AI reveals potential in Alzheimer’s drug trial

An AI model uncovered a 46 per cent drop in cognitive decline among early-stage Alzheimer’s patients when reanalysing data from a previously unsuccessful drug trial.

Scientists used artificial intelligence to split trial participants into two groups based on how quickly their condition was progressing. The reassessment revealed the drug slowed symptoms in those with early-stage, slow-progressing mild cognitive impairment – a condition that can develop into Alzheimer’s disease.

The findings suggest AI could help improve patient selection for clinical trials, potentially reducing the cost of developing new medicines. The model was three times more accurate than standard clinical assessments, which typically rely on memory tests, MRI scans and blood tests.

Developed at the University of Cambridge, the AI system predicts whether and how fast someone at the early stages of cognitive decline will develop Alzheimer’s. It is now being supported by Health Innovation East England to help bring the technology into clinical care.

Researchers applied the model to data from a completed trial of a drug that had failed to show benefits in the overall population. The drug cleared beta amyloid – a protein linked to early Alzheimer’s – in all patients. But only those in the slow-progressing group showed symptom improvements, highlighting the need to target treatment at the right stage.

“Promising new drugs fail when given to people too late, when they have no chance of benefiting from them. With our AI model, we can finally identify patients precisely, and match the right patients to the right drugs. This makes trials more precise, so they can progress faster and cost less, turbocharging the search for a desperately-needed precision medicine approach for dementia treatment,” said Professor Zoe Kourtzi, senior author from the University of Cambridge’s department of psychology.

“Our AI model gives us a score to show how quickly each patient will progress towards Alzheimer’s disease. This allowed us to precisely split the patients in the clinical trial into two groups – slow- and fast-progressing – so we could look at the effects of the drug on each group.”

Joanna Dempsey, principal advisor at Health Innovation East England, said: “This AI-enabled approach could have a significant impact on easing NHS pressure and costs in dementia care by enabling more personalised drug development—identifying which patients are most likely to benefit from treatment, resulting in faster access to effective medicines and targeted support for people living with dementia.”

These drugs are not designed to cure Alzheimer’s, but to slow cognitive decline and help patients maintain their condition for longer.

Dementia is the UK’s leading cause of death and one of the top global causes of mortality. It costs US$1.3 trillion each year worldwide, and the number of cases is expected to triple by 2050.

Despite decades of research and over US$43bn invested in drug development, the failure rate for new treatments remains above 95 per cent. One key barrier is the wide variation in symptoms and progression among patients.

While some new dementia drugs have been approved in the US, concerns about side effects and limited cost-effectiveness have so far delayed their adoption in the NHS.

Understanding individual differences in disease progression is critical for developing effective treatments. Alzheimer’s is a complex disease, and while drugs exist, they don’t work for every patient.

“AI can guide us to the patients who will benefit from dementia medicines, by treating them at the stage when the drugs will make a difference, so we can finally start fighting back against these cruel diseases. Making clinical trials faster, cheaper and better, guided by AI, has strong potential to accelerate the discovery of new precise treatments for individual patients, reducing side effects and costs for health care services,” said Kourtzi.

She added: “Like many people, I have watched hopelessly as dementia stole a loved one from me. We’ve got to accelerate the development of dementia medicines. Over £40bn has already been spent over thirty years of research and development – we can’t wait another thirty years.”