New technology can predict ON/OFF motor fluctuations in Parkinson’s patients

Chloe Kent 18 April 2019 (Last Updated December 23rd, 2019 10:24)

Researchers from Florida Atlantic University College of Engineering and Computer Science have developed wearable motion sensors to detect and monitor medication ON and OFF states in Parkinson’s patients.

New technology can predict ON/OFF motor fluctuations in Parkinson’s patients
A patient can wear the wrist and ankle bands in day to day life to monitor their ON/OFF motor fluctuations. Credit: Shutterstock

Researchers from Florida Atlantic University College of Engineering and Computer Science have developed wearable motion sensors to detect and monitor medication ON and OFF states in Parkinson’s disease (PD) patients.

PD is a chronic, progressive neurological disorder which affects around six million people globally, a statistic which is expected to double by 2040. The disease leads to motor impairments such as a tremor and difficulty walking and balancing, alongside sleep and speech issues and cognitive impairments.

PD patients often experience motor fluctuations, defined as periods when they are ON, responding positively to their medication, and OFF, when the patient experiences a re-emergence of symptoms. These fluctuations occur in 50% of patients within three to five years of diagnosis, rising to 80% within ten years.

Motor fluctuations mean patients need ongoing adjustments of their treatment, as the frequency and dosage of medication will need to change accordingly. These are typically addressed with clinical examinations backed by a patient’s history with the disease and self-reports of symptoms, however these can often be unreliable and require regular follow-up visits.

Researchers have now developed an algorithm and sensor-based system that can detect ON and OFF state patterns in PD patients using two wearable motion sensors placed on the patient’s most affected wrist and ankle.

The sensors then collected movement signals from patients while they performed daily activities like walking and getting dressed, both in ON and OFF phases, with data from the sensors providing objective measures of disease severity. The algorithm was trained using 15% of the data from four of the activities, then tested on the remaining data.

Florida Atlantic University assistant professor and senior author of the paper Dr Behnax Ghoraani said: “Our approach is novel because it is customized to each patient rather than a ‘one-size-fits-all’ approach and can continuously detect and report medication ON and OFF states as patients perform different daily routine activities.”

The results, published in Medical Engineering and Physics, reveal that the algorithm was able to detect the response to medication during the subjects’ daily routine activities with an average of 90.5% accuracy, 94.2% sensitivity, and 85.4% specificity.

The researchers hope that this will enable the development of an in-home monitoring system for PD patients to provide a comprehensive overview of their condition and allow for a more efficient medication review process.

Florida Atlantic University College of Engineering and Computer Science dean Dr Stella Batalama said: “There is a great need for a technology-based system to provide reliable and objective information about the duration in different medication phases for patients with Parkinson’s disease that can be used by the treating physician to successfully adjust therapy.

“The research that Professor Ghoraani and her collaborators are doing in this field could considerably improve both the delivery of care and the quality of life for the millions of patients who are afflicted by this debilitating neurodegenerative disease.”