Smart Watches Could Identify Parkinson’s Disease Years before Symptoms Appear
Posted on 10 Jul 2023
Parkinson's disease impacts brain cells known as dopaminergic neurons, predominantly located in an area called the substantia nigra. This condition leads to motor symptoms such as tremors, stiffness or rigidity, and slowed movements. Unfortunately, by the time these classic symptoms of Parkinson's become apparent, facilitating clinical diagnosis, over half of the substantia nigra cells have already died. Consequently, there's an urgent need for cost-effective, reliable, and readily available methods to detect early changes, thereby permitting intervention before the disease inflicts extensive brain damage. Now, new research has revealed that smartwatches could potentially identify Parkinson's up to seven years prior to the onset of characteristic symptoms and clinical diagnosis.
A study led by scientists at Cardiff University (Wales, UK) analyzed data gathered by smartwatches over a week, focusing on the speed of participants' movements. The researchers examined data derived from 103,712 UK Biobank participants who wore medical-grade smartwatches for a week between 2013 and 2016. These devices continuously measured average acceleration, or movement speed, throughout the seven-day span. The team compared data from a subset of participants already diagnosed with Parkinson's disease to another group diagnosed up to seven years after the smartwatch data collection. They also compared these groups to age and sex-matched healthy individuals.
![Image: Smart watches using AI could accurately predict those who can go on to develop Parkinson’s (Photo courtesy of Freepik) Image: Smart watches using AI could accurately predict those who can go on to develop Parkinson’s (Photo courtesy of Freepik)](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2023-07-10/SDD-294797825.jpg)
The researchers discovered that they could accurately predict, using artificial intelligence (AI), who would eventually develop Parkinson's disease. Not only could they differentiate these participants from the healthy controls, but they also demonstrated that the AI could identify individuals in the general population who would later develop Parkinson's. This method was found to be more precise than any other risk factor or recognized early disease sign in predicting Parkinson's development. The machine learning model was also capable of predicting the time to diagnosis. According to the researchers, this could serve as a novel screening tool for Parkinson's disease, facilitating detection at much earlier stages than current methods permit.
“Smartwatch data is easily accessible and low-cost. As of 2020, around 30 percent of the UK population wear smart watches. By using this type of data, we would potentially be able to identify individuals in the very early stages of Parkinson’s disease within the general population,” said study leader Dr. Cynthia Sandor, Emerging Leader at the UK Dementia Research Institute at Cardiff University.
“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. 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 future when such treatments become available,” added Dr. Sandor
Related Links:
Cardiff University