Scientists have leveraged artificial intelligence to reanalyze a clinical trial for an Alzheimer's medication, identifying a patient group that responded positively to the treatment. This approach highlights AI's potential in enhancing the design of future clinical trials, potentially expediting the development of new medicines.
In a completed Alzheimer's disease drug trial, researchers utilized an AI model and discovered that the drug reduced cognitive decline by 46% among patients with early-stage, slow-progressing mild cognitive impairment—a precursor to Alzheimer's.
The use of AI allowed researchers to categorize participants into groups based on their progression rate towards Alzheimer's. This method enables more precise participant selection, potentially lowering the cost of developing new drugs by optimizing clinical trials.
The AI model, developed at the University of Cambridge, predicts how quickly individuals in early cognitive decline stages will progress to Alzheimer's. It offers predictions three times more accurate than traditional assessments using memory tests, MRI scans, and blood tests.
Re-analysis using this stratification model revealed that while both groups showed beta amyloid clearance—a key Alzheimer's marker—only early-stage patients exhibited symptom changes. The findings suggest that AI can help identify patients who would benefit most from specific treatments.
Published in Nature Communications, Professor Zoe Kourtzi from Cambridge's Department of Psychology noted: "Promising new drugs fail when given to people too late... With our AI model we can finally identify patients precisely... turbocharging the search for a desperately-needed precision medicine approach for dementia treatment."
Health Innovation East England is assisting Kourtzi in applying this AI-enabled method in clinical care. Joanna Dempsey from Health Innovation East England commented: "This AI-enabled approach could have a significant impact on easing NHS pressure and costs... enabling more personalized drug development."
Current dementia treatments aim to slow cognitive decline rather than cure it. Dementia remains a leading cause of death worldwide and poses significant economic challenges due to high research failure rates and costs exceeding $1.3 trillion annually.
Despite recent US approvals for new dementia drugs, adoption by NHS has been hindered by side effects and cost concerns. Personalized treatment approaches are crucial given individual differences in disease progression and response.
"AI can guide us to the patients who will benefit from dementia medicines," Kourtzi stated. "Making clinical trials faster... guided by AI has strong potential..."
Kourtzi also shared her personal motivation: "Like many people, I have watched hopelessly as dementia stole a loved one from me..."
This research received funding from entities including the Royal Society and Wellcome Trust.