AI is increasingly used in healthcare to diagnose and treat patients effectively.
In terms of ageing population challenges, AI can help to ease the burden on healthcare settings as well as picking up any early warning signs.
The latest innovations include those that aid diagnosis and prognosis, and enable older people to live longer, more independent lives.
AT World reports on some of the biggest advances in age-focused AI.
Hearing aids – and more
Generally from the age of 70, hearing can start to deteriorate and, while hearing aids are nothing new, AI is being used to make them more effective than ever.
For example, US company Starkey is using AI, sensors and digital technology to track hearing aid users’ fitness, detect falls and even translate languages.
The latter is achieved through the Starkey app which connects to Google Translate; when the hearing aid detects a foreign language, it can then be translated into English via the connected smartphone and streamed back into the hearing aid and transcribed on-screen.
The product also features sensors, such as accelerometers and gyroscopes that can add additional features and tools, tracking users’ health or understanding if the user has fallen alerting a carer or family member.
Cancer treatment
While cancer can affect anyone at any age, its prevalence rises with age – while the effectiveness of treatment lowers.
A number of AI-driven innovations have been introduced to assess how patients will respond to certain treatments, particularly chemotherapy.
In one example, researchers from Denmark created a system to detect which patients are at the highest risk of developing debilitating side effects from the treatment.
It was able to successfully identify over 90 per cent of patients who were at low risk from developing nephrotoxicity – a rapid deterioration in kidney function due to toxic effect of medications and chemicals.
Closer to home, scientists at the University of Leeds created a similar algorithm for elderly bowel cancer patients, assessing their levels of two key proteins which could then determine how a patient would respond to chemotherapy.
Diagnosing dementia
Earlier this year, a Cambridge University team, along with The Alan Turing Institute, announced the development of machine learning tools that can detect dementia in patients at a very early stage.
Using brain scans from patients who went on to develop Alzheimer’s, the algorithm learned to spot structural changes in the brain, which, when combined with results from standard memory tests, the was able to evaluate the likelihood of the individual having Alzheimer’s disease.
Remote monitoring
Loss of independence is a common struggle for the elderly; increasing care needs mean many older people feel unable to stay in their own homes as long as they would like.
AI can help to monitor patients in their own homes, while alerting clinicians to any worrying signs such as deterioration.
One such example is Imperial College Healthcare NHS Trust’s partnership with remote healthcare innovator Luscii to allow heart failure patients to self-monitor their vital signs at home
Users can carry out regular checks on their weight, blood pressure and general condition without having to attend a healthcare setting – something that often presents logistical difficulties aside from the fears surrounding Covid-19.
Powered by AI, the Luscii platform has been designed to spot early warning signs of patient deterioration, alerting medical staff who can then triage the situation and provide support or resources. Additionally, the technology can also ensure that outpatients are on the right medications.
Smart technology
The world of smart technology has so a multitude of uses in elderly healthcare, from fighting loneliness to keeping dementia patients safe.
For example, a pilot project in Sweden used a voice assistant smart speaker to drive conversations about users’ memories as a way of tackling loneliness.
Participants were asked to discuss topics including their biggest loves and travel experiences, with the speakers responding with relevant follow-up questions.
Meanwhile, technology such as SafelyYou is able to monitor physical stability and analyse movement to prevent fall risk, through the use of video monitors and artificial intelligence.
Or the Buddi system is a GPS alarm fitted to a silicone wrist strap, which also features an integrated fall detector and alarm button. The wristband sends a signal to a clip that can be attached to clothing, keys or carried in a handbag and which dials through to a 24/7 monitoring centre should a fall occur.
In the home, wearables such as CarePredict can track the activity that a person is likely to be engaged in by analysing the patterns in their gestures, among other data.
If repetitive eating motions aren’t detected as expected, a carer is alerted, or the system identifies someone as being in the bathroom and it detects a sitting posture, it can be inferred that the person “is using the toilet”, notes one of its patents.
Should a change to expected patterns be observed, such as a lack of movement or wandering outside usual boundaries, carers or family can be alerted.
