Smartwatches can help identify Parkinson’s disease up to seven years before key symptoms appear and a clinical diagnosis can be made, a study has found.
Data collected by a device that measures how fast people move over seven days was analyzed by the researchers.
They discovered that they could use artificial intelligence (AI) to accurately predict who would later develop Parkinson’s.
According to experts, this could be used as a new screening tool for Parkinson’s, allowing the disorder to be detected at a much earlier stage than current methods allow.
Study leader Dr Cynthia Sandor, new lead at the UK Dementia Research Institute at Cardiff University, said: “With these results we can develop a valuable screening tool to aid in the early detection of Parkinson’s.
“This has implications both for research, in increasing recruitment into clinical trials; and in clinical practice, in enabling patients to access care at an early stage, in the future when it becomes available.”
Dr Kathryn Peall, senior clinical lecturer at NMHII (Neuroscience and Mental Health Innovation Institute) at Cardiff University, said: “For most people with Parkinson’s disease, by the time they start experiencing symptoms, many of the affected brain cells are already damaged. is lost.
“This means diagnosing the condition early is challenging.
“While our findings here are not meant to replace existing diagnostic methods, smartwatch data can provide a useful screening tool to assist in the early detection of this disease.
“This means that as new treatments hopefully start to emerge, people will be able to access them before the disease causes extensive brain damage.”
Read more: AI policing: Can Sunak make Britain the center of regulation?
Parkinson’s affects cells in the brain called dopaminergic neurons, which are located in an area of the brain known as the substantia nigra.
This causes motor symptoms such as tremors, rigidity (stiffness), and slowness of movement.
By the time the characteristic symptoms of this condition begin to appear, and a clinical diagnosis can be made, more than half of the cells in the substantia nigra are already dead, the researchers said.
An inexpensive, reliable and accessible way to detect changes early could allow intervention before disease causes severe brain damage.
In the new study, researchers analyzed data collected from 103,712 people in a UK Biobank study who wore a medical-grade smartwatch for seven days in 2013-2016.
The device measures the average acceleration – meaning movement speed – continuously over a period of a week.
The scientists compared data from a group of people who had been diagnosed with Parkinson’s disease, with another group who received a diagnosis up to seven years after the smartwatch data was collected.
Not only could people who developed Parkinson’s be distinguished from healthy people in this study, but the researchers later expanded on this to show that AI could be used to identify individuals who would later develop Parkinson’s in the general population.
It is more accurate than other known risk factors or early signs of disease in predicting whether a person will develop Parkinson’s disease.
This model is also able to predict the time to diagnosis.
The study was led by scientists at the UK Dementia Research Institute and the Neuroscience and Mental Health Innovation Institute at Cardiff University.
It was published Monday in the journal Nature Medicine, and was funded by the UK Dementia Research Institute, the Welsh Government and Cardiff University.
Additional reporting by PA Media.
#Smartwatches #detect #Parkinsons #years #symptoms #studies #show