A new study has found that smartwatches could help to diagnose Parkinson's Disease seven years before hallmark symptoms of the disease typically surface. /Wikipedia Commons/
Millions of people use smartwatches to track their health and manage their emails and texts – but the lead scientist of a new study says that they could be used alongside AI to serve an even bigger purpose.
New research carried out by Cardiff University and the Mental Health Innovation Institute has found the technology could help to predict who is likely to develop Parkinson's disease, up to seven years before clinical diagnosis.
Scientists analysed data collected by smartwatches over a seven-day period measuring participants' speed of movement. They found that they could accurately predict, using artificial intelligence (AI), those who would go on to later develop the disease. Researchers say this could be used as a new screening tool, which would enable detection of the disorder at a much earlier stage than current methods allow.
Cynthia Sandor, who led the study, says the findings represent a crucial step forward. "Smartwatch data is easily accessible and low-cost," she told CGTN. "As of 2020, around 30 percent of the UK population wear smartwatches. By using this type of data, we would potentially be able to identify individuals in the very early stages of Parkinson's disease within the general population.”
READ MORE
All aboard Germany's shopping bus
Future of Commonwealth Games in doubt
Heatwaves hit Europe, U.S. and China
What is Parkinson's disease?
Parkinson's is a debilitating disease that is typically associated with motor symptoms, such as tremors and slowness of movement loss. But there are many other symptoms, known as non-motor changes, that occur in an earlier stage of the disease called the prodromal stage. These could be spotted by smartwatches long before physical problems occur.
"When most people are diagnosed with Parkinson's, they have already lost 50 percent of the brain cells in the region of the brain that control movement," Sandor explains.
"Another problem is that there is no one Parkinson's disease – some patients don't have tremors or movement issues and by the time they do, they often occur very late on. Up to 30 percent of Parkinson's cases are misdiagnosed.”
Scientists analysed data collected by smartwatches over a seven-day period measuring participants' speed of movement. They found that they could accurately predict, using artificial intelligence (AI), those who would go on to later develop the disease. /Wikipedia Commons/
What did the study involve?
Researchers analysed data collected from 103,712 UK Biobank participants who wore a medical-grade smartwatch for a seven-day period in 2013-2016. The devices measured average acceleration, meaning speed of movement, continuously over the week-long period.
They compared data from a subset of participants who had already been diagnosed with Parkinson's disease, to another group who received a diagnosis up to seven years after the smartwatch data was collected. These groups were also compared to age- and sex-matched healthy people.
The researchers showed that, using AI, it is possible to identify participants who would later go on to develop Parkinson's disease, from their smartwatch data.
Not only could these participants be distinguished from healthy controls in the study, but the researchers then extended this to show that the AI could be used to identify individuals who would later develop Parkinson's in the general population. They found that this was more accurate than any other risk factor or other recognised early sign of the disease in predicting whether someone would develop Parkinson's disease. The model was also able to predict time to diagnosis.
What happens next?
In addition to using smartwatch data in isolation to improve Parkinson's diagnosis, the development of a vaccine also offers the potential for a two-pronged approach. A number of studies are investigating the potential for vaccines to reduce the risk of or slow the development of Parkinson's disease. So far, the vaccines haven't been effective but Sandor says that if they are then vaccines could be used at an earlier stage.
"In the future, if vaccines prove effective on humans who are suffering with Parkinson's then it will be interesting to see what impact they will have if they are used much sooner, after a diagnosis is made using smartwatch data in the early phase of the disease," she added.
Subscribe to Storyboard: A weekly newsletter bringing you the best of CGTN every Friday