AI can Accelerate Search for More Effective Alzheimer's Medicines by Streamlining Clinical Trials

Scientists have used an AI model to reassess the results of a completed clinical trial for an Alzheimer’s disease drug. They found the drug slowed cognitive decline by 46% in a group of patients with early stage, slow-progressing mild cognitive impairment - a condition that can progress to Alzheimer’s.

Using AI allowed the team to split trial participants into two groups: either slowly or rapidly progressing towards Alzheimer’s disease. They could then look at the effects of the drug on each group.

More precise selection of trial participants in this way could help select patients most likely to benefit from treatment, with the potential to reduce the cost of developing new medicines by streamlining clinical trials.

The AI model developed by researchers at the University of Cambridge predicts whether, and how quickly, people at early stages of cognitive decline will progress to full-blown Alzheimer’s. It gives predictions for patients that are three times more accurate than standard clinical assessments based on memory tests, MRI scans and blood tests.

Using this patient stratification model, data from a completed clinical trial - which did not demonstrate efficacy in the total population studied - was re-analysed. The researchers found that the drug cleared a protein called beta amyloid in both patient groups as intended - but only the early stage, slow-progressing patients showed changes in symptoms. Beta amyloid is one of the first disease markers to appear in the brain in Alzheimer’s disease.

The new findings have significant implications: using AI to separate patients into different groups, such as slow versus rapidly progressing towards Alzheimer’s disease, allows scientists to better identify those who could benefit from a treatment approach - potentially accelerating the discovery of much-needed new Alzheimer’s drugs.

The results are published in the journal Nature Communications.

Professor Zoe Kourtzi in the University of Cambridge’s Department of Psychology, senior author of the report, said: "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-need precision medicine approach for dementia treatment."

She added: "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 on the clinical trial into two groups - slow, and fast progressing, so we could look at the effects of the drug on each group."

Health Innovation East England, the innovation arm of the NHS in the East of England, is now supporting Kourtzi to translate this AI-enabled approach into clinical care for the benefit of future patients.

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."

Drugs like this are not intended as cures for Alzheimer’s disease. The aim is to reduce cognitive decline so that patients don't get worse.

Dementia is the UK's leading cause of death, and a major cause of mortality globally. It costs $1.3 tr per year, and the number of cases are expected to treble by 2050. There is no cure, and patients and families face high uncertainty.

Despite decades of research and development, clinical trials of treatments for dementia have been largely unsuccessful. The failure rate for new treatments is unreasonably high at over 95%, despite $43 bn having been spent on research and development. Progress has been hampered by the wide variation in symptoms, disease progression and responses to treatment among patients.

Although new dementia drugs have recently been approved for use in the US, their risk of side effects and insufficient cost effectiveness have prevented healthcare adoption in the NHS.

Understanding and accounting for the natural differences among individuals with a disease is crucial, so that treatments can be tailored to be most effective for each patient. Alzheimer’s disease is complex, and although some drugs are available to treat it they don’t work for everybody.

"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 discovery of new precise treatments for individual patients, reducing side effects and costs for healthcare 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 £40 billion has already been spent over thirty years of research and development - we can’t wait another thirty years."

Vaghari D, Mohankumar G, Tan K, Lowe A, Shering C, Tino P, Kourtzi Z.
AI-guided patient stratification improves outcomes and efficiency in the AMARANTH Alzheimer's Disease clinical trial.
Nat Commun. 2025 Jul 17;16(1):6244. doi: 10.1038/s41467-025-61355-3

Most Popular Now

AI also Assesses Dutch Mammograms Better…

AI is detecting tumors more often and earlier in the Dutch breast cancer screening program. Those tumors can then be treated at an earlier stage. This has been demonstrated by...

RSNA AI Challenge Models can Independent…

Algorithms submitted for an AI Challenge hosted by the Radiological Society of North America (RSNA) have shown excellent performance for detecting breast cancers on mammography images, increasing screening sensitivity while...

AI could Help Emergency Rooms Predict Ad…

Artificial intelligence (AI) can help emergency department (ED) teams better anticipate which patients will need hospital admission, hours earlier than is currently possible, according to a multi-hospital study by the...

Head-to-Head Against AI, Pharmacy Studen…

Students pursuing a Doctor of Pharmacy degree routinely take - and pass - rigorous exams to prove competency in several areas. Can ChatGPT accurately answer the same questions? A new...

NHS Active 10 Walking Tracker Users are …

Users of the NHS Active 10 app, designed to encourage people to become more active, immediately increased their amount of brisk and non-brisk walking upon using the app, according to...

Unlocking the 10 Year Health Plan

The government's plan for the NHS is a huge document. Jane Stephenson, chief executive of SPARK TSL, argues the key to unlocking its digital ambitions is to consider what it...

AI can Find Cancer Pathologists Miss

Men assessed as healthy after a pathologist analyses their tissue sample may still have an early form of prostate cancer. Using AI, researchers at Uppsala University have been able to...

How AI could Speed the Development of RN…

Using artificial intelligence (AI), MIT researchers have come up with a new way to design nanoparticles that can more efficiently deliver RNA vaccines and other types of RNA therapies. After training...

AI, Full Automation could Expand Artific…

Automated insulin delivery (AID) systems such as the UVA Health-developed artificial pancreas could help more type 1 diabetes patients if the devices become fully automated, according to a new review...

MIT Researchers Use Generative AI to Des…

With help from artificial intelligence, MIT researchers have designed novel antibiotics that can combat two hard-to-treat infections: drug-resistant Neisseria gonorrhoeae and multi-drug-resistant Staphylococcus aureus (MRSA). Using generative AI algorithms, the research...

AI Hybrid Strategy Improves Mammogram In…

A hybrid reading strategy for screening mammography, developed by Dutch researchers and deployed retrospectively to more than 40,000 exams, reduced radiologist workload by 38% without changing recall or cancer detection...

Penn Developed AI Tools and Datasets Hel…

Doctors treating kidney disease have long depended on trial-and-error to find the best therapies for individual patients. Now, new artificial intelligence (AI) tools developed by researchers in the Perelman School...