Scots scientists create algorithm to detect Parkinson's side-effect

Scientists have created an algorithm which can detect a side-effect of Parkinson's treatment that causes involuntary jerking movements.

Two clinical studies were carried out on 23 Parkinsons patients showing evidence of dyskinesia

Prolonged exposure to dopamine replacement drugs can lead to dyskinesia, causing involuntary jerking and spasms of the whole body.

Heriot-Watt University academics have conducted clinical studies that prove their algorithm reliably detects the condition.

They are now using their study to develop a home monitoring device for patients that will help clinicians adapt and improve treatment.

Dr Michael Lones, associate professor of computer science at Heriot-Watt, said: “The problem is that, as Parkinson’s disease worsens over time, the dose required to treat the motor features increases, which increases the risk of inducing dyskinesia, or making it more severe and prolonged for patients who already have it.

“Patients don’t see their clinicians that frequently and medication only changes at regular review periods.

“So it’s very difficult for clinicians to know when dyskinesia is occurring. A better solution would be a portable device that identifies and monitors dyskinesia while patients are at home and going about day-to-day life, broadcasting data to their clinicians through simple mobile technology.”

The motor features of Parkinson’s, such as tremor, postural instability and a general slowing of movement, are caused by a lack of dopamine.

Clinicians treat this through replacement drugs such as levodopa, but prolonged exposure to them can lead to dyskinesia.

Around 90 per cent of patients treated with dopamine replacement drugs over ten years report symptoms but the exact cause is unknown.

Dr Lones and his team carried out two clinical studies with 23 Parkinson’s patients who had displayed evidence of dyskinesia.

Three clinicians then graded the intensity of the condition shown by them.

Dr Lones said: “The clinical studies allowed us to capture and mine data about how patients move and used those to build models.

“We developed our algorithm to make as few assumptions as possible.

“With traditional analysis, you make assumptions about what a movement looks like. If it doesn’t look like exactly that way, you won’t detect it.

“The algorithm works by building a mathematical equation that describes patterns of acceleration which are characteristic of dyskinesia.

“The system then uses this equation to discriminate periods of dyskinesia from other movements, relaying this information to clinicians who can then adapt a patient’s medication as necessary.

“We’ve demonstrated that our system can reliably detect clinically significant dyskinesia, which is the information clinicians need to adjust a patient’s medication.”

The research was done in collaboration with the University of York and with clinicians at the Leeds Teaching Hospitals NHS Trust.