Scientists have used AI to re-analyse a clinical trial for an Alzheimer’s medicine, and identified a group of patients who responded to treatment. The work demonstrates that AI can inform the design of future clinical trials to make them more effective and efficient, accelerating the search for new medicines.
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.
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.
