Scientists at the University of Cambridge have developed an artificial intelligence tool that can predict whether people with early signs of dementia will remain stable or develop Alzheimer's in four out of five cases.
The researchers say this new approach could reduce the need for invasive and costly diagnostic tests and improve outcomes at an earlier stage, when interventions such as lifestyle changes and new drugs may be most effective.
Dementia is a major global healthcare challenge, affecting more than 55 million people worldwide and costing an estimated $820 billion annually, with the number of patients expected to nearly triple over the next 50 years.
The leading cause of dementia is Alzheimer's disease, accounting for 60-80% of cases. Early detection is important because treatment is likely to be most effective, but early diagnosis and prognosis of dementia may be inaccurate without invasive or expensive tests such as positron emission tomography (PET) scans or lumbar punctures, which are not available at all memory clinics. As a result, up to a third of patients may be misdiagnosed, and others may be diagnosed too late for treatment to be effective.
A team led by scientists from the University of Cambridge's School of Psychology has developed a machine learning model that can predict whether people with mild memory or thought disorders will develop Alzheimer's disease, and how quickly they will develop it. Clinical Medicineand has been shown to be more accurate than current clinical diagnostic tools.
To build their model, the researchers used non-invasive, low-cost patient data collected routinely from more than 400 patients in a US study group - including cognitive tests and structural MRI scans showing grey matter atrophy.
The researchers then tested the model using data from an additional 600 real-life patients participating in a US cohort study, as well as longitudinal data from 900 people from memory disorders clinics in the UK and Singapore (the key data).
The algorithm was able to distinguish between people with stable mild cognitive impairment and those who progressed to Alzheimer's disease within three years. Using only cognitive tests and MRI scans, it correctly identified those who went on to develop Alzheimer's disease in 82% of cases and those who did not in 81% of cases.
The algorithm was approximately three times more accurate at predicting progression to Alzheimer's disease than the current standard of care, i.e. standard clinical markers (such as gray matter atrophy and cognitive scores) and clinical diagnosis, indicating that the model can significantly reduce misdiagnosis.
The model allowed the researchers to classify Alzheimer's patients into three groups, using data from each person's first visit to a memory clinic: those whose symptoms remain stable (about 50% of participants), those whose Alzheimer's disease progresses slowly (about 35%), and those whose Alzheimer's disease progresses more rapidly (the remaining 15%). These predictions were validated by looking at six years of follow-up data. This is important because it could help identify patients at an earlier stage who may benefit from new treatments, while at the same time identifying those who need closer monitoring because their symptoms may worsen rapidly.
Importantly, the 50% of people who have symptoms such as memory loss but remain stable are better off being directed down a different clinical pathway as their symptoms may be caused by something other than dementia, such as anxiety or depression.
Lead author Professor Zoe Curzi, from the University of Cambridge's School of Psychology, said: "Despite using only data from cognitive tests and MRI scans, we have developed a tool that is much more sensitive than current approaches in predicting whether mild symptoms will progress to Alzheimer's disease, and if so, whether the progression will be fast or slow."
"This has the potential to significantly improve patient health outcomes by identifying which patients need the most careful care and removing anxiety for those who are predicted to remain in a stable condition. At a time of increasing pressure on healthcare resources, this will also help to eliminate the need for unnecessary invasive and costly diagnostic tests."
The researchers tested their algorithm on data from the study cohort, but it was validated using independent data including nearly 900 individuals attending memory clinics in the UK and Singapore. In the UK, patients were recruited through the Quantitative MRI Study in NHS Memory Clinics (QMIN-MC), led by study co-author Dr Timothy Littman from Cambridge University Hospitals NHS Trust and Cambridgeshire Peterborough NHS Foundation Trust (CPFT).
The researchers say this shows potential application to real patients and clinical settings.
Dr Ben Underwood, Honorary Consultant Psychiatrist, CPFT and Associate Professor of Psychiatry at the University of Cambridge, said: "Memory loss is a common symptom of ageing. In clinical practice we see that the uncertainty of whether this is the first sign of dementia causes great anxiety for patients and their families, and frustrates doctors who want to give definitive answers. The fact that we may be able to reduce this uncertainty with the information we already have is extremely encouraging, and will become even more important as new treatments emerge."
Professor Kurzi said: "An AI model is only as good as the data it is trained on. To ensure that our model can be adopted in clinical practice, we trained and tested it not only on a research cohort, but also on data collected routinely from real memory clinic patients. This shows that the AI model is generalizable to the real world."
The team now hopes to extend the model to other types of dementia, such as vascular and frontotemporal dementia, using different types of data, such as blood test markers.
Professor Kurzi added: "To tackle the health challenges posed by dementia, we need better tools to identify and intervene at the earliest possible stage. Our vision is to extend AI tools to help clinicians assign the right diagnosis and treatment pathway to the right person at the right time. Our tools will help match the right patients to clinical trials and accelerate the discovery of new medicines for disease-modifying treatments."
The research was funded by Wellcome, the Royal Society, Alzheimer's Research UK, the Alzheimer's Drug Discovery Foundation Diagnostic Accelerator, the Alan Turing Institute and the National Health Research Institute Cambridge Biomedical Research Centre.
