Early diagnosis of dementia and Alzheimer’s can be challenging because both conditions share many symptoms with age-related cognitive loss. Researchers at the University of Cambridge have created an artificial intelligence (AI) tool that can forecast if a person with early dementia symptoms would remain stable or develop Alzheimer’s. It was three times more accurate than current clinical standards and may aid in directing patients to suitable treatment early in their illness.
Early diagnosis is essential to arrest the progression of both dementia and Alzheimer’s disease. However, past research indicates that fewer than half of people with dementia symptoms ever receive a diagnosis [1]. Furthermore, it might be challenging to diagnose dementia or Alzheimer’s early on because both conditions overlap symptoms of age-related cognitive loss.
To address this problem, University of Cambridge researchers have created an artificial intelligence (AI) tool that can predict whether an individual with early dementia symptoms would continue to remain stable or develop Alzheimer’s [2]. Journal eClinical Medicine published the findings recently [3].
The AI-Based Tool
Researchers employed cognitive tests and MRI scan data from over 400 people in a US-based research group to develop their AI tool.
They then used data from 600 more participants in the US research group and 900 individuals from memory clinics in Singapore and the United Kingdom to test their AI technology.
The research team trained and tested their AI model on regularly acquired data from research cohorts as well as patients in real-memory clinics to ensure that it could be implemented in a healthcare setting. This demonstrated its applicability in a real-world context.
AI Tool 3 Times More Accurate in Predicting Alzheimer’s Development than Standard Tests
According to the research, the AI-powered tool could distinguish between study participants with stable mild cognitive impairment and those who progressed to Alzheimer’s in three years.
The technique identified 82% of individuals who ultimately had Alzheimer’s disease and 81% of individuals who did not, based solely on MRI scans and cognitive testing.
Researchers found that compared to the current standard of treatment, the AI tool was nearly three times more accurate at predicting the development from early-stage dementia symptoms to Alzheimer’s.
The model also enabled the researchers to divide the population with Alzheimer’s into three groups based on information from each patient’s initial visit to the memory clinic: participants with stable symptoms (approximately 50%), those with a gradual progression of the disease (approximately 35%), and those with a faster progression (15%).
Examining follow-up data spanning six years confirmed these predictions. It is significant because it can help identify patients who may benefit from novel treatments at the early stage and those who require close monitoring since their illness can deteriorate rapidly.
Zoe Kourtzi, PhD, the study’s senior author and an experimental psychology professor at the University of Cambridge, claims that despite employing only data from MRI scans and cognitive tests, their tool is far more sensitive than existing methods at predicting whether a person will progress from mild symptoms to Alzheimer’s and, if so, how quickly.
She stated that this AI tool has the potential to significantly enhance patient well-being by identifying which patients require the closest care and relieving anxiety in those patients who will remain stable. This will also help eliminate the need for unnecessary invasive and expensive diagnostic testing.
Alzheimer’s Research Association is a non-profit organization dedicated to helping caregivers of Alzheimer’s disease and dementia. We provide the latest information and news about the illness and helpful tips to help caregivers cope with their daily caregiving challenges. We realize the most important thing that a caregiver needs is financial assistance. Therefore, we provide grants to caregivers to ease their financial burden. Caregivers can apply for grants here: Alzheimer’s Grant Application.
You can also help caregivers in their endeavor by donating as much as possible: Donation To Alzheimer’s Research Associations.
References
- Advancing Early Detection. Alzheimer’s Disease and Healthy Aging. CDC. https://www.cdc.gov/aging/healthybrain/issue-maps/early-detection.html. Accessed: 13th August, 2024.
- Artificial intelligence outperforms clinical tests at predicting progress of Alzheimer’s disease. University of Cambridge. https://www.cam.ac.uk/research/news/artificial-intelligence-outperforms-clinical-tests-at-predicting-progress-of-alzheimers-disease. Published Online: 12th July, 2024. Accessed: 13th August, 2024.
- Lee, L.Y., Vaghari, D., Burkhart, M.C., Tino, P., Montagnese, M., Li, Z., Zühlsdorff, K., Giorgio, J., Williams, G., Chong, E. and Chen, C., 2024. Robust and interpretable AI-guided marker for early dementia prediction in real-world clinical settings. EClinicalMedicine.
- Scientists create AI tool that helps predict Alzheimer’s with up to 82% accuracy. Medical News Today. https://www.medicalnewstoday.com/articles/ai-outperforms-clinical-tests-4-out-of-5-at-predicting-progress-of-alzheimers-disease. Published Online: 19th July, 2024. Accessed: 13th August, 2024.
- AI tool predicts Alzheimer’s better than standard tests. News Nation. https://www.newsnationnow.com/health/ai-predicts-alzheimers/. Published Online: 16th July, 2024. Accessed: 13th August, 2024.