Among the challenges faced by many Parkinson's patients are "medication on-off" motor fluctuations, in which the severity of their symptoms can change quickly and drastically. There could be hope for better managing the condition, however, using body-worn sensors.

In a nutshell, the on-offs occur as the effectiveness of Parkinson's medication decreases over the patient's lifetime. This means that instead of generally feeling OK from dose to dose, patients will experience a reduction in symptoms immediately after taking the drug, but those symptoms will return in force before it's time for the next dose.

Among other things, the symptoms can include severe muscle stiffness, an inability to speak clearly, and a slowing of movement – occasionally even to the point that the person can't move at all. And while it's sometimes possible to predict how long the on and off phases will last, in other cases they can be quite random, making it difficult to plan around them.

Ordinarily, the problem is assessed via patient self-reports, and examinations performed at a clinic. The former can be quite subjective, though, while the latter isn't always practical, particularly for patients living in rural areas.

Led by Asst. Prof. Behnaz Ghoraani, a team at Florida Atlantic University has set about addressing this problem by devising a system in which two KinetiSense motion sensors are attached to the patient's body – more precisely, on their most-affected wrist and ankle. As the wearer proceeds to perform their daily activities at home, those sensors gather movement data. When that data is analyzed using a custom algorithm, the onset times and durations of their on and off phases is clearly defined.

In a test of the system, 19 Parkinson's patients wore the sensors as they went through seven routine activities while in both phases. After initially being "trained" on each person, the algorithm was subsequently found to detect their response to medication with an average of 90.5 percent accuracy, 94.2 percent sensitivity, and 85.4 percent specificity.

"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," says Dr. Stella Batalama, Dean of the university's College of Engineering and Computer Science. "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."

A paper on the research was recently published in the journal Medical Engineering and Physics.