You are here

Doctors to harness AI to diagnose dementia

Doctors to harness AI to diagnose dementia
26th October 2018

Artificial intelligence (AI) could be used to help diagnose dementia in future in bid to be more accurate and create better treatments. Researchers at University College London (UCL) have developed a computer algorithm which can learn to recognise different types of dementia from MRI brain scans.

The reason this could be a significant breakthrough is because many types of the neurodegenerative condition have similar symptoms. Despite this, they all respond differently to treatment, so it’s important to ascertain exactly which type an individual has.

Using AI in this way has therefore been deemed ‘pioneering’, with the potential to revolutionise dementia treatment in the future. The condition is expected to affect one million people in Britain by 2025 and there is currently no cure.

The algorithm has been named SuStaln, which combines Subtype and Stage Inference. While processing MRI images, it begins to recognise the types of dementia as they develop and can make predictions on how it will affect the patient’s brain going forward.

Dr Sara Imarisio, head of research at Alzheimer's Research UK, said: “Diagnosing dementia accurately can be a challenge. Particularly as many of the early symptoms may overlap with other health conditions.

“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.”

Many studies into dementia treatments have run into trouble, because the conditions being monitored in the patients are not the same. Things that work for those with Alzheimer’s may be ineffective on participants with the less common frontotemporal dementia.

Professor Daniel Alexander from UCL believes that SuStaln has the potential to expedite treatments to market, because scientists will be able to look at their effects of different subgroups of patients. Drugs may no longer fail trials because they haven’t proved effective on a vast and varied group.

To test out SuStaln, a database of brain scans from 365 volunteers was analysed, with changes to the brain associated with Alzheimer’s and dementia correctly identified. It could establish what stages the conditions were at and how they differ from each other.

Professor Jonathan Schott, a neurologist at UCL, said: “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.”

Seeing a loved one’s memory decline is difficult to go through and it’s hard as they lose their independence. Hopefully, medical breakthroughs will mean that the current trend in increased cases can be reversed and more people can live out a happy old age.