Researchers have found that smart watches could identify Parkinson’s years before the main symptoms appear ©CanvaWearing a smartwatch could identify Parkinson’s up to seven years before the main symptoms of the disease start to show, new research suggests.
Detecting and diagnosing Parkinson’s early can mean more effective treatment options, and data gleaned from a smartwatch over a period of just 7 days could indicate signs of the disease.
In the study, the scientists analyzed the movement speed of the participants. Using a machine learning algorithm, an artificial intelligence (AI) program was able to accurately predict who would develop the disease.
This AI tool can find sperm in infertile men 1,000 times faster than a human
Led by the UK Dementia Research Institute (UKDRI) and Cardiff University’s Neuroscience and Mental Health Innovation Institute (NMHII), the researchers say this method could be used as a new screening tool for the disease.
Parkinson’s is a progressive neurological condition in which there is not enough dopamine in the brain. This deficiency causes problems in the brain that get worse over time.
According to the charity Parkinson’s UK, it’s still not clear why people develop Parkinson’s disease, but researchers think it could be a combination of age, genetics and environmental factors.
The main symptoms are involuntary shaking of body parts, slow movements and stiff, inflexible muscles, but there can also be psychological symptoms such as depression, loss of smell and memory problems.
Most people with Parkinson’s start showing symptoms after age 50, but some experience symptoms in their 40s.
By the time the characteristic symptoms begin to show, more than half of the cells in the affected part of the brain may already be dead, making some form of early diagnosis much needed.
‘Easily accessible and low cost’
‘Smartwatch data is easily accessible and low cost,’ said study leader Dr Cynthia Sandor, an emerging leader at the UK’s DRI.
“As of 2020, around 30% of the UK population wear smartwatches. 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.”
With these results we could develop a valuable screening tool to aid in the early diagnosis of Parkinson’s. This has implications for both research, to improve recruitment into clinical trials, and for clinical practice.
The researchers used data from 103,712 UK Biobank participants, all of whom wore a medical-grade smartwatch over a 7-day period between 2013 and 2016.
They measured the person’s average acceleration continuously over a period of one week.
By comparing data from a subset of participants who had already been diagnosed with Parkinson’s disease with another group who received a diagnosis up to seven years after the smartwatch data was collected, it was possible to use artificial intelligence to identify the participants who would later develop the disease.
The AI was able to distinguish these study participants from control participants, and the researchers showed that it could be used to identify at-risk individuals in the general population.
They found that this was more accurate than any other recognized risk factor or early sign of the disease in predicting whether someone would develop Parkinson’s. The model was also able to predict the time required for diagnosis.
Gut bacteria could hold the key to preventing Parkinson’s disease, Finnish scientists say
“We’ve shown here that just one week of captured data can predict events up to seven years into the future,” Sandor said.
“With these findings, we could develop a valuable screening tool to aid in the early diagnosis of Parkinson’s.
“This has implications for both research, in improving recruitment into clinical trials, and clinical practice, in enabling patients to access treatments at an earlier stage, in the future, when those treatments become available.”
The researchers said a limitation of their study was the lack of replication using another data source, as they did not have access to another comparable dataset.
The results were published in the journal Medicine of Nature.
