Artificial intelligence outperforms clinical tests in predicting the progression of Alzheimer’s disease

Scientists from Cambridge have developed an artificially intelligent tool that can predict in four out of five cases whether people with early signs of dementia will remain stable or develop Alzheimer’s disease.

The team says this new approach could reduce the need for invasive and expensive diagnostic tests while improving treatment outcomes early on when interventions such as lifestyle changes or new medications have a chance to work best.

Dementia is a significant global health care problem, affecting more than 55 million people worldwide, with an estimated annual cost of $820 billion. The number of cases is expected to almost triple over the next fifty years.

The leading cause of dementia is Alzheimer’s disease, which accounts for 60-80% of cases. Early detection is critical because this is when treatments are likely to be most effective, but early diagnosis and prognosis of dementia may not be accurate without the use of invasive or expensive tests such as positron emission tomography (PET) scans or lumbar puncture, which are not possible. available in 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 Department of Psychology has developed a machine learning model that can predict whether and how quickly a person with mild memory and thinking problems will progress to developing Alzheimer’s disease. From research published in eClinical Medicinethey show that it is more accurate than current clinical diagnostic tools.

To build their model, the researchers used routinely collected, non-invasive and inexpensive patient data – cognitive tests and structural MRI scans showing gray matter atrophy – from more than 400 individuals who were part of a research cohort in the US.

They then tested the model using real-world data from a further 600 participants from the US cohort and, importantly, longitudinal data from 900 people from memory clinics in Britain and Singapore.

The algorithm was able to distinguish between people with stable mild cognitive impairment and those who progressed to Alzheimer’s disease within a three-year period. It was able to correctly identify individuals who developed Alzheimer’s disease in 82% of cases, and correctly identify those who did not in 81% of cases based on cognitive testing and an MRI scan alone.

The algorithm was approximately three times more accurate at predicting progression to Alzheimer’s disease than the current standard of care; that is, standard clinical markers (such as gray matter atrophy or cognitive scores) or clinical diagnosis. This shows that the model can significantly reduce misdiagnosis.

The model also allowed the researchers to divide people with Alzheimer’s disease into three groups, using data from each person’s first visit to the memory clinic: those whose symptoms would remain stable (about 50% of participants), those who would slowly progress to Alzheimer’s (about 35%) and those who would progress more quickly (the remaining 15%).

These predictions were validated by looking at six-year follow-up data. This is important as it can help identify these people early so they can benefit from new treatments, while also identifying those who need close monitoring as their condition is likely to deteriorate quickly.

Importantly, the 50% of people who have symptoms such as memory loss but remain stable may be better directed to another clinical pathway, as their symptoms may be due to causes other than dementia, such as anxiety or depression.

Senior author Professor Zoe Kourtzi from the University of Cambridge’s Department of Psychology said: “We have created a tool that, despite using only data from cognitive tests and MRI scans, is much more sensitive than current approaches to predicting whether someone will make progress. from mild symptoms to Alzheimer’s disease – and if so, whether this progress will be fast or slow.

“This has the potential to significantly improve patient wellbeing, by showing us which people need care most, while allaying anxiety for those patients who we predict will remain stable. At a time of intense pressure on healthcare resources, this will also help eliminate the need for unnecessary invasive and expensive diagnostic tests.”

While the researchers tested the algorithm on data from a research cohort, it was validated using independent data from nearly 900 individuals who attended memory clinics in Britain and Singapore.

In Great Britain, patients were recruited through the Quantitative MRI in NHS Memory Clinics Study (QMIN-MC), led by study co-author Dr. Timothy Rittman at Cambridge University Hospitals NHS Trust and Cambridgeshire and Peterborough NHS Foundation Trusts (CPFT).

The researchers say this shows that it should be applicable in a real clinical patient environment.

Dr. Ben Underwood, Honorary Consultant Psychiatrist at CPFT and Assistant Professor at the University of Cambridge’s Department of Psychiatry, said: “Memory problems are common as we get older. In the clinic I see how uncertainty about whether these could be the first signs of dementia can cause a lot of worry for people and their families, but also be frustrating for doctors who would rather give definitive answers.

“The fact that we can reduce this uncertainty with information we already have is exciting and will likely become even more important as new treatments emerge.”

Professor Kourtzi said: “AI models are only as good as the data they are trained on. To ensure ours have the potential to be applied in healthcare, we trained and tested them on routinely collected data, not just research cohorts. , but from patients in real memory clinics. This shows that it will be generalizable to a practical situation.’

The team now hopes to extend their model to other forms of dementia, such as vascular dementia and frontotemporal dementia, and use different types of data, such as markers from blood tests.

Professor Kourtzi added: “If we are to tackle the growing health challenge of dementia, we need better tools to identify and intervene in this disease at the earliest possible stages.

“Our vision is to scale our AI tool to help doctors assign the right person to the right diagnostic and treatment path at the right time. Our tool can help match the right patients to clinical trials, accelerating the discovery of new drugs for disease-modifying treatments. “