How health tech could help in the early diagnosis of dementia by Emily Reynolds

Dementia is a growing condition, overtaking heart disease, lung cancer and stroke as the leading cause of death in the UK, and Alzheimer’s Research UK suggests there are over 209,000 new cases of dementia every year in the UK – roughly equivalent to a new case every three minutes.

As life expectancy increases, so the likelihood of people developing dementia has risen – making it a pressing public health concern.

Early detection can be difficult, too, as Dr Carol Routledge, director of research at Alzheimer’s Research UK, explains. Clinical tools are currently not sensitive enough to diagnose early, and blood tests are “not sufficiently specific” to diagnose the diseases causing dementia. She also points out that PET (positron emission tomography) imaging – a type of brain scanning often used to diagnose dementia – can be prohibitively expensive, making it almost impossible to use as widely as needed. “We need to develop inexpensive, disease-specific tools that can be used on a population-wide basis,” she says.

 Dr Sina Habibi, founder of Cognetivity.

This year’s AXA Health Tech & You State of the Nation survey, conducted by YouGov to examine developing health tech trends, produced similar findings: more than half of adults (54%) felt that there was a delay between a loved one experiencing symptoms of dementia to eventually receiving a diagnosis, and almost half (48%) said they would have encouraged their loved one to visit the doctor earlier if technology had been available to detect it.

Against this backdrop, a number of companies have started developing innovative tech to address the issue. Cognetivity, Aparito and Memrica are finalists for AXA’s Innovations in the Early Diagnosis of Dementia award, which is part of the AXA Health Tech & You 2018 Programme. They utilise technology in different ways to tackle the problem of early detection and diagnosis of dementia.

Cognetivity uses “cutting-edge AI and neuroscience to create disruptive software solutions” for the early detection of dementia, explains co-founder Dr Sina Habibi. Founded in 2013, when Habibi and co-founder Seyed-Mahdi Khaligh-Razavi were PhD students at Cambridge, Cognetivity uses an Integrated Cognitive Assessment (or ICA), which it describes as a “quick and simple cognitive test”.

Subjects are shown a succession of “short exposure visual stimuli” and then asked whether or not they saw an animal. The speed and accuracy of a subject’s response varies “according to [their] cognitive ability”, with the speed of information transmission often slower in neurons affected by dementia.

“While other tests only heavily focus on memory, ours activates key and large parts of the brain such as the visual, motor and frontotemporal cortexes simultaneously, making it more sensitive to lower levels of deterioration,” he explains.

These test results are then combined with additional data from the subject’s profile – including their demographics and medical history – so Cognetivity’s AI engine can “process and compare the scores with its knowledge base” to provide an indication of the subject’s risk of developing dementia.

 Aparito founder Dr Elin Haf Davies: she describes healthcare as ‘the last of the industries not to be disrupted by technology.’

Companies are also providing care outside of hospitals. Aparito, founded by Dr Elin Haf Davies, utilises wearable technology to monitor patients outside of typical healthcare environments. Data including step counts, movement type, skin and ambient temperatures, humidity, heart rate and sleep patterns is collected; the app also contains modules that allow patients to measure medication adherence and monitor visits to healthcare professionals, as well as to measure perceived quality of life.

Davies points out that only 1% to 3% of a patient’s journey is captured during hospital visits and clinic appointments; her platform allows for “all outcomes important to patients to be captured remotely, passively and in real time”.

“Our time in hospitals and clinics is only a very snapshot, episodic view of a patient’s experience and wellbeing,” she says. “Monitoring patients between these visits is imperative to see subtle changes, and emerging technology gives us the opportunity to move healthcare provisions outside of the hospital settings.”

Memrica, says director Mary Matthews, takes a similar approach, and is currently developing a system to detect early signs of dementia via smartphone data.

“The concept came from our current app, Prompt by Memrica, which helps people stay socially active when memory loss robs them of their confidence,” she says. “We started to look at changes in social engagement as a behavioural indicator for cognitive decline, and just naturally began to think about what else we could capture and analyse with the user’s permission.

“It was one of those ‘what if?’ moments that got us really excited, because the smartphone is something so many of us carry all the time. If we could tell people they were showing an early risk of dementia later in life, we could help them change their lifestyle to delay or prevent the condition.”

Memrica is currently at the early design stage – Matthews notes that the company is “working through practicalities” including which data sets to collect first and ensuring that the app will give people “the right insights into their health and the right individual advice to reduce their risk”.

Davies describes healthcare as very risk averse: “the last of the industries not to be disrupted by technology”.

Regulatory science can’t keep up with emerging technology

Dr Elin Haf Davies

“This is partly because regulatory science can’t keep up with emerging technology, but mainly because it requires a cultural shift in working,” she says. “A way to do this is to have a collaborative approach to the development. All parties – patients, clinicians, regulators and innovators – need to have the chance to co-develop the solution from conception. At Aparito, we see this as the best way to navigate around all barriers – real and perceived.”

Habibi also points to slow uptake of technology as an issue in the area, citing a “lack of sensitive tools available at primary care”.

“Currently, GPs either rely on crude pen and paper tests focused on memory (if affected, this suggests significant disease progression) or have to refer patients already suffering symptoms to memory clinics,” he says.

All three founders point to knowledge gaps, meaning increasing awareness of early symptoms is key. But, as Routledge points out, “significant progress” has been made in early diagnosis, with research helping the understanding of “what goes wrong and the mechanistic processes underlying these changes”.

And Habibi stresses how large a role AI and big data will play in the future of dementia detection.

“Data from accurate health-monitoring tools, higher-resolution imaging, deeper genetic information and a bigger variety of biomarkers will all come together with the power of AI to give us an engine that can not only monitor and detect abnormalities earlier and more accurately, but also herald an era of personalised medication,” he says.