Artificial intelligence (AI) could be used to detect brain injury and recommend personalised treatments faster than traditional methods, it has been suggested.
The research, carried out by Imperial College London and Cambridge University, is among the first to use autonomous technology to identify and suggest potential treatments for serious brain trauma.
Published in peer-reviewed journal The Lancet Digital Health, the researchers say the results of the trial could be used in “large-scale” research studies to develop quick, personalised treatments for head injuries, particularly where clinical experts are in high demand.
The scientists say the new tool was fed images of more than 600 CT scans before validating it on an existing large dataset of CT scans. The results show that the AI was able to classify individual parts of each image and tell whether it was normal or not.
According to the latest statistics, head injuries affect up to 60 million people worldwide each year, with 348,000 hospital admissions in the UK alone.
If left untreated, brain injury and concussion can cause serious physiological and mental health problems, and even death.
However, innovative technology, such as that used in the university study, may be able to process patients and point them in the direction of personalised treatment faster than ever, significantly increasing the odds of a full recovery.
Commenting on the technology, study co-author Miguel Monteiro said: “Head injuries are a major health problem worldwide. Our artificial network and algorithm showed us that we can somewhat automate the diagnosis of different injury types to potentially help inform treatment in the future.
“We’re currently only using the AI for research, but with proper validation, it could also be used in clinical scenarios like in resource-limited areas where there are few radiologists.”