Smart watches could detect Parkinson's seven years before clinical diagnosis

The research was conducted at Medical Research Council-funded (MRC) UK Dementia Research Institute at Cardiff University under the supervision of  Dr Kathryn Peall, an MRC Clinician-Scientist Fellow at Cardiff University.

The scientists were able to accurately predict the outcomes with the help of artificial intelligence, a statement by UK Research and Innovation says. 

Using AI, the team analyzed data from 103,712 people wearing smart watches and monitored their speed of movement over a single week between the years – 2013 and 2016. 

Scientists discovered that AI allowed them to gather more accurate data compared to any other risk factor in identifying early signs of the disease.

The study enabled the scientists to create a “screening tool” that could identify individuals who would later develop Parkinson's disease.

“It would enable the detection of the disorder at a much earlier stage than current methods allow,” the organization states. 

Early detection

The study leader, Dr Cynthia Sandor from notes that the Smartwatch data is easily accessible and low cost.

“As of 2020, around 30 percent of the UK population wear smartwatches,” she said, “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.”

The disease not only causes physiological symptoms but also psychological symptoms including depression and anxiety, balance problems, loss of sense of smell (anosmia), problems sleeping (insomnia), and memory problems, the NHS says. 

By aiding individuals to detect the hallmark symptoms of Parkinson's' at an early stage through affordable and reliable means, it would allow medical professionals to intervene before the disease causes extensive damage to the brain.

A statement by the researchers says, “Parkinson’s affects cells in the brain called dopaminergic neurons, located in an area of the brain known as the substantia nigra. It causes motor symptoms such as tremors, rigidity (stiffness), and slowness of movement.”

Usually, the diagnosis is made when the symptoms are observed and by the time the disease is identified, “more than half of the cells in the substantia nigra will already have died,” researchers said.

Dr Sandor said that the study showed a single week of data captured can predict events up to seven years in the future. With the help of results, scientists are able to develop a  valuable screening tool that aids early detection of neurodegenerative disease.

“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,” she said.

So far, the scientists compared data taken from a group of participants who were already diagnosed with Parkinson's to another group that received a diagnosis upon the collection of the smartwatch seven years later. 

Researchers stress that more scientific research needs to be studied and conducted around the world in order to check the accuracy level of the new findings. 

The study was published on 3 July in Nature Medicine.

Abstract

Parkinson’s disease is a progressive neurodegenerative movement disorder with a long latent phase and currently no disease-modifying treatments. Reliable predictive biomarkers that could transform efforts to develop neuroprotective treatments remain to be identified. Using UK Biobank, we investigated the predictive value of accelerometry in identifying prodromal Parkinson’s disease in the general population and compared this digital biomarker with models based on genetics, lifestyle, blood biochemistry or prodromal symptoms data. Machine learning models trained using accelerometry data achieved better test performance in distinguishing both clinically diagnosed Parkinson’s disease (n = 153) (area under precision recall curve (AUPRC) 0.14 ± 0.04) and prodromal Parkinson’s disease (n = 113) up to 7 years pre-diagnosis (AUPRC 0.07 ± 0.03) from the general population (n = 33,009) compared with all other modalities tested (genetics: AUPRC = 0.01 ± 0.00, P = 2.2 × 10−3; lifestyle: AUPRC = 0.03 ± 0.04, P = 2.5 × 10−3; blood biochemistry: AUPRC = 0.01 ± 0.00, P = 4.1 × 10−3; prodromal signs: AUPRC = 0.01 ± 0.00, P = 3.6 × 10−3). Accelerometry is a potentially important, low-cost screening tool for determining people at risk of developing Parkinson’s disease and identifying participants for clinical trials of neuroprotective treatments.