A team of Canadian researchers has developed a new technique to help people suffering from tremors that can cause major difficulties in the patient's daily life.
One million people throughout the world have been diagnosed with Parkinson's disease, just one of the neurodegenerative diseases that can cause hand tremors.
While technology such as sophisticated wearable exoskeleton suits and neurorehabilitative robots could help people offset some involuntary movements, these robotic assistants need to precisely predict involuntary movements in real-time, as a lag of merely 10 or 20 milliseconds can thwart effective compensation by the machine and in some cases may even jeopardize safety, the German news agency (dpa) reported.
The researchers designed an algorithmic model that will make the robots more accurate, faster and safer when battling hand tremors.
According to a report released by the Scientific Reports, an online journal of Nature, the new algorithmic model is able to characterize pathological hand tremors affecting a large number of people, mostly aging adults.
Researchers at the Movement Disorders Center (Ontario) named the machine-learning model PHTNet.
They used small sensors to analyze the hand motions of 81 patients in their 60s and 70s, and then applied the neural network modeling technique to predict the involuntary movements of these patients.
Co-author Farokh Atashzar from the University of New York said: "Our model is already at the ready-to-use stage, available to neurologists, researchers, and assistive technology developers."
"The new technique requires substantial computational power, so we plan to develop a low-power, cloud-computing approach that will allow wearable robots and exoskeletons to operate in patients' homes," he added.
