Wearable technology aided by artificial intelligence can warn and prevent falls for patients recovering from stroke and spinal injuries.
Simon Fraser University researchers are using cutting edge technology, in combination with artificial intelligence and machine learning, to support safer rehabilitation for patients. The work is highlighted in a research paper in the journal Clinical Rehabilitation, co-authored by Gustavo Balbinot, an SFU assistant professor in neurorehabilitation.
Balbinot leads the Movement Neurorehabilitation and Neurorepair laboratory, which focuses on rehabilitation after stroke or a spinal cord injury. For those patients, a potential fall can have very serious, long-term consequences, so the research is focused on optimizing safety during the rehabilitation process.
"Rehab is all about movement, so we want to make patients move. And by moving, patients can regain the movement they lost," says Balbinot. "But we want them to move safely, so the importance of this research is that now we can really understand movement in terms of safety during rehabilitation."
The study looked at more than 50 chronic stroke survivors and monitored them during mobility tasks. The patients wore a wearable device that measured their movements as they went through various day-to-day activities such as standing from chairs and navigating challenging obstacles. The researchers have developed software that can interpret the huge volume of data from the wearable sensors and identify when the individual is undertaking potentially risky movements. SFU is B.C.'s top university for artificial intelligence, according to the AI Rankings, with more than 100 researchers across eight faculties engaged in AI research.
"This sensor can quantify characteristics of the movements of the person, and with machine learning we can identify patterns of movement for those patients," says Balbinot. "The software can learn about the patterns of movement when the person was just about to fall and for a subsequent event the technology can warn the patient, this is a very challenging movement you are doing right now, take care, mind your step, and move safely'."
With the development of wearable technology, very sophisticated, small sensors can now be created. Balbinot envisages a world where these sensors are incorporated discreetly into clothing and worn comfortably, providing constant monitoring of a patient's movement patterns and provide alerts that are fully tailored to the individual.
"Wearables are important in this", he says. "They can really bring the lab to people's daily life."
