforcement investigations.

Citation

Wei, Y., Oldroyd, J., Haste, P., Jayamohan, J., Jones, M., Casey, N., Peña, J.-M., Baylis, S., Gilmour, S., & Jérusalem, A. (in press). A mechanics-informed machine learning framework for traumatic brain injury prediction in police and forensic investigations. Communications Engineering, 4(1), 1-12. https://doi.org/10.1038/s44172-025-00352-2

• Journal Article Type: Article
• Acceptance Date: Jan 21, 2025
• Online Publication Date: Feb 26, 2025
• Deposit Date: Mar 6, 2025
• Publicly Available Date: Mar 6, 2025
• Journal: Communications Engineering
• Electronic ISSN: 2731-3395
• Publisher: Nature Research
• Peer Reviewed: Peer Reviewed
• Volume: 4
• Issue: 1
• Article Number: 29
• Pages: 1-12
• DOI: https://doi.org/10.1038/s44172-025-00352-2
• Public URL: https://keele-repository.worktribe.com/output/1080530