Smartwatches can detect Parkinson's years before diagnosis

Smart watches carry a series of sensors that allow you to record physical activity, heart rate or sleep quality. Nastasic (Getty Images)

Before Parkinson's disease becomes visible, those who will suffer from it begin to write with smaller and smaller print. Even before they themselves perceive it, they hold down the keys of the mobile longer when sending a message. And several years before diagnosis, the first disorders in movement occur. By the time the doctor diagnoses it, 60% or more of the neurons that produce dopamine have stopped doing so, making tremor, muscle stiffness, depression tremendously evident... Now, an investigation with thousands of people wearing smartwatches on their wrists has been able to anticipate who will have the evil long before it becomes visible.

Since 2006, a study has been underway in which the health authorities of the United Kingdom follow the evolution of the health of half a million people who were then over 40 years old (UK Biobank). A decade later, 103,712 of them were given smartwatches to record their activity for a week. These data have helped a group of scientists to investigate something that science longs to find: an objective marker of Parkinson's that serves for its early detection. Already when they put the watches, there were 273 with clinical diagnosis of parkinsonism. And 196 others have since been diagnosed. Data from these two groups have been key to detecting the abnormal signal that something is wrong in the substantia nigra, the part of the brain that degenerates as the disease progresses.

"[People with Parkinson's] may have subtle motor or non-motor symptoms that often go unnoticed by the people themselves."

Cynthia Sandor, neurodegenerative disease researcher at Cardiff University

"Parkinson's is a neurodegenerative movement disorder characterized by slow disease progression," recalls Cynthia Sandor, a researcher at Cardiff University (UK) and co-author of the study. "Affected people experience motor symptoms such as slowness of movement, rigidity, coordination difficulties and tremors," he adds. All of these prodromes, or signs that precede the disease, appear many before its diagnosis. "They may present with subtle motor or non-motor symptoms that often go unnoticed by the people themselves." But the accelerometers, magnetometers and gyroscopics worn by activity bracelets or smartwatches do not escape them. In theory, mobiles also have all that technology, but by not always carrying them with one, they would invalidate their records.

In this work they relied on the data offered by the accelerometer carried by smart watches. This sensor records acceleration, the onset of each movement, and is represented in a three-dimensional system that changes with each second. To distinguish distinctive patterns in the resulting thousands and thousands of graphs, the scientists relied on an artificial intelligence system. The results of this work, just published in the scientific journal Nature Medicine, show a decrease in mobility between 7 am and 12 pm of people who had the diagnosis of Parkinson's when they put the watches. Artificial intelligence was able to differentiate this pattern from that of the more than 40,000 people they used as a control group.

With that training, the researchers went further, also identifying the nearly 200 who received the diagnosis an average of 4.33 years after their movements were recorded. In some cases, detection occurred up to 7 years earlier. "We showed that a single week of captured data can predict events up to seven years in advance. With these results, we could develop a valuable tool to aid in the early detection of Parkinson's disease," said Sandor, head of the Institute for Dementia Research in the United Kingdom. Smartwatch data is easily accessible and, at least in that country, a third of the population already uses it. A platform should be built to centralize the data and the authors of the study do not escape the technological problems and the legal and privacy implications, but Parkinson's has no cure and all therapies to stop its advance have failed.

The head of Neurology at the Gregorio Marañón Hospital (Madrid), Francisco Grandas, a great expert in Parkinson's, recalls that all the treatments that exist are symptomatic, improve the patient's condition, "but do not prevent its progression". He also says that there are several trials, several drugs, in the experimental phase, that aim to slow its progress, but so far they have not succeeded. "In addition to problems such as the blood-brain barrier [membrane that protects brain tissue], we intuit that it may be because the moment has already passed, because the disease is already at an advanced stage," adds Grandas. That's why he values this new job. "Other markers are being investigated, such as brain imaging, lifestyle, blood biochemistry... Years before, non-motor symptoms appeared first, but now we begin to know that there are also subtle motor signs and these systems of analysis of these movements could detect them," he concludes. This would open the possibility of using those experimental treatments in the prodromal phase of the disease.

"Disease-modifying therapies are ineffective in the clinical phase of Parkinson's. The probable reason is that the pathology of the disease is already too advanced at that stage."

Sirwan Darweesh, Department of Neurology, Faculty of Medicine, Erasmus University Rotterdam

Sirwan Darweesh, from the department of neurology at the Faculty of Medicine at Erasmus University Rotterdam (Netherlands) has been studying the appearance and evolution of Parkinson's for years. In 1990, researchers from the university began a very ambitious study to follow the health of all inhabitants over 55 years of Ommord, a barium of the Dutch city. Within this work, Darwesh focused on a hundred people who ended up being diagnosed with Parkinson's. From his research, Darwesh can say that "the pathology of the disease begins more than two decades before a clinical diagnosis can be made. The first symptoms usually appear 10 years before it is done." Darwesh agrees with the Spaniard Grandas that the diagnosis comes too late: "Disease-modifying therapies are ineffective in the clinical phase of Parkinson's. The likely reason is that the pathology of the disease is already too advanced at that stage, as more than 60% of key dopaminergic brain cells have already been depleted by the time the diagnosis is made."

One of the weaknesses of this research is that the recording of activity with the watches only lasted a week, but if applied in a real environment, the accumulation of data over time could fine-tune the red flag. Before Sandor's current work, a group of scientists in the United States already used artificial intelligence to detect patterns in smartwatch data. They also used the sample from the UK Biobank, but they started from those already diagnosed with Parkinson's. One of the authors of this research is University of California, San Francisco neurologist Karl Friedl. For him, a good snapshot, such as a full week of sampling movement patterns, is enough "to be able to detect someone who is going to have Parkinson's." From a broader point of view, "we can help people discover many important features of their health and well-being through the way they move," Friedl adds. In addition, "if we add all the other prodromal characteristics that are emerging related to Parkinson's (anosmia, REM sleep disturbance, depression...), the predictive algorithms in our new world of AI will become very powerful," he concludes.

Precisely the work with smart watches also obtained data on sleep patterns, in this case with a sample of 65,000 people. Again, artificial intelligence was able to detect a decrease in sleep duration and quality both in those diagnosed when they were recorded activity and those who were diagnosed years later. "The clocks tell us that people experience more frequent nighttime awakenings and longer sleep duration several years before a Parkinson's diagnosis," Sandor says. Combining nighttime and daytime data, accelerometers could give doctors time to try to curb the disease.

You can follow EL PAÍS Salud y Bienestar on Facebook, Twitter and Instagram.