Smarter Rehab with Robotics and Machine Learning

According to the Worldwide Health Organization (WHO), 15 million people globally suffer a stroke each year, with the United States accounting for almost 800,000 of those instances. A third of stroke sufferers—approximately five million people—are left permanently disabled and in need of some sort of physical therapy or patient care to help them attempt to regain even a fraction of their original physical mobility.

The loss of motor skills is common in stroke survivors, as the body is often impaired on one side of the body, leaving it difficult to walk or even to squeeze a hand to grip something. Current patient care relies on physical therapists to help survivors learn how to balance and strengthen muscles through a series of exercises and stretches. While effective enough as the primary course of patient care over the last decade, traditional physical therapy for stroke survivors and other sufferers of neurological disorders lags what is possible when technology is integrated into the course of care.

Recent research around motor learning interference and motor memory consolidation has shown that the most optimal way to treat patients with neurological disorders is through a collaborative effort of robots and human therapists, where the robots focus on reducing physical impairments and the therapists assist in translating the physical gains into function.

The evolution of robotics, along with advancement of machine learning technologies, have allowed for commercialized robotic therapy solutions that have exceptional capacity for measurement and immediate interactive response. Where a human therapist can likely only guide a patient through a handful of movements during a session—and with the ability to only track significant movement as progress—a therapy robot can guide a patient through hundreds of movements during a session and sense even the slightest response while adjusting to the patient’s continually-changing physical ability.

Current robotic therapy systems can guide the exercise treatment in a way that is more precise than a human therapist could, particularly due to the amount of data it can process that can make it “smarter” as it learns the patient’s capabilities. If a patient is unable to move, they are gently assisted to initiate movement toward the target. If coordination is the issue, robots can guide the patient through the physical movement in a way that makes certain the patient is practicing the exact movement in the correct way. As the patient gains strength and ability, the robots provide less assistance to provide a greater challenge.

By Michal Prywata | MDDI



Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s