Getty ImagesThis is the sixth feature in a six-part series looking at how AI is changing medical research and treatment.
When 58-year-old Will Studholme ended up in accident and emergency at an NHS hospital in Oxford in 2023 with gastrointestinal symptoms, he wasn’t expecting a diagnosis of osteoporosis.
The disease, strongly associated with age, causes bones to become weak and brittle, increasing the risk of fractures.
It turned out that Mr. Studholme had a severe case of food poisoning, but early in the investigation of his illness, he obtained a CT scan of his abdomen.
This scan was later carried out using artificial intelligence (AI) technology which identified a collapsed vertebra in Mr Studholme’s spine, a common early indicator of osteoporosis.
Further testing followed, and Mr. Studholme came up with not only his diagnosis, but a simple treatment: an annual infusion of an osteoporosis drug that is expected to improve his bone density.
“I feel very lucky,” says Mr. Studholme, “I don’t think this would have been achieved without AI technology.”
Will StudholmeIt’s not unheard of for a radiologist to notice something random in a patient’s image—an undetected tumor, a concern with a particular tissue or organ—outside of what they originally checked.
But the application of AI in the background to systematically comb through scans and automatically identify early signs of common preventable chronic diseases that may be developing — regardless of why the scan was originally ordered — is new.
The clinical use of AI for opportunistic screening, or opportunistic imaging, as it’s called, is “just getting started,” notes Perry Pickhardt, a professor of radiology and medical physics at the University of Wisconsin-Madison, who is among those developing the algorithms.
It is considered opportunistic because it takes advantage of images that have already been taken for another clinical purpose – be it suspected cancer, chest infection, appendix or abdominal pain.
It has the potential to catch previously undiagnosed diseases in their early stages, before the onset of symptoms, when they are easier to treat or prevent progression. “We can avoid a lot of the lack of prevention that we missed before,” says Prof Pickhardt.
Regular physical or blood tests often fail to detect these diseases, he adds.
Getty ImagesThere’s a lot of data in CT scans related to body tissues and organs that we don’t really use, notes Miriam Bredella, a radiologist at NYU Langone who is also developing algorithms in this area.
And while his analysis could theoretically be done without artificial intelligence from radiologists taking measurements – it would take time.
There are also benefits of technology in terms of reducing bias, she notes.
A disease like osteoporosis, for example, is thought to mostly affect thin, older white women—so doctors don’t always think to look outside that population.
Opportunistic images, on the other hand, do not discriminate in this way.
The case of Mr. Studholme is a good example. Being relatively new to osteoporosis, male and with no history of broken bones, it is unlikely that he would have been diagnosed without AI.
In addition to osteoporosis, AI is being trained to help opportunistically identify heart disease, fatty liver disease, age-related muscle wasting and diabetes.
While the main focus is on CT scans, for example of the abdomen or chest, work is being done to opportunistically gather information from other types of imaging as well, including chest x-rays and mammograms.
The algorithms have been trained on thousands of previously labeled scans, and it is important that the training data includes scans from a wide range of ethnic groups if the technology is to be used on a diverse range of people, experts point out.
And there’s supposed to be some level of human review—if the AI finds something suspicious, it’ll be sent to radiologists to confirm before it’s then reported to doctors.
The artificial intelligence technology used to examine Mr. Studholme belongs to the Israeli company Nanox.AI, which is one of only a handful of companies working on AI for opportunistic screening—many more are focused on using AI to aid in accurate and rapid diagnoses of specific conditions for which the scans are actually performed.
Nanox.AI offers three opportunistic screening products aimed at helping identify osteoporosis, heart disease and fatty liver disease from routine CT scans.
Oxford NHS Hospitals began testing Nanox.AI’s osteoporosis-focused product in 2018 before officially launching it in 2020.
The results from Oxford hospitals show an increase of up to six times above the NHS average in the number of patients being identified with vertebral fractures – patients who can then be screened for osteoporosis and start treatment to combat the disease, says Kassim Javaid, a professor. of osteoporosis and rare bone diseases at the University of Oxford, who led the introduction of the algorithm.
Further trials of the algorithm are also underway at hospitals in Cambridge, Cardiff, Nottingham and Southampton. “We want to build the evidence to use it across the NHS,” says Prof Javaid.
However, while the technology may benefit individuals, there are wider implications to consider, says Sebastien Ourselin, a professor of healthcare engineering at Kings College London, who directs the AI Center for Value-Based Healthcare .
A major problem that must be balanced, he notes, is the additional number of patients that the use of the technology can create. “This is increasing the demand on the health system, not reducing it,” he says.
First, people flagged by opportunistic screening as potentially having a disease will need further confirmatory testing, which requires resources. And, if the AI is inaccurate or too sensitive, it can result in a lot of unnecessary testing.
Then services need to be in place for those additional people who end up being diagnosed.
The extra burden is a challenge that comes with technology Prof Javaid admits – but there are solutions.
Patients confirmed to have fractures in Oxford are referred for follow-up to a fracture prevention service run mainly by nurses, so as not to overburden doctors. “Artificial intelligence forces you to change your path,” he says.
And in the long run, Prof Javaid believes, if more people with osteoporosis are identified in the early stages and get the preventative treatment they need, it will save the NHS money. “Fracture is one of the main reasons people end up in hospital,” he says.
Mr Studholme has seen first-hand the ravages of osteoporosis: it led to his mother breaking both of her hips. It used to be considered simply the condition of an elderly person with nothing that could be done, he says. “I feel quite privileged to be able to do something before my bones turn to chalk,” he says.
