(Press-News.org) A team of researchers from the University of Oxford, in collaboration with Thames Valley Police, the National Crime Agency, the John Radcliffe Hospital, Lurtis Ltd. and Cardiff University, has developed an advanced physics-based AI-driven tool to aid the forensic investigation of traumatic brain injuries (TBI).
The study, published today (26 Feb) in Communications Engineering, introduces a mechanics-informed machine learning framework to help police and forensic teams accurately predict TBI outcomes based on documented assault scenarios.
TBI is a critical public health issue, with severe and long-term neurological consequences. 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, to improve the accuracy and consistency of TBI investigations.
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 study’s AI framework, trained on real, anonymised police reports and forensic data, achieved remarkable prediction accuracy for TBI-related injuries:
94% accuracy for skull fractures
79% accuracy for loss of consciousness
79% accuracy for intracranial haemorrhage (bleeding within the skull)
In each case, the model showed high specificity and high sensitivity (a low rate of false positive and false negative results).
The framework uses a general computational mechanistic model of the head and neck, designed to simulate how different types of impacts—such as punches, slaps, or strikes against a flat surface—affect various regions. This provides a basic prediction of whether an impact is likely to cause tissue deformation or stress. However, it does not predict on its own any risk of injury. 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 (e.g., age, sex, body build of the victim/offender). This resulted in a model capable of integrating mechanical biophysical data with forensic details to predict the likelihood of different injuries occurring.
When the researchers assessed which factors had the most influence on the predictive value for each type of injury, the results were remarkably consistent with medical findings. For instance, when predicting the likelihood of skull fracture, the most important factor was the highest amount of stress experienced by the scalp and skull during an impact. Similarly, the strongest predictor of loss of consciousness was the stress metrics for the brainstem.
The research team insists that the model is not intended to replace the involvement of human forensic and clinical experts in investigating assault cases. Rather, the intention is to provide an objective estimate of the probability that a documented assault was the true cause of a reported injury. The model could also be used as a tool to identify high-risk situations, improve risk assessments, and develop preventive strategies to reduce the occurrence and severity of head injuries.
Professor Jérusalem added: ‘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.’
Ms Sonya Baylis, Senior Manager at the National Crime Agency who supported this research project, 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.’
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.’
The study was conducted by an interdisciplinary team of engineers, forensic specialists, and medical professionals from the University of Oxford, Thames Valley Police, the National Crime Agency, Cardiff University, Lurtis Ltd., the John Radcliffe Hospital and other partner institutions.
Notes to editors:
A copy of the research paper is available under embargo and the research team is available for interview requests.
Contact: Caroline Wood, Communications Manager (Research and Innovation), University of Oxford
E: caroline.wood@admin.ox.ac.uk
T: 01865 280534
The study ‘A mechanics-informed machine learning framework for traumatic brain injury prediction in police and forensic investigations’ will be published in Communications Engineering at 10 am GMT Wednesday 26 February 2025 at https://www.nature.com/articles/s44172-025-00352-2
About the University of Oxford
Oxford University has been placed number 1 in the Times Higher Education World University Rankings for the ninth year running, and number 3 in the QS World Rankings 2024. At the heart of this success are the twin-pillars of our ground-breaking research and innovation and our distinctive educational offer.
Oxford is world-famous for research and teaching excellence and home to some of the most talented people from across the globe. Our work helps the lives of millions, solving real-world problems through a huge network of partnerships and collaborations. The breadth and interdisciplinary nature of our research alongside our personalised approach to teaching sparks imaginative and inventive insights and solutions.
Through its research commercialisation arm, Oxford University Innovation, Oxford is the highest university patent filer in the UK and is ranked first in the UK for university spinouts, having created more than 300 new companies since 1988. Over a third of these companies have been created in the past five years. The university is a catalyst for prosperity in Oxfordshire and the United Kingdom, contributing £15.7 billion to the UK economy in 2018/19, and supports more than 28,000 full time jobs.
END
New AI-powered tool could enhance traumatic brain injury investigations in forensics and law enforcement
2025-02-26
ELSE PRESS RELEASES FROM THIS DATE:
A protein from tiny tardigrades may help cancer patients tolerate radiation therapy
2025-02-26
CAMBRIDGE, MA -- About 60 percent of all cancer patients in the United States receive radiation therapy as part of their treatment. However, this radiation can have severe side effects that often end up being too difficult for patients to tolerate.
Drawing inspiration from a tiny organism that can withstand huge amounts of radiation, researchers at MIT, Brigham and Women’s Hospital, and the University of Iowa have developed a new strategy that may protect patients from this kind of damage. Their approach makes use of a protein from tardigrades, often also called “water bears,” which are usually less than a millimeter in ...
Double network hydrogel polymers with rapid self-strengthening abilities
2025-02-26
New double network hydrogel technology features automated self-strengthening that rapidly activates upon deformation of its polymer network.
Hydrogels are soft materials consisting of polymer networks and water. They are permeable to substances smaller than their network mesh size and have applications in biomaterials, contact lenses, soft robots, and more. At the molecular level, the cleavage of chemical bonds causes a material to become mechanically weaker and can lead to its destruction. Mechanochemically ...
Schizophrenia is reflected in the brain structure
2025-02-26
The symptoms of schizophrenia vary greatly from person to person. A new study shows how these differences manifest themselves in the structure of the brain.
Schizophrenia is a complex mental health condition that affects perception, thought and emotions. This complexity is reflected in the individual manifestations of the disease: for some patients, perceptual disturbances are the main problem, while for others, cognitive impairments are more prevalent. “In this sense, there is not one schizophrenia, but many, each with different neurobiological profiles,” says Wolfgang Omlor, first author of the study and senior physician at the University Hospital of Psychiatry ...
Researchers warn continuous glucose monitors can overestimate blood sugar levels
2025-02-26
Continuous Glucose Monitors (CGMs) are growing in popularity but new peer-reviewed research, published in The American Journal of Clinical Nutrition, from the University of Bath, suggests they may not be as accurate as many believe. Originally designed to help people living with diabetes manage their blood sugar, these devices are now being used by the health-conscious to track how different foods affect their glucose levels.
The study, from the University’s Centre for Nutrition, Exercise ...
Colorectal cancer: Lipids can predict treatment efficacy
2025-02-26
Colorectal cancer, the second most common cause of cancer-related death, affects almost 2 million people worldwide every year. It is mainly treated with chemotherapy, but its effectiveness decreases over time due to the progressive resistance of tumor cells. A team from the University of Geneva (UNIGE) has identified specific alterations in certain lipids in cancer cells resistant to chemotherapy. These lipid signatures could serve as prognostic markers for understanding resistance to treatment and pave the way for personalized, targeted strategies ...
Physical activity boosts mental health in women with chronic pelvic pain disorders
2025-02-26
New York, NY [February 26, 2025]— A new Mount Sinai study provides compelling evidence that exercise can significantly help the mental well-being of millions of women living with chronic pelvic pain disorders (CPPDs), such as endometriosis and uterine fibroids.
The researchers at the Icahn School of Medicine at Mount Sinai found that activities like brisk walking or aerobic exercise can lead to measurable improvements in mental well-being, regardless of pain levels or history of anxiety or depressive disorders. Their findings were reported in the February 26 online issue of the Journal of Pain Research.
CPPDs affect millions of women worldwide, leading to increased health care ...
New method searches through 10 sextillion drug molecules
2025-02-26
A recent study shows that computer algorithms can be used to find molecules that can be developed into anti-inflammatory drugs. In the article, the researchers also describe how the same strategy can be used to search through 10 sextillion alternatives to identify the best drug candidate.
One of the biggest challenges in drug development is finding the right candidates among the vast number of possible molecules. A new study published in Nature Communications shows that it is possible to identify drug molecules by modelling them using computer algorithms.
“We use the computer models to search through databases containing billions of molecules. This method will be able ...
Breakthrough in the development of a new low-cost computer
2025-02-26
A low-energy challenger to the quantum computer that also works at room temperature may be the result of research at the University of Gothenburg. The researchers have shown that information can be transmitted using magnetic wave motion in complex networks.
Spintronics explores magnetic phenomena in nano-thin layers of magnetic materials that are exposed to magnetic fields, electric currents and voltages. These external stimuli can also create spin waves, ripples in a material's magnetisation that travel with a specific phase and energy.
The researchers ...
New computer model can predict the length of a household's displacement in any U.S. community after a disaster
2025-02-26
HERNDON, Va., February 25, 2025 -- One of the human impacts of natural hazards is household displacement. Destructive floods, wildfires, earthquakes and hurricanes often force people to leave their homes -- some briefly, others for months or indefinitely.
Most disaster risk assessments, used by insurance companies, government agencies, development banks, and academic researchers to predict the potential future impacts of natural hazards, fail to account for hardships incurred by household displacement. Instead, they focus on direct ...
At your service: How older adults embrace demand-responsive transportation
2025-02-26
In residential areas, where a growing number of older people live, the first- and last-mile mobility between their homes and bus stops has become a social problem. Older adults are encouraged to relinquish their licenses and rely on public transportation. Demand-responsive transport (DRT) has the potential to address this social problem. DRT is a mode of transportation that dispatches on demand to pick up and drop off passengers according to their needs. However, older adults’ lesser acceptance of digital solutions poses a challenge to this new system.
Dr. Haruka Kato, a junior associate professor at Osaka Metropolitan ...