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



About Peter Coffaro 815 Articles
A growth-driven and strategic executive, Peter Coffaro commands more than 20 years of progressive management success within the orthopedic industry. Recognized by as one of the top medical sales influencers in the industry; he has 10 years of combined sales management experience and has held positions as a Director, General Manager and Distributor. Peter has worked for some of the top orthopedic companies in the world - Zimmer, DePuy and Stryker. He is also the founder of OrthoFeed: a popular blog that covers orthopedic news and emerging medical technologies. Peter is a three-time Hall of Fame award winner at Johnson and Johnson and has an extensive background in organizational development, business development, sales management, digital marketing and professional education. Peter holds a B.S. degree in Biology from Northern Illinois University.

Be the first to comment

Leave a Reply

Your email address will not be published.


This site uses Akismet to reduce spam. Learn how your comment data is processed.