Science & Enterprise subscription

Follow us on Twitter

  • FDA today approved a treatment for spinal muscular atrophy in young children that replaces a faulty gene in motor n… https://t.co/C8uIamFD3C
    about 13 hours ago
  • New post on Science and Enterprise: FDA Approves Rare Infant Disease Gene Therapy https://t.co/wqx9iCTxVe #Science #Business
    about 13 hours ago
  • FDA Approves First Mesothelioma Treatment in 15 Years https://t.co/PnKrL24HW0 via @medscape ATTN: @innerarchitect @deansguide
    about 17 hours ago
  • A neuroscience lab in the U.K. designed a process using virtual reality to detect early-stage Alzheimer's disease i… https://t.co/SrIZhdhyLJ
    about 17 hours ago
  • New post on Science and Enterprise: Virtual Reality Harnessed to Detect Alzheimer’s https://t.co/tJrT1Q6LsE #Science #Business
    about 17 hours ago

Please share Science & Enterprise

RSS
Follow by Email
Facebook
Facebook
Google+
Twitter
Visit Us
LinkedIn
INSTAGRAM

Sensors, Algorithm Personalize Parkinson’s Therapy

Parkinson's technology team

Behnaz Ghoraani, standing right, with co-authors Murtadha Hssayeni, left, and Lillian Boettcher, center. (Florida Atlantic University)

18 Apr. 2019. An engineering lab developed a system with wearable sensors and machine learning to detect periods of medication ineffectiveness in people with Parkinson’s disease. A team from Florida Atlantic University in Boca Raton describes the system in a recent issue of the journal Medical Engineering & Physics (paid subscription required).

Parkinson’s disease occurs when the brain produces less of the substance dopamine, a neurotransmitter that sends signals from one neuron or nerve cell to another. As the level of dopamine lowers, people with Parkinson’s disease become less able to control their bodily movements and emotions. Symptoms include tremors, i.e. shaking, slowness and rigidity in movements, loss of facial expression, decreased ability to control blinking and swallowing, and in some cases, depression and anxiety. According to Parkinson’s Disease Foundation, some 60,000 new cases of Parkinson’s disease are diagnosed in the U.S. each year, with more than 10 million people worldwide living with the disease.

A drug usually prescribed for Parkinson’s disease is levodopa that the body converts to dopamine and helps reduce the disease’s symptoms. Levodopa is often combined with carbidopa to prevent levodopa from releasing prematurely, which allows for lower doses, reducing side effects such as nausea and vomiting. The beneficial effects of levodopa for Parkinson’s patients, however, are not always automatic, resulting in “off” periods when dopamine levels drop and symptoms return. These off-periods occur more often among people taking levodopa for longer periods of time, and are difficult to track, except by reports from patients or their caregivers.

A team from the Biomedical Signal and Image Analysis Lab at Florida Atlantic is seeking a technology to determine the state of levodopa “on” and “off” periods, to better administer the patient’s medications or deep brain stimulation treatments. The researchers, led by computer science and engineering professor Behnaz Ghoraani, designed a system with commercially-available motion sensors made by Kinetisense, used in sports medicine and physical therapy to collect data on limb movements by patients with Parkinson’s disease. Data from the sensors, collected in real time, would likely provide more realistic assessments than diaries or questionnaires collected later on.

The sensors are worn on the wrist and ankle, and provide data for an algorithm that processes the data, and based on limb movements, detects and records the person’s levodopa “on” and “off” periods. Ghoraani and colleagues trained the algorithm with data collected from 19 individuals with Parkinson’s disease recorded about 7 types of day-to-day life experiences, such as getting dressed and walking. The team used 4 of those experiences to train the algorithm, and tested the algorithm on the other 3 activity types.

The results show the sensor data and algorithm accurately reported levodopa “on” and “off” periods 91 per cent of the time, with 94 percent sensitivity, indicating the true “on” or “off” condition, and 85 percent specificity, accurately indicating when “on” and “off” periods were not occurring.

Ghoraani says the Florida Atlantic system makes it possible to personalize treatment plans for Parkinson’s disease patients. “Our approach is novel,” notes Ghoraani in a university statement, “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 researchers believe their system could become part of an at-home monitoring system that provides valuable data for clinicians treating patients in remote sites, as well as alert caregivers earlier to problems encountered by people with Parkinson’s disease.

More from Science & Enterprise:

*      *      *

Please share Science & Enterprise ...
error

1 comment to Sensors, Algorithm Personalize Parkinson’s Therapy