logo
Hospitals scan more patients with AI technology

Hospitals scan more patients with AI technology

Yahoo05-07-2025
Staff at NHS hospitals in Hull said AI technology had cut MRI scan times, allowing them to see more patients.
Hull University Teaching Hospitals NHS Trust said the software used algorithms to help reduce background noise, helping to achieve sharper images in a shorter time.
Karen Bunker, head of imaging, said: "This means we can reduce the scanning time on certain sequences, but still get the same imaging quality."
The software has been installed at Hull Royal Infirmary and Castle Hill Hospital and will also be introduced at Scunthorpe General Hospital and Diana, Princess of Wales Hospital in Grimsby.
The Air Recon Deep Learning (ARDL) software was installed on the hospitals' existing MRI machines.
Staff said the software was cutting between 10 and 15 minutes from average scan times.
A routine MRI head scan used to take 30 minutes but now takes 20, the trust said, while a prostate scan now takes 30 minutes instead of 45.
The trust added it can now scan 31 lumber spine patients over a 12 hour period, instead of 21 before.
Ms Bunker said: "People who struggle with claustrophobia or those with learning disabilities, who previously couldn't tolerate a scan, are finding they are able to endure the shorter scan times."
Staff also reported fewer children needed to have a general anaesthetic to get through a scan.
Listen to highlights from Hull and East Yorkshire on BBC Sounds, watch the latest episode of Look North or tell us about a story you think we should be covering here.
AI in healthcare: what are the risks for the NHS?
Hospitals will use AI to speed up patient care
AI 'co-pilot' used to speed up cancer diagnosis
Hull University Teaching Hospitals NHS Trust
Orange background

Try Our AI Features

Explore what Daily8 AI can do for you:

Comments

No comments yet...

Related Articles

Study reveals ChatGPT and other AI systems lag behind humans in one essential skill — and it's entirely unique
Study reveals ChatGPT and other AI systems lag behind humans in one essential skill — and it's entirely unique

Tom's Guide

time3 hours ago

  • Tom's Guide

Study reveals ChatGPT and other AI systems lag behind humans in one essential skill — and it's entirely unique

ChatGPT seems to be outpacing us at every turn. The AI chatbot is a better poet, mathematician, and coder than we are. But don't worry, researchers at the University of Amsterdam have identified a point where AI lags behind humans and it's all to do with a simple concept our brains grapple with on a daily basis. When you see a mountain path, a busy road or meandering river, your brain can instantly determine how to navigate it, whether that be by walking, swimming, cycling or even arriving at the conclusion it's not possible to pass. This decision-making process is possible because of unique brain patterns. Normally, AI is pretty good at replicating human decision-making, but not in this case. "AI models turned out to be less good at this and still have a lot to learn from the efficient human brain," said Iris Groen, a computational neuroscientist who led the study. The team utilised MRI scanners to try to understand what happens in the brain in these navigational situations. Brain scans were taken while participants looked at various photos of both indoor and outdoor environments. Each participant was told to use a button, indicating if the image invited them to walk, cycle, drive, swim, boat, or climb. While they were set this task, their brains were analysed. 'We wanted to know: when you look at a scene, do you mainly see what is there, such as objects or colours, or do you also automatically see what you can do with it,' says Groen. Get instant access to breaking news, the hottest reviews, great deals and helpful tips. The answer, they found, was both. Participants' brain activity showed that they recognised both what was in the image and how to interact with it. 'Even if you do not consciously think about what you can do in an environment, your brain still registers it,' says Groen. The team of scientists wanted to see how well AI algorithms compared to the human brain in this test. They used image recognition models and GPT-4. In the tests, they were worse at predicting possible actions. "When trained specifically for action recognition, they could somewhat approximate human judgments, but the human brain patterns didn't match the models' internal calculations," says Groen. ChatGPT doesn't have to cross rivers or navigate busy streets. However, as AI becomes more and more prevalent, these kinds of problems will arise more. This didn't just occur with standard AI models without training. Even leading AI models didn't give exactly the same answers as humans, despite the task being so normal for us. But why does any of this matter? ChatGPT doesn't have to cross rivers or navigate busy streets. However, as AI becomes more and more prevalent, these kind of problems will arise more. AI chatbots are rolling out live video and audio discussions, and AI is finding its way into other areas like self-driving cars, robotics, and healthcare. As the technology gets more advanced, we are discovering areas where AI struggles to think in a human capacity. In other words, it struggles to interact with a world in the way it has been designed. ChatGPT and its competitors will likely quickly work out how to navigate environments. But in the meantime, feel some pride in the fact that you are smarter than an all-knowing chatbot when it comes to navigating across a rocky hill. As the technology gets more advanced, we are discovering areas where AI struggles to think in a human capacity. In other words, it struggles to interact with a world in the way it has been designed. ChatGPT and its competitors will likely quickly work out how to navigate environments. But in the meantime, feel some pride in the fact that you are smarter than an all-knowing chatbot when it comes to navigating across a rocky hill.

Physician associates ‘should be banned from seeing patients without review'
Physician associates ‘should be banned from seeing patients without review'

Yahoo

time9 hours ago

  • Yahoo

Physician associates ‘should be banned from seeing patients without review'

Physician associates (PAs) should be banned from seeing patients who have not been reviewed by a medic to prevent the risk of 'catastrophic' misdiagnoses, a Government-ordered report has found. The study suggests a major change to the role of PAs after it acknowledged they have been used as substitutes for doctors, despite having significantly less training. More than 3,500 PAs and 100 anaesthesia associates (AAs) are working in the NHS and there have been previous calls for an expansion in their number. But a general lack of support for the roles from the medical profession – plus high-profile deaths of patients who were misdiagnosed by PAs – led Health Secretary Wes Streeting to order a review. Presenting her findings, Professor Gillian Leng, president of the Royal Society of Medicine, said: 'Crucially I'm recommending that PAs should not see undifferentiated or untriaged patients. 'If (patients) are triaged, they (PAs) should be able to see adult patients with minor ailments in line with relevant guidance from the Royal College of GPs.' She said more detail was needed on which patients can be seen by PAs and national clinical protocols should be developed in this area. She added: 'Let's be clear, (the role of PAs) is working well in some places, but there indeed has been some substitution and any substitution is clearly risky and confusing for patients.' Prof Leng also recommended PAs should be renamed 'physician assistants' to position them 'as a supportive, complementary member of the medical team', while AAs should be renamed 'physician assistants in anaesthesia'. Newly qualified PAs should also work in hospitals for two years before they are allowed to work in GP surgeries or mental health trusts. The study said safety concerns in relation to PAs were 'almost always about making a diagnosis and deciding the initial treatment, particularly in primary care or the emergency department, where patients first present with new symptoms.' It added: 'It is here that the risk of missing an unusual disease or condition is highest, and where the more extensive training of doctors across a breadth of specialties is important. 'Making the wrong initial diagnosis and putting patients on an inappropriate pathway can be catastrophic.' Despite the shorter two years of training for PAs, where local NHS services have struggled with filling roles, 'the easy option in some cases was simply to fill gaps in medical rotas with PAs', the report went on. 'This seems to have been done without taking into account the more limited training of the PAs and how the roles would interact, other than with the caveat that they would be supervised by doctors. 'This lack of planning may have been responsible for driving the resentment felt by some resident (doctors) and potentially exposed patients to unnecessary risk.' The study noted concerns in the medical profession about the impact on training and employment of resident doctors when PAs take on tasks. When it comes to the safety of PAs and AAs, Prof Leng said the 'evidence is poor', with 'no compelling evidence' in published research 'that PAs were safe to work as doctor substitutes in primary care'. She also said the evidence was poor when it came to cost effectiveness. The report said that while research suggests patients are satisfied after seeing a PA, some did not know they were not seeing a doctor. Many doctors also told the review they were concerned about the time required to supervise PAs and AAs and the lack of training for supervisors about the role of PAs. A survey conducted for the report found 'relatively few doctors felt it was appropriate for PAs to diagnose illness', with only 29% of those working with PAs in primary care backing this, and 14% in secondary care. The survey also found 'marked differences in which tasks were considered appropriate in primary and secondary care, with PAs significantly more likely than doctors to believe that certain activities were appropriate for them to carry out'. When it came to AAs, there were also questions over whether the role was actually needed as fully qualified anaesthetists already face tough competition to find a job. Prof Leng concluded there were 'no convincing reasons to abolish the roles of AA or PA' but there is also no case 'for continuing with the roles unchanged'. She recommended that both PAs and AAs should have the opportunity for ongoing training and development, with potential to prescribe medicines in the future, and they should also should have the opportunity to become an 'advanced' PA or AA. A named doctor should take overall responsibility for each PA, while clothing, lanyards, badges and staff information should be standardised to 'distinguish physician assistants from doctors'. Six patient deaths linked to contact with PAs have been recorded by coroners in England. One high-profile death involved Emily Chesterton, 30, who died from a pulmonary embolism. She was misdiagnosed by a PA on two occasions and told she had anxiety. Unison head of health, Helga Pile, said: 'By working closely with doctors and other healthcare professionals, these roles can make a real difference to the improvement of services and reduction of waiting lists. 'Clearer identification of physician associates and anaesthesia associates will give patients a greater understanding of who's delivering their care and what they can expect. ' Dr Tom Dolphin, chair of BMA council, said the review 'laid bare the catastrophic failures in NHS leadership that have put patients at serious risk of harm' but said its recommendations 'do not adequately protect patients'. He added: 'Despite correctly recommending that assistants shouldn't be the first person seeing patients coming straight through the doors in GP practices or in A&E, the report then contradicts itself by saying that PAs can act as a first point of contact in primary care for minor and common conditions. 'It is not clear how these two recommendations can coexist, and this must be urgently clarified. Minor complaints are only minor in retrospect and serious conditions can present in subtle or unusual ways. 'No doubt doctors will look back at this report as a moment when historic failures could have been addressed and patients finally protected – but sadly will see this as an inadequate response to what is a patient safety scandal.'

OPINION - A once-a-day ‘life-changing' pill for cystic fibrosis patients ...Tech & Science Daily podcast
OPINION - A once-a-day ‘life-changing' pill for cystic fibrosis patients ...Tech & Science Daily podcast

Yahoo

time14 hours ago

  • Yahoo

OPINION - A once-a-day ‘life-changing' pill for cystic fibrosis patients ...Tech & Science Daily podcast

Listen here on your chosen podcast platform. A once-a-day pill health experts are calling 'life-changing' will be offered to hundreds of people living with cystic fibrosis. The drug, called Alyftrek, is a type of modular therapy which works to tackle the underlying cause of the rare condition. NHS England has announced that the treatment will be available for children and adults with rare forms of cystic fibrosis. A new £650 million Electric Car Grant announced by the government is set to reduce the cost of some new electric cars. We speak with Octopus Energy CEO Greg Jackson about the technology behind their new EV bundle, which includes free charging. Plus, Nvidia are getting the ball rolling again for sales of their famous chips in China. Also in this episode: -Blue Sharks have a unique structure on their skin which allows them to change colour -Elon Musk's Grok is making AI companions, including a goth anime girl - are they romantic interests or just skins? -Hamleys names Lego, Barbie and Rubik's Cube the top three toys of all time

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into a world of global content with local flavor? Download Daily8 app today from your preferred app store and start exploring.
app-storeplay-store