Researchers at the University of Cambridge have developed a groundbreaking AI tool that can predict the progression of Alzheimer’s disease with greater accuracy than existing clinical tests. The study, led by cognitive computational neuroscientist Zoe Kourtzi, utilized AI algorithms trained on cognitive ability tests and brain scans from 410 individuals to identify patterns linking cognitive function with underlying brain changes. In trials involving 1,486 cases not included in the training data, the AI accurately predicted the development of Alzheimer’s within three years 82 percent of the time and successfully identified individuals who would not develop the disease 81 percent of the time.
This performance significantly outpaces current clinical assessments.
Cambridge ai predicts Alzheimer’s progression
The AI’s ability to forecast the speed of dementia progression could aid doctors in administering timely treatments and facilitate further research into the early stages of Alzheimer’s.
Kourtzi emphasized the importance of training the model on real-world data from memory clinics to ensure its applicability in healthcare settings. The new AI-based approach is relatively cost-effective and non-invasive, avoiding the need for tissue or blood collection. Identifying individuals at low risk of developing Alzheimer’s can also provide peace of mind to those experiencing memory issues as they age.
Psychiatrist Ben Underwood from the University of Cambridge commented, “The fact that we might be able to reduce this uncertainty with information we already have is exciting and is likely to become even more important as new treatments emerge.
The research has been published in the journal eClinicalMedicine and represents a significant advancement in Alzheimer’s research through the use of AI, offering hope for early and more accurate diagnosis and treatment planning.
