Before the onset of Parkinson’s disease became apparent, the patient began to write in progressively smaller letters. Before they even know it themselves, they hold down the phone button longer while texting. And a few years before the diagnosis, the first movement disorders occurred. By the time doctors diagnose Parkinson’s, 60% or more of the dopamine-producing neurons have stopped doing so, making tremors, muscle stiffness, depression very noticeable. Now, investigations into the thousands of people who wear smartwatches have been able to anticipate who will develop Parkinson’s long before it becomes evident.
Since 2006, a study has been conducted in which UK health authorities have monitored the health of half a million people over the age of 40 (UK Biobank). A decade later, 103,712 of them were given smartwatches to record their activities for a week. This data allowed a group of scientists to investigate something that science was eager to find: objective markers of Parkinson’s that could be used for early detection. When they wore their watches, 273 of the participants had a clinical diagnosis of Parkinson’s. And since then, another 196 have been diagnosed. Data from these two groups is key for detecting abnormal signals that indicate that something is wrong in the substantia nigra, the part of the brain that degenerates as the disease progresses.
“Parkinson’s is a neurodegenerative movement disorder characterized by slow disease progression,” recalls Cynthia Sandor, a researcher at Cardiff University in England and one of the study’s authors. “Affected people experience motor symptoms such as slow movements, stiffness, coordination difficulties, and tremors,” he added. All these prodromals – signs that precede the disease – appear long before its diagnosis. “They can display fine motor or non-motor symptoms that the person is often not aware of.” But the accelerometers, magnetometers, and gyros found in motion-tracking devices and smartwatches can catch up. In theory, cell phones also have this technology, but since they aren’t always carried by someone, their records are invalid.
In the study, the researchers relied on the data offered by the smartwatch’s accelerometer. This sensor records the acceleration, the start of each movement, and is represented in a three-dimensional system that changes every second. To distinguish distinctive patterns in the thousands and thousands of generated graphs, scientists use artificial intelligence systems. The results of research that has just been published in the scientific journal Natural Medicine, showing decreased mobility between 7 a.m. and 12 p.m. in people diagnosed with Parkinson’s while they were wearing a smartwatch. Artificial intelligence was able to distinguish this pattern from more than 40,000 people in the control group.
With that training, the researchers went a step further, also identifying nearly 200 people who were diagnosed an average of 4.33 years after their movements were recorded. In some cases, detection occurred up to seven years earlier. “We show that one week of data capture can predict events up to seven years in advance. With these results, we can develop a valuable tool to help early detection of Parkinson’s disease,” said Sandor, who is also head of the Institute for Dementia Research in England. Data from smartwatches is easily accessible and, in the UK, one-third of the population already use the device. A platform had to be set up to centralize the data, and the researchers recognized that this posed a technological challenge as well as legal and privacy implications. But there is no cure for Parkinson’s and all treatments to stop it from progressing have failed.
Francisco Grandas, a Parkinson’s expert at the Gregorio Marañón Hospital in Madrid, points out that all of the available treatments are symptomatic: they improve the patient’s condition, “but do not prevent its progression.” He also said that there were several trials of the drug in the trial phase purporting to slow the progression of the disease, but so far had not been successful. “Other than troubles like those brought about by the blood-brain barrier [the membrane that protects brain tissue], we suspect that maybe because the time has passed, because the disease is already in an advanced phase, “explained Grandas. That’s why he’s optimistic about the new research. “Other markers are being investigated, such as brain imaging, lifestyle, blood biochemistry… Non-motor symptoms appeared years before, but now we are starting to learn that there are also fine motor signs and systems to analyze these movements can detect it. ,” he said. This will open up the possibility of using experimental treatments in the prodromal phase of the disease.
Sirwan Darweesh, from the Department of Neurology at Eramus University School of Medicine in Rotterdam (Netherlands) has spent many years studying the origins and evolution of Parkinson’s. In 1990, university researchers began a very ambitious study to monitor the health of all residents over the age of 55 in Ommord, a neighborhood of the Dutch city. In this work, Darwesh focuses on one hundred people who are eventually diagnosed with Parkinson’s. Based on his research, Darwesh can say that “the pathology of the disease begins more than two decades before a clinical diagnosis is made. The first symptoms usually appear 10 years before diagnosis.” Darwesh agrees with Grandas that Parkinson’s is diagnosed late: “Disease-modifying therapies are not effective in the clinical phase of Parkinson’s. A possible reason is that the pathology of the disease was too advanced at that stage, as more than 60% of the main dopaminergic brain cells were depleted by the time the diagnosis was made.”
One drawback of the new research is that smartwatches only record a week’s worth of activity, but when applied to a real environment, collecting data over time can refine warning signals. Prior to Sandor’s current work, a group of scientists in the United States used artificial intelligence to detect data patterns from smartwatches. They also used samples from the UK Biobank, but they started with data on patients who had been diagnosed with Parkinson’s. One of the authors of the study is neurologist Karl Friedl. For him, a full week of movement pattern sampling was enough “to be able to detect someone who is going to have Parkinson’s.” From a broader perspective, “we can help people discover many important characteristics of their health and well-being through the way they move,” adds Friedl. “If we add up all the other emerging prodromal features associated with Parkinson’s [anosmia, REM sleep disturbance, depression]predictive algorithms in our new AI world are going to be very powerful,” he concluded.
Indeed, the smartwatch study also obtained data on sleep patterns, in this case using a sample of 65,000 people. Again, artificial intelligence was able to detect decreases in sleep duration and quality, both in those with a Parkinson’s diagnosis when activity was recorded and in those diagnosed years later. “Smartwatches tell us that people wake up more frequently during the night and experience longer sleep durations several years before the diagnosis of Parkinson’s,” said Sandor. Combined with day and night data, accelerometers could buy doctors time to try to curb the disease.
Sign up for our weekly newsletter for more English news coverage from EL PAÍS USA Edition
#Smartwatches #detect #Parkinsons #years #diagnosis
