Predictive models offer insight into cognitive decline for early Alzheimer’s patients, highlighting potential benefits of new drugs.
The variability in the progression of cognitive decline among individuals diagnosed with early Alzheimer’s disease has posed significant challenges for patients, caregivers and clinicians alike. Now a recent study published Neurology, explores the potential of predictive models to provide clearer prognostic information. Conducted by a team at the Amsterdam University Medical Center, Netherlands, the study also assesses how recently approved Alzheimer’s drugs might slow cognitive decline [1].
Dr Pieter van der Veere, of Amsterdam University Medical Center, Netherlands and the lead author, emphasized the importance of these predictive models: “The rate of cognitive decline varies greatly from person to person, and people are very interested in what to expect from the disease in themselves or their loved ones, so better prediction models are urgently needed [2].”
Longevity.Technology: Dementia, the most common cause of which is Alzheimer’s disease, affects over 55 million people globally, with an annual economic impact of approximately $820 billion [3]. As the number of dementia cases is projected to nearly triple over the next 50 years, the development of accurate, non-invasive predictive tools and effective treatments is of critical importance.
Early detection of Alzheimer’s disease is paramount as it allows for timely interventions, which are most effective at the initial stages of the disease, and can facilitate the use of emerging treatments and lifestyle adjustments that may slow the progression of the disease. This not only benefits patients in managing symptoms but also alleviates the economic burden associated with advanced Alzheimer’s care. This early diagnosis can significantly enhance the quality of life for patients and provide a clearer framework for caregivers and medical professionals to plan appropriate care strategies.
The study evaluated the cognitive trajectories of 961 individuals, with an average age of 65, who exhibited mild cognitive impairment or mild dementia and had amyloid-beta plaques in their brains, an early indicator of Alzheimer’s disease. The cognitive abilities of these participants were measured using a test where scores range from zero to 30. Scores of 25 and higher suggest no dementia, 21 to 24 indicate mild dementia, 10 to 20 denote moderate dementia, and scores below 10 reflect severe dementia.
Over five years, individuals with mild cognitive impairment showed a decline in test scores from an average of 26.4 to 21.0, while those with mild dementia saw a decline from 22.4 to 7.8. The models developed by the researchers predicted these declines with reasonable accuracy. For half of the participants with mild cognitive impairment, actual test scores were within two points of the predicted scores; for those with mild dementia, scores were within three points of the predicted outcomes.
Impact of new drugs
The study further explored the impact of new Alzheimer’s drugs in slowing cognitive decline. A hypothetical scenario was analyzed where an individual with mild cognitive impairment and a baseline score of 28, with a certain level of amyloid plaques, would progress to moderate dementia (a score of 20) in six years without treatment. With a drug that reduces the rate of decline by 30%, this progression could be delayed to 8.6 years. Similarly, for an individual with mild dementia and a baseline score of 21, the time to reach a score of 15 would extend from 2.3 years to 3.3 years with treatment.
Dr van der Veere made the important point that while scores like these play a key role in research, those living with the disease will need more ‘real world’ predictions.
“We understand that people with cognitive problems and their care partners are most interested in answers to questions like ‘How long can I drive a car?’ or ‘How long can I keep doing my hobby?’,” he explained. “In the future, we hope that models will help make predictions about these questions about quality of life and daily functioning. But until then, we hope these models will help physicians translate these predicted scores into answers for people’s questions [2].”
Advances in predictive tools
Complementing these findings, researchers at Cambridge have developed an AI tool capable of predicting, with a high degree of accuracy, whether individuals with early signs of dementia will progress to Alzheimer’s disease. This AI tool, which outperforms clinical tests, has shown to correctly predict the progression to Alzheimer’s in 82% of cases and identify stable mild cognitive impairment in 81% of cases [4].
The algorithm’s predictive accuracy surpasses that of current standard diagnostic methods, which rely on clinical markers such as gray matter atrophy or cognitive scores. This advancement suggests a significant reduction in misdiagnosis and a potential decrease in the reliance on invasive and expensive diagnostic tests, such as PET scans and lumbar punctures, which are not universally accessible.
The combined insights from the Amsterdam University Medical Center’s study and the Cambridge AI tool signify promising steps forward in the management of Alzheimer’s disease; by enhancing the accuracy of early diagnosis and offering potential avenues to slow cognitive decline, these advancements provide hope for improved patient outcomes and more efficient use of healthcare resources.
[1] https://www.neurology.org/doi/10.1212/WNL.0000000000209605
[2] https://www.aan.com/PressRoom/Home/PressRelease/5186
[3] https://www.cam.ac.uk/research/news/artificial-intelligence-outperforms-clinical-tests-at-predicting-progress-of-alzheimers-disease
[4] https://www.thelancet.com/journals/eclinm/article/PIIS2589-5370(24)00304-3/fulltext
Photograph: iLexx/Envato
