Radiology AI may improve workflows and patient care, but the technology also brings challenges for radiology departments, research suggests.

A focus issue from the Journal of the American College of Radiology brings together invited research and reviews exploring how AI is being used across different practice types.

Barriers include insufficient infrastructure, strict institutional regulations and a lack of insurance reimbursement, all of which can hamper the integration of AI into routine clinical workflows.

Radiology, the branch of medicine that uses imaging such as X-rays and scans to diagnose and treat disease, is widely seen as one of the fields most likely to be reshaped by AI.

The research includes contributions arguing that workflow improvement is not simply a secondary benefit of AI, but a main determinant of whether a tool succeeds.

Gelareh Sadigh, associate editor for health services research at the Journal of the American College of Radiology, said: “When thoughtfully implemented, AI can complement human expertise and improve efficiency and patient care.

“Successful workflow optimisation requires the integration of AI technology into routine workflows.

“This can be hampered by insufficient infrastructure, strict institutional regulations, and lack of insurance reimbursement.

“Poor integration of AI may degrade workflows, satisfaction, and safety and perpetuate bias in healthcare.”

According to Dr Sadigh, the articles in the focus issue reflect a broader shift in radiology: workflow is not a secondary benefit of AI, but a key factor in whether a tool is successful.

If AI is going to meaningfully help radiology, it must make care delivery better and not more complicated.

Ruth C. Carlos, editor-in-chief of the Journal of the American College of Radiology, said: “This focus issue provides meaningful signposts for AI effectiveness as we navigate a rapidly shifting landscape.”

An AI tool could help identify Alzheimer’s disease around two years earlier by analysing signals already recorded in patients’ clinical records.

DementAI, a prototype developed by consultancy Katalyze Data, analyses existing medical record data to flag patients who may show early signs of the condition but have not yet been referred for specialist assessment.

Built as an end-to-end working prototype, the system connects stages clinicians often manage separately, from analysing medical records to applying models within decision pathways.

It is designed to work using information healthcare providers already hold, turning fragmented data into actionable insight without adding new screening burdens.

The system combines structured medical records, brain activity data and unstructured clinical information, using synthetic data where appropriate to support development.

By blending these signals, it aims to detect subtle patterns of decline that may be difficult to identify during short consultations.

Tamás Bosznay, principal consultant at Katalyze Data, said: “We are in a race against time when it comes to dementia.

“Early identification can make a meaningful difference to how patients and families experience the condition.

“But without better ways of finding people sooner, those opportunities can be lost.

“We didn’t build DementAI just to make predictions; we built it to buy patients time.

“By surfacing the signals already hiding in plain sight within clinical records, the system is designed to help ensure that when care teams are ready to act, the right patients are identified earlier and more consistently.”

DementAI was developed as part of the SAS Hackathon 2025, where it won the healthcare and life sciences category.

The team is now seeking engagement with NHS trusts to explore pilot deployments that could validate the model’s impact and support efforts to reduce delays in diagnosis.

Dr Iain Brown, global head of AI and data science at SAS, said: “Synthetic data, agentic AI concepts and governance are not ‘nice-to-haves’ in sensitive settings like healthcare.

“They are what make innovation usable at scale.

“DementAI shows how artificial intelligence can be applied in a way that is both ambitious and responsible.

AI smart lights in care homes were linked to up to 75 per cent fewer hospital visits after falls, according to an NHS evaluation.

The study examined 87 rooms across seven care homes providing residential, nursing, dementia and assisted living care.

Researchers compared six months of baseline data with six months after installing Nobi Smart Lights, AI-enabled ceiling-mounted devices designed to detect falls and alert staff within seconds.

The lights also turn on automatically when residents get out of bed, helping reduce the risk of night-time falls. Some homes reported zero fall-related hospital admissions during the evaluation period, while ambulance call-outs fell by up to 65 per cent.

Staff reported greater confidence when responding to unwitnessed incidents and said they spent less time reconstructing events or completing documentation.

Better visibility also helped staff distinguish genuine falls from controlled descents, where someone lowers themselves to the floor intentionally or slowly, allowing more incidents to be managed safely inside the care home.

The evaluation was carried out by the Suffolk and North East Essex Integrated Care Board.

“The Nobi light gives me peace of mind because Mum does fall a lot,” said the daughter of a resident at a participating Suffolk care home.

“I felt guilty about her going into a home, but now I know staff are alerted instantly and can be there straight away.”

The work formed part of the Integrated Care Board’s Digitising Social Care Programme, which supports care providers to adopt digital tools.

Implementation was delivered in partnership with Porters Care, one of Nobi’s UK partners, with support from Suffolk County Council and participating care providers.

Using NHS reference costs, the evaluation estimated £89,000 in avoided emergency care costs over six months, equivalent to a projected return on investment of around 196 per cent over three years.

Roeland Pilgrims, chief executive and co-founder of Nobi, said: “This independent NHS evaluation shows how intelligent care technology can deliver measurable improvements for residents, care teams and the wider health system.

“By giving staff timely, reliable insight, we can help reduce avoidable hospital admissions while improving safety, dignity and peace of mind.”

David Knowles, managing director of Porters Care, added: “These findings show the real-world impact of smart technology in care homes.

“By improving how falls are detected and understood, Nobi helps teams make clearer decisions and avoid unnecessary hospital admissions, while keeping residents safe.”

Further independent NHS-led evaluations are underway in other regions of the UK.