LONDON, Oct 19 — A team of researchers at Oxford University is using a system of wearable sensors and machine-learning algorithms to track the progression of Parkinson’s disease. It’s a method designed to enable a more accurate monitoring of the progression of motor symptoms in a bid to improve diagnoses.

Researchers from the Department of Clinical Neurosciences at Oxford University in England have demonstrated the usefulness of machine learning algorithms (too often summed up over simplistically as "artificial intelligence”) in analyzing data from sensors worn by Parkinson’s disease patients. Analysis of the data collected during walking and standing tasks shows the progression of the disease’s motor symptoms over time, as participants in this study were assessed every three months. The study shows that such a system can considerably improve diagnostic — and prognostic — accuracy.

Being able to track the progression of motor symptoms in people with neurological disorders such as Parkinson’s disease is useful for adapting their care protocol and ensuring it addresses their needs. With current assessment scales — scoring systems based on purely physical examination — detection of disease progression can sometimes be delayed by the subjectivity of observations and ratings. The laboratory conducting this study evaluated sensor devices placed on patients’ torso, wrists and feet. The data collected, combined with machine learning, enables the progression of motor symptoms to be tracked much more accurately than traditional assessments. The result is a more precise diagnosis, whatever the degree of severity of Parkinson’s disease. It should be noted that this approach can also work with other similar disorders.

It’s also a major step forward for clinical trials and drug development, which usually require years of study and work. It is crucial to be able to identify truly effective drugs as early as possible, in order to accelerated work on them and such a system facilitates sorting out drugs with real promise from others. — ETX Studio