Before Parkinson’s becomes visible, those who will suffer from it start writing in smaller and smaller letters. Even before they realize it themselves, they hold down the mobile phone keys longer when they are sending a message. And several years before the diagnosis, the first movement disorders occur. By the time a doctor diagnoses it, 60% or more of the neurons that produce dopamine have stopped doing so, causing tremors, muscle stiffness, and obvious depression… Now, an investigation with thousands of people who have worn smartwatches on their wrists has He was able to predict who would be afflicted with evil long before it became visible.
Since 2006, there has been an ongoing study in which UK health authorities have been tracking the evolution of the health status of half a million people over the age of 40 (UK Biobank). A decade later, 103,712 of them were given smartwatches to log their activity for a week. This data has served a group of scientists to investigate something science has been dying to find: an objective marker of Parkinson’s disease for early detection. When they wore the watches, 273 people had a clinical diagnosis of Parkinson’s disease. Since then 196 more have been diagnosed, and data from those two groups has been key to detecting the abnormal signal that something is wrong with the substantia nigra, the part of the brain that deteriorates as the disease progresses.
“[Las personas con párkinson] They can present with subtle motor or non-motor symptoms that often go unnoticed by the subjects themselves.
Cynthia Sandor, a neurodegenerative disease researcher at Cardiff University
“Parkinson’s disease is a neurodegenerative movement disorder characterized by slow disease progression,” says Cynthia Sandor, a researcher at Cardiff University (UK) and co-author of the study. “Afffected people present with motor symptoms such as slowed movement, stiffness, coordination difficulties, and tremors,” he adds. All of these indications, or signs that precede the disease, appear long before it is diagnosed. “They can present subtle motor or non-motor symptoms that often go unnoticed by the person themselves.” But the accelerometers, magnetometers, and gyroscopes in activity bracelets or smartwatches haven’t escaped it. In theory, cell phones also have all this technology, but by not always carrying it with you, they will invalidate your records.
In this work, they relied on the data provided by the accelerometer carried by smart watches. This sensor records acceleration, the beginning of each movement, and is represented in a 3D system that changes with every second. To discern distinct patterns in the thousands and thousands of resulting graphs, the scientists relied on an artificial intelligence system. The results of this work have just been published in the scientific journal Nature medicine, showing a decrease in movement between 7 am and 12 noon in people diagnosed with Parkinson’s disease when wearing watches. The AI was able to distinguish this pattern from the more than 40,000 people they used as a control group.
With this training, the researchers went even further, also identifying nearly 200 people diagnosed an average of 4.33 years after their movements were recorded. In some cases, the discovery occurred 7 years earlier. “We show that one week of captured data 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,” says Sandor, head of Dementia Research UK. Data from smartwatches is easily accessible, and at least a third of the population in that country is already using it. A platform must be created for data centralization, and the study authors are not ignorant of the technological issues and legal and privacy implications, but there is no cure for Parkinson’s disease and all treatments to halt its progression have failed.
All available treatments are symptomatic, improve the patient’s condition, “but do not prevent its progression,” recalls Francisco Grandas, Head of Neurology at Hospital Gregorio Marañón (Madrid), a leading expert in Parkinson’s disease. He also says that there are several trials, several drugs, in the experimental phase, aimed at slowing his progression, but so far they have not been successful. In addition to problems such as those caused by the blood-brain barrier [membrana que protege al tejido cerebral]We sense that it may be because the moment has already passed, because the disease is already in an advanced stage,” adds Grandas. That’s why he appreciates this new job. “Other markers are being investigated, such as brain imaging, lifestyle, blood biochemistry… Years ago, non-motor symptoms appeared first, but now we are beginning to learn that there are also subtle motor signs and these systems for analyzing these movements can detect them,” he ends. This would open up the possibility of using those experimental therapies in the prodromal stage of the disease.
“Disease-modifying therapies are not effective in the clinical stage of Parkinson’s disease. The likely reason is that the pathology of the disease has already advanced at that stage.”
Sirwan Darwish of the Department of Neurology at the Faculty of Medicine of Eramus University in Rotterdam
Sirwan Darwish, of the Department of Neurology at the Eramus University School of Medicine in Rotterdam (Netherlands), has spent years studying the onset and progression of Parkinson’s disease. In 1990, researchers from the university began a very ambitious study to follow the health of all residents over the age of 55 in Oomord, a neighborhood in the Dutch city. In this work, Darwish focused on one hundred people diagnosed with Parkinson’s disease. Darwish can say from his research that “pathology begins more than two decades before clinical diagnosis. The first symptoms usually appear 10 years before they occur. Darwish agrees with the Spaniards that diagnosis comes too late: “Disease-modifying therapies are ineffective in the clinical stage for Parkinson’s disease. The likely reason is that the pathology of the disease has already advanced at that point, as more than 60% of the main dopaminergic brain cells have already been depleted by the time of diagnosis.”
One of the weaknesses of this research is that the hourly activity recording only lasted for a week, but if applied in a real setting, the accumulation of data over time could improve the warning signal. Prior to Sandor’s current work, a group of scientists in the US had already used artificial intelligence to detect patterns in data from smartwatches. They also used a sample from the UK Biobank, but started from those who had already been diagnosed with Parkinson’s disease. One of the authors of this research is neurologist Carl Friedel of the University of California, San Francisco. For him, a good snapshot is enough, like a full week of sampling movement patterns “to be able to detect someone with Parkinson’s disease.” From a broader view, “we can help people discover many characteristics important to their health and well-being through the way they move,” adds Friedel. In addition, “if we add to it all the other emerging prodromal features related to Parkinson’s disease (loss of smell, REM sleep disorder, depression…), then the predictive algorithms in our new AI world will become very powerful,” he concludes.
Working with smartwatches also obtained data on sleep patterns, in this case with a sample of 65,000 people. Again, the AI was able to detect decreases in sleep duration and quality in those diagnosed when their activity was recorded and in those diagnosed years later. “Clocks tell us that people experience more frequent nocturnal awakenings and longer sleep duration several years before a Parkinson’s disease diagnosis,” says Sandor. Combined with day and night data, accelerometers could give doctors time to try to suppress the disease.
You can follow Country health and well-being in FacebookAnd Twitter And instagram.