CGTN Share
New research suggests smartwatches can track data that allows AI to find Parkinson’s disease seven years before obvious symptoms appear. /alvarez/Getty Creative/CFP
Smartwatches can track data that allows artificial intelligence (AI) programs to find Parkinson’s disease as early as seven years before symptoms show, according to a new study.
The landmark report opens the door to detecting and diagnosing Parkinson’s early on, meaning more effective treatment options – with smartwatch data from over a 7-day period capable of pointing to signs of the disease.
Researchers from Cardiff University focused on the speed of movement in patients, setting up AI software to be able to use data on this area detected in smartwatches to accurately predict whether people would develop Parkinson’s later in life
Parkinson’s is a neurological condition where there isn’t enough dopamine in the brain, with the deficiency causing progressively worse motor symptoms like tremors and slowness of movement over time.
It isn’t completely clear why people develop the disease, but researchers believe it may be related to a combination of age, genetics, and environmental factors. Most people with Parkinson’s begin to show symptoms after 50, but some experience them in their 40s.
“Parkinson’s disease is a progressive movement disorder caused by the loss of brain cells that use dopamine,” explained Dr Kathryn Peall, a clinical senior lecturer at Cardiff.
“However, by the time of clinical diagnosis approximately 50 to 70 percent of these brain cells will have been lost. This makes early diagnosis of the disease difficult,” she added.
To try and resolve this issue the new report by researchers from Cardiff’s Neuroscience and Mental Health Innovation Institute and the UK Dementia Research Institute looked at information on over 500,000 individuals aged between 40 to 69 from the UK Biobank.
First they compared data on speed of movement – or accelerometery – to models based on genetics, lifestyle, blood biochemistry, and early stage symptoms of Parkinson’s.
They then programmed AI software to follow the speed movement data, finding it was able to pick out both the patients who were clinically diagnosed with Parkinson’s later in life and those at an earlier stage of the disease from the general population.
The researchers say this is the first demonstration of using such markers to find early stage Parkinson’s in the general population.
Cynthia Sandor from Cardiff’s Dementia Research Institute said that the results related to speed of movement were unique to Parkinson’s and that they could not be observed for any other disorder they examined.
“It suggests that accelerometery could be used to identify those at elevated risk for Parkinson’s disease on an unprecedented scale,” she said.
Sandor pointed out that continuously or even semi-continuously monitoring people for signs of Parkinson’s was difficult because of the time, cost, accessibility and sensitivity necessary.
“But smart devices capable of collecting accelerometer data are worn daily by millions of people,” she said.
In fact, since 2020, around 30 percent of the UK population have been wearing smartwatches since 2020.
“While much more work will need to be done before this is put into clinical practice, our discovery marks a significant leap forward in the early diagnosis of Parkinson’s disease, and suggests that devices such as activity trackers and smartwatches could play a key role in clinical monitoring,” Sandor added.
Leave a Reply