Smart watches could be used to speed up the diagnosis of Parkinson’s disease by as much as seven years, using a new artificial intelligence (AI) tool, research has found.

People with Parkinson’s go through subtle changes in how they walk and sleep years before ‘characteristic’ symptoms such as tremors and balance problems appear – but these are usually not noticed until the disease is quite advanced.

Using a type of artificial intelligence known as machine learning, the researchers analyzed data collected from more than 100,000 smartwatches.

They were able to detect these changes, such as reduced gait speed and restless sleep, years earlier than is currently possible and while they are still imperceptible to the individual or their doctor.

“We have shown here that one week of collected data can predict events up to seven years into the future,” said Cynthia Sandor of Cardiff University.

Although the watches cannot provide a clinical diagnosis, identifying people at high risk or showing early signs of the disease could help the process and lead to a faster diagnosis.

There are currently no treatments to slow or stop Parkinson’s disease, but there are some non-pharmaceutical steps that may help people slow its progression, although it is not clear how effective they are.

Steps that can be taken include physical exercise, such as walking, biking, swimming and yoga, and eating a whole, plant-based, Mediterranean-style diet, including fresh vegetables, fruits and berries, nuts, seeds and fish, according to the Parkinson’s Disease Foundation .

In the near future, smartwatches could also help scientists find a cure for Parkinson’s disease by identifying the most suitable people to test drugs at key early stages of the disease.

This means that people at high risk could be included in clinical trials of new drugs if they wanted to – while in the future they could access treatment at an earlier stage when they become available.

“This is a potentially important, low-cost screening tool for determining people at risk of developing Parkinson’s disease and identifying participants for clinical trials of neuroprotective treatments,” said Dr. Sandor.

“Machine learning models achieved significantly better test performance in differentiating clinically diagnosed Parkinson’s disease from prodromal [early signs of] Parkinson’s disease up to seven years before diagnosis from the general population” – compared with tests based on genetics, lifestyle, blood biochemistry and prodromal signs, Dr. Sandor added.

There is currently no specific test to diagnose Parkinson’s disease. Instead, diagnosis is based on a person’s medical history, a review of symptoms, and a neurological and physical exam. Dr. Sandor said I she was surprised and encouraged by her findings.

“We suspected that some movement or sleep functions were impaired before the diagnosis. However, we had no doubt that the damage could be detected so early and achieve better results than any other risk factor tested, such as genetics or known prodromal symptoms,” she said.

“Another surprising aspect we found was a reduction in acceleration that is quite specific to Parkinson’s disease. Other movement disorders have not shown this reduction and no other disorder has shown it before clinical diagnosis,” added Dr Sandor, who works at the UK’s Cardiff University Dementia Research Institute.

“The field of application of our tool would be in the identification of risk persons and in the earliest stages of the disease. Such individuals are crucial for clinical trials of neuroprotective treatments. Instead of testing a new drug on a group of individuals who have been diagnosed and therefore have already lost about 50 percent of their dopaminergic neurons, smartwatches would allow us to test a new drug on a group of individuals in the earlier stages of the disease with less loss of neurons.”

Identifying high-risk individuals could make trials smaller and faster, she said.

The researcher used UK Biobank data collected from 103,712 people aged 40 to 69 who wore a medical-grade smartwatch over a seven-day period from 2013 to 2016 to model whether data from motion trackers could be used to identify cases of Parkinson’s disease before clinical diagnosis.

The devices continuously measured the average acceleration, which means the speed of movement, during a week.

The researchers compared data from a subset of participants who had already been diagnosed with Parkinson’s disease with another group who received the diagnosis up to seven years after the smartwatch data was collected.

dr. Sandor said “acceleration during light physical activity” is the most significant measure taken by the smartwatch. She explained that slowing of movement – ​​known as ‘bradykinesia’ – is a key symptom of Parkinson’s disease and one of the first motor symptoms to develop.

She said she would look for further research in other groups of people and with other smartwatches.

While she hopes a ‘validation tool’ will emerge, she cautioned that “despite our promising results, there are several further steps to implementation – replicating the results and developing an algorithm that works with the largest consumer-grade products”.

Parkinson’s disease was known to affect movement and sleep, and there are subtle motor symptoms such as slowing of movement that occur many years before the disease is diagnosed. This study demonstrates a method for their detection in the general population. The researchers also created a machine learning model that could identify these signs and better predict whether someone will develop Parkinson’s disease.

Scientists not involved in the study welcomed the findings, although some questioned the benefit to a person of knowing they are at high risk of Parkinson’s disease in the absence of effective treatment.
“The research is very interesting,” said Professor José López Barneo of the University of Seville.

“Finding out 10 years ago that you have a high risk of developing Parkinson’s disease is very interesting and valuable from a scientific point of view. In addition, the future patient gets a chance to prevent/mitigate his illness.

“However, given that such prevention is not yet possible, it is not clear whether this is beneficial for the future patient. This is an issue with important ethical implications,” he said.

José Luis Lanciego, from the University of Navarra, added: “This study showed that accelerometry measurements obtained using wearable devices are more useful than the assessment of any other potentially prodromal symptom in determining which people in the normal population are at increased risk of developing Parkinson’s disease in the future, as well as being able to estimate how many years it will take to start suffering from this neurodegenerative process.”

Smart watches are already being used to monitor the progression of Parkinson’s disease and help improve treatment plans, but unlike this new device, they don’t detect signs of the disease far in advance.

The study was published in the journal Natural medicine and was funded by UK DRI, Welsh Government and Cardiff University.

Parkinson’s disease is a brain disorder that causes involuntary or uncontrolled movements, such as tremors, stiffness, and difficulty with balance and coordination. Symptoms usually start gradually and worsen over time. As the disease progresses, people may have difficulty walking and speaking.

It affects around 145,000 people in the UK.

Associate Director of Parkinson’s Research UK, Claire Bale, said: “This could be a major step towards a test that could be used to screen and identify people in the very early stages of the condition, years before a formal diagnosis. This could open the door to early intervention with treatments and therapies that can slow, stop or even reverse brain cell damage – and potentially prevent Parkinson’s disease.

Although we do not yet have treatments that can stop Parkinson’s disease, there are a number of promising candidates on the horizon, some of which have already been tested in early clinical trials.”