The earliest symptoms of Parkinson's disease may be very subtle, and the disease can progress slowly, making it difficult to detect. Slow movement, tremors, muscle stiffness, and impaired balance are considered primary symptoms of the disorder, but many patients have recalled other symptoms like loss of smell, sleep problems, and restless legs prior to the onset of tremor or stiffness. There are other diseases that may resemble Parkinson's, and doctors still have to perform a subjective examination to diagnose the condition, as there are no biomarkers or tests that identify Parkinson's patients who have a non-genetic form of the disease.
Now scientists have reported that smartwatches could help diagnose Parkinson's disease as many as seven years before the hallmarks that enable a clinical diagnosis start to appear. These symptoms are caused by the death of certain neurons in a part of the brain known as the substantia nigra. This new method could be a major benefit for patients, who are typically not diagnosed until over half of the neurons in the substantia nigra have died.
The findings have been reported in Nature Medicine.
In this study, the researchers assessed data in the UK Biobank from over 103,000 people who had worn a smart watch for a weeklong period at some point from 2013 to 2016. The smartwatches measured speed of movement over that week. This information was compared to data from Parkinson's patients, as well as to data from a group of people who had gotten a Parkinson's diagnosis within seven years of the data collection, and data from healthy people.
With an analysis utilizing artificial intelligence, the researchers determined that people who went on to develop Parkinson's disease were identifiable with the smartwatch data. These people were distinguishable from healthy controls. The researchers found that this method could be used to find individuals in the general population who will eventually develop Parkinson's disease.
Not only is smartwatch data easy to obtain, but the investigators also showed that this method is more accurate as a Parkinson's diagnostic tool than any other early disease symptom. It can also predict how long it will be before a person is diagnosed.
"We have shown here that a single week of data captured can predict events up to seven years in the future. With these results we could develop a valuable screening tool to aid in the early detection of Parkinson's," said study leader Dr. Cynthia Sandor, an emerging leader at the UK Dementia Research Institute at Cardiff University. "This has implications both for research, in improving recruitment into clinical trials, and in clinical practice, in allowing patients to access treatments at an earlier stage, in [the] future when such treatments become available."
Sources: Cardiff University via Medical Express, Nature Medicine
