Artificial Intelligence (AI) – human intelligence exhibited by machines – in healthcare is developing rapidly, with many applications currently in use or in development in the UK and worldwide.

We speak to Dr David Llewellyn, a Senior Research Fellow in Clinical Epidemiology at the University of Exeter Medical School, about the impact of AI on dementia diagnosis. David’s research focuses on how data science and AI can improve the way in which we conceptualise neurocognitive disorders in order to improve diagnosis, treatment and prevention.

How do you define AI as it relates to healthcare and what are some of the biggest transformations that it will bring to the field?
In its broadest sense, artificial intelligence is the creation of generalisable intelligence. At the moment the majority of progress is being made with machine learning, where we’re teaching machines to learn patterns in real clinical data. We’re taking techniques that have been developed for a wide range of purposes, for example, self-driving cars and search engines, and applying this to real clinical data. This gives us a massive advantage in that we’re able to handle a much richer range of data than we were able to do so before with traditional statistical methods. We’re developing pieces of software which can be used by clinicians or patients to improve healthcare efficiency, patient safety, and patient outcomes.

How close are we to a world where AI are used to diagnose and treat patients?
I think that AI is already used to diagnose and treat patients but in limited ways. For example, before patients come and see their GP, they’re increasingly using the internet. They’re using AI through search engines to work out what their symptoms might mean. Doctors are also increasingly using various forms of AI and we’re seeing the growth in decision-making aid. It’s very much that the doctor is still in control, but they’re getting more targeted information about individual patients.

Do you foresee a future where AI technologies can operate autonomously in healthcare?
We’re much further away from systems that can actually make decisions autonomously without the doctor and without any clinical oversight. If we think about autonomous cars as an analogy, we’ve got cruise control. Similarly with AI in healthcare, we’ve got aids to decision-making. What we don’t have are ‘robot doctors’ that can diagnose and treat patients without any human oversight. I think that will come, but we’re a long way from that.

The biggest question at the moment is how we are going to regulate that process. If it’s an aid for doctors but the doctor is still in control, then you can regulate it as a medical device. But if it’s autonomous, then actually what it’s doing is practicing medicine, not supporting a doctor who practices medicine. Medical societies regulate people who practice medicine but who exactly is going to regulate machines that have the capacity to practice medicine? I don’t think we’re anywhere near to reaching a solution for that and there is certainly no way which we can effectively regulate that at the moment.

Are there any common misconceptions or general misunderstandings about AI that you believe could use some clarity?
When we think about how AI can influence medicine, there’s often the misconception that it’s going to deskill the workforce and put people out of a job. However, when you bear in mind the immense pressures that the NHS is under, I think AI technologies in healthcare should be seen as a massive opportunity to improve patient outcomes and to make the jobs themselves better for clinicians. Particularly things that are routine – they can be taken away from a clinician’s job. It will become less about whether AI will replace clinicians, but more about how clinicians will use the technology to enhance their own abilities. That’s a tremendous opportunity if you can empower clinicians to think in that way. It will allow them to focus on the human side of medicine, which for most medical professionals is the most interesting bit!

Identifying people with dementia is clinically challenging given the non-specific pattern of symptoms associated with it. You’ve recently developed a computerised decision support system called DECODE to help address this. Can you tell us more about it?
It’s a very difficult clinical challenge assessing patients who you may not know well and who are concerned about their memory and thinking, and trying to work out whether they are just ageing normally as no two cases of dementia are exactly alike. If you’re a non-specialist, you may not have seen a patient with a particular combination of signs and symptoms before. So one of the advantages of DECODE, a machine learning-driven system, is that it can learn to recognise patterns in hundreds, thousands, potentially millions of dementia cases and work out what needs to happen clinically to benefit that patient. So it’s the idea it doesn’t get tired or distracted and it’s very consistent. It’s not a completely objective system though, as it captures the human expert decision-making that we used to train it in the first place.

To find out more about the DECODE project, follow David (@DrDJLlewellyn) on Twitter. To read more about dementia research at Exeter, please visit our website, or follow #ExeterDementia.

Professor Clive Ballard, Executive Dean of the University of Exeter Medical School and internationally-renowned dementia researcher, updates on the latest from the Alzheimer’s Association International Conference 

It’s an incredibly exciting time in dementia research. I’m part of a team from the University of Exeter who have just returned from the Alzheimer’s Association International Conference in Chicago– one of the largest showcases of worldwide dementia research. It’s where the cutting-edge of dementia research is shared, often for the first time. It’s really on the front line of discovery. We presented our own research in a range of areas around improving prevention, treatment and care in dementia, and we spoke to the research teams behind the latest innovations. I’m feeling inspired and optimistic about a number of promising developments.

 

Hope in Alzheimer’s therapeutics

There’s an urgent need for more and better research in dementia, a disease which affects 40 million people worldwide. Our own research highlighted that there are only 29 clinical trials with the potential to modify Alzheimer’s disease that have passed the first phase of testing – compared to more than 1,000 in cancer, for example. We’ve seen a number of high-profile failures in dementia clinical trials, and we urgently need more and better-designed trials to make an impact.

We finally got the positive news we’ve been craving at the conference. A compound called BAN2401 is showing real promise in treating Alzheimer’s disease. In a trial of 800 people, it reduced levels of amyloid – a protein linked to dementia – by more than 90 per cent. The trial was conducted in people who already had some amyloid build-up in the brain. Particularly excitingly, more than 80 per cent of them saw levels reduce to normal over the 18 month trial, and the rate of cognitive decline was reduced by 50 per cent.

It’s early days yet, but these figures are stunning  – the most promising results we’ve ever seen in a clinical trial at this stage. We need a larger trial, which will take at least three years, to see if the results are confirmed. If so it will be a really significant breakthrough.

 

Reduction of “chemical cosh” prescribing

Our research revealed that people with dementia are being harmed by medication designed to ease their symptoms. An opioid-based painkiller called buprenorphine and a class of sleeping pill called Z-drugs both increase harms such as falls in people with dementia, and in turn falls lead to a significant rise in death rates.

It makes sense – these drugs have a sedative effect. We have to stop sedating elderly, frail people with dementia and look for non-drug options to help them more effectively.

Our research uncovered the harms caused by antipsychotics to people with dementia. It provided the evidence base to persuade everyone involved in dementia research and care to make a concerted effort to find alternatives, which led to a 50 per cent reduction in prescribing. We now need this approach with other medications – and to ensure that the alternatives we use are not harmful in themselves.

 

Personalising care improves lives

Care homes are really challenging environments, both for people with dementia and for carers. Our previous research has shown that the average person with dementia experiences just two minutes of social interaction each day. Imagine that! It’s no wonder that levels of agitation and apathy are very high. Residents have complex needs and staff need training in techniques that really work. Incredibly, only three of 170 care home staff training programmes are evidence-based, and none of those improved quality of life.

Our WHELD staff training programme incorporates ten minutes of social interaction each day and a programme of personalised care, designed around the needs and interests of the individual resident. It brings people with dementia and their carers together, resulting in improved wellbeing and more positive staff attitudes to care. We found these outcomes when the programme is delivered as e-learning, supported by Skype. It’s now time this rolls out to care homes to improve people’s lives.

 

Take action to prevent dementia

 Our previous research has found that dementia risk could be reduced by a third, if people took action from mid-life onwards. Factors including diet, exercise, education, social interaction and effectively managing health issues such as hearing loss and depression all play a role in dementia risk.  There’s an increasing body of evidence around links to blood pressure and dementia risk. Previously this has focussed around high blood pressure, but research at the conference has found compelling evidence that orthostatic hypotension – or unusually high drops in blood pressure – is also linked to increased dementia risk. We need to understand this better, but it does add further weight to the advice to look after your heart to protect your brain.

The conference included interesting updates on the benefits of sleep – a deep night’s sleep means the amyloid levels in the body are lower the next morning. We also saw some interesting research on food products such as green tea, ginseng and omega 3 fatty acids, and on curcumin, contained in turmeric, and how they activate different parts of the brain that are implicated in dementia. We’ll be putting these to the test in our online PROMOTE platform, which has 25,000 people aged 50 or over signed up. Watch this space to find out what really works!

Keep updated on our dementia research by following #ExeterDementia on Twitter or visiting: http://www.exeter.ac.uk/dementia/

 

Hello and thank you for visiting our new Exeter dementia blog!

We will be using this blog space to keep you in touch with all the latest dementia research happening at the University of Exeter Medical School.

Over the next couple of months we’ll be inviting our dementia researchers to contribute to our blog – watch this space for an exciting insight into the work we do on dementia!