Smart Watch Identifies Parkinson’s Disease Before Symptoms

Scientists conducted a study where they examined data gathered from smart watches worn by participants for a period of seven days. The data focused on measuring how quickly the participants moved.

Using artificial intelligence (AI), the scientists were able to predict individuals who would later develop Parkinson’s disease accurately.

According to the researchers, this breakthrough could potentially serve as a novel screening tool for Parkinson’s disease. Unlike current methods, this approach would allow for early detection of the disorder, identifying it at a much earlier stage.

Scientists led the study from the UK DRI and Neuroscience and Mental Health Innovation Institute (NMHII) at Cardiff University. The results of their investigation have been published in the journal Nature Medicine.

What is Parkinson’s disease?

Parkinson’s disease affects specific neurons called dopaminergic neurons, which are located in a part of the brain known as the substantia nigra. It gives rise to motor symptoms such as tremors, stiffness, and slowed movements.

Unfortunately, by the time these symptoms become noticeable, and a clinical diagnosis is made, more than half of the cells in the substantia nigra have already perished.

Dr. Kathryn Peall, Clinical Senior Lecturer in the NMHII at Cardiff, commented on the challenges associated with diagnosing the condition early.

Study setting and design

In their study, the researchers examined data from 103,712 participants in the UK Biobank project. These individuals wore a high-quality smartwatch for a duration of seven days between 2013 and 2016. Throughout this period, the smartwatches continuously measured the participants’ speed of movement.

To investigate the potential of predicting Parkinson’s disease, the researchers compared the data from a subset of participants who had already received a diagnosis of Parkinson’s disease to another group of individuals who received their diagnosis up to seven years later.

Both of these groups were then compared to a control group of healthy individuals matched in age and sex.

Results of the study

The results of the study demonstrated that by employing artificial intelligence (AI), it was possible to identify participants who would later develop Parkinson’s disease based on their smartwatch data.

The researchers successfully distinguished these participants from the healthy control group within the study. They extended their findings to show that the AI model could identify individuals in the general population who would later develop Parkinson’s disease.

This prediction’s accuracy was higher than any other known risk factor or early indicator of the disease. Additionally, the model could estimate the time it would take for a diagnosis to occur.

It is important to note that the study has a limitation due to the absence of replication using another data source. Currently, there are no comparable datasets available for a similar analysis. However, the research team conducted thorough evaluations to minimize any potential biases in their findings.

Dr. Cynthia Sandor, an Emerging Leader at the UK DRI in Cardiff and the lead researcher of the study, expressed the significance of their findings.

She stated, “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.”