Scientists Train Computers To Recognise the Memory-robbing Disorder

Doctors could use artificial intelligence to diagnose dementia more accurately and give better treatment, scientists say.

Researchers have invented a computer algorithm which can analyse MRI brain scans and learn how to recognise different types of dementia.

They say that although many types of the brain-destroying condition have similar symptoms, they respond differently to treatment.

Being able to correctly identify which type someone has means patients could be helped earlier on in their illness or given more targeted therapy.

Experts say the research is ‘pioneering’ and has ‘huge potential’ in the future of treating dementia, expected to affect one million Britons by 2025.

University College London researchers have come up with the algorithm SuStaIn, which stands for Subtype and Stage Inference.

As it processes MRI images it learns how to recognise different types of dementia as they develop, predict what will happen in patients’ brains, and identify the illness in its earlier stages.

‘Diagnosing dementia accurately can be a challenge,’ said Dr Sara Imarisio, head of research at Alzheimer’s Research UK.

‘Machine learning is an incredibly powerful tool and we are only just beginning to realise its full potential to analyse vast and intricate datasets in dementia research.

‘In this new study the value of machine learning is demonstrated through its ability to bring together brain scans to give in-depth insights into the subtle brain changes in Alzheimer’s disease and frontotemporal dementia.’

Dementia is not an illness in itself but a term which describes symptoms caused by various diseases of the brain – by far the most common is Alzheimer’s disease.

Scientists say studies into dementia treatments can be troubled because difficulty distinguishing between types of the condition means participants may not have exactly the same illness.

But using this AI to accurately group patients with the same diseases will mean trials are more likely to be successful, researchers say, speeding up drug development.

Professor Daniel Alexander, from UCL, said: ‘This new algorithm has the unique ability to reveal groups of patients with different variants of disease.

‘One key reason for the failure of drug trials in Alzheimer’s disease is the broad mixture of very different patients they test; a treatment with a strong effect on a particular subgroup of patients may show no overall effect on the full population so fail the drug trial.

‘SuStaIn provides a way to show treatment effects on distinct subgroups, potentially expediting treatments to market.’

In a trial, SuStaIn used a database of MRI brain scans from 365 volunteers from 13 locations across the UK.

The algorithm scanned the images for changes in the brain which were linked to the Alzheimer’s disease and frontotemporal dementia and their progression.

It could successfully recognise the different types and stages of the two diseases and could aid a more accurate diagnosis of either.

Both cause dementia but they have different underlying causes and ways of developing.

And while both have unique symptoms their symptoms can often overlap as they get worse over time, making diagnosis even more difficult.

Spotting the types early on in the disease process using non-invasive MRI scanning means there is a better chance of identifying the best treatment for patients.

UCL neurologist Professor Jonathan Schott added: ‘Understanding how different diseases evolve over time is critical if we are to design rational treatment trials and inform patients about prognosis.

‘This is a major challenge for diseases that evolve over years, if not decades, and where there may be substantial differences in the underlying pathology and progression between patients.

‘This work shows that it is possible to tease out different disease patterns – some hitherto unknown – from single MRI scans taken from patients with a range of different dementias.

‘As well as providing new insights into dementia, this work demonstrates the huge potential of SuStaIn to delineate disease subtypes in a range of other medical contexts.’

The research was published in journal Nature Communications, and the team are exploring whether the technology could work for other chronic diseases such as those in the lungs.