Improving dementia care through increased and timely diagnosis is an NHS priority, yet around half of those living with dementia live with the condition unaware. Now a new machine-learning model that scans routinely collected NHS data has shown promising signs of being able to predict undiagnosed dementia in primary care. Led by the University of Plymouth, the study collected Read-encoded data from 18 consenting GP surgeries across Devon, UK, for 26,483 patients aged over 65. The Read codes – a thesaurus of clinical terms used to summarise clinical and administrative data for UK GPs – were assessed on whether they may contribute to dementia risk, with factors included such as weight and blood pressure. These codes were used to train a machine-learning classification model to identify patients that may have underlying dementia.
Smart bottles that dispense the correct dose of medication at the correct time, digital assistants, and chairs that know how long you've sat in them are among the devices set to change the face of care for those living with dementia. Dementia is now the leading cause of death in England and Wales, and is thought to affect more than 850,000 people in the UK. But a new wave of connected devices, dubbed "the internet of things", could offer new ways to help people live independently for longer. "We have got an elderly population, and children in their 40s and 50s are looking after their elderly parents – and they may not have the capabilities to coordinate that care effectively," said Idris Jahn, head of health and data at IoTUK, a programme within the government-backed Digital Catapult. While phone calls and text messages help to keep people in touch, says Jahn, problems can still arise, from missed appointments to difficulties in taking medication correctly.
Music's ability to soothe the symptoms of dementia and Alzheimer's has been known for years. Now, a new BBC website aims to help by connecting dementia patients with the songs they love. Eventually, it's hoped the site will build a database of music that's effective at triggering memories. "Music can have such a powerful effect," said Snow Patrol star Gary Lightbody, whose father suffers from dementia. "It fires all sorts of things in the brain much more immediately than anything else can, whether it be pictures or old home movies or conversations.
Associate professor Masayuki Sato, who leads the research team, also said exercising with music helps dementia patients maintain daily activities more than exercise alone. The team asked 31 people with mild to moderate symptoms of dementia living in the towns of Mihama and Kiho in the prefecture to conduct 40 minutes of exercise to the music once a week for six months. They sat on a chair and bent and stretched their arms and waists and stamped their feet along with pop music with varying tempos. The team said those who participated in the program managed to maintain their physical activity level regarding daily routines, including changing clothes, eating and taking a bath, better than another group of 31 dementia patients who were only engaged in brain training exercises such as playing games and solving math questions. "We believe that exercising along with music proved highly effective because it is more complicating than just moving your body," Sato said.
A robot is being trained to recognise signs of dementia – by watching TV. Robbie the Robot, believed to be the first gadget of its kind, binge-watched ITV soap opera Emmerdale to learn how to recognise facial expressions. The machine monitored 65,082 images of the character Ashley Thomas – who developed dementia – from more than 13 episodes of the programme. Already able to spot aggressiveness and depression – possible signs of the degenerative brain disease – researchers hope Robbie will help diagnose patients. And they will now show it scenes from the sitcom Friends to help it learn about social interactions.