New robotic system helps stroke survivors track recovery

For these individuals, the concept of ‘Use it or lose it’ is often easier said than done, particularly in breaking the habit of ‘arm nonuse’ or ‘learned nonuse’. However, overcoming this habit is crucial for improving strength and preventing injury.

Researchers from the University of Southern California (USC) have taken a significant step in addressing this issue. They developed a novel robotic system to collect accurate data on the spontaneous use of arms by stroke survivors. This development, detailed in a paper in the November 15 issue of Science Robotics, is a leap forward in stroke rehabilitation.

The system employs a robotic arm to monitor 3D spatial information, leveraging machine learning to process this data. It generates an ‘arm nonuse’ metric, aiding clinicians in assessing a patient's rehabilitation progress. A socially assistive robot (SAR) accompanies the system, offering instructions and encouragement.

Nathan Dennler, the paper’s lead author and a computer science doctoral student at USC, explains the system's goal: “Ultimately, we are trying to assess how much someone’s performance in physical therapy transfers into real life.”

This study is the result of a collaboration between USC’s Thomas Lord Department of Computer Science and the Division of Biokinesiology and Physical Therapy. The research involved 14 participants, initially right-hand dominant before their stroke, interacting with the system.

Maja Matarić, study co-author and Distinguished Professor of Computer Science, Neuroscience, and Pediatrics at USC, describes the process: “This work brings together quantitative user-performance data collected using a robot arm, while also motivating the user to provide a representative performance thanks to a socially assistive robot.”

Participants interacted with the system by placing their hands on a 3D-printed box with touch sensors, responding to a SAR's cues. The research indicated significant variability in hand selection and time taken to reach targets, suggesting differences in arm use among stroke survivors.

Dennler adds: “The participants have a time limit to reach the button, so even though they know they’re being tested, they still have to react quickly. This way, we’re measuring gut reaction to the light turning on – which hand will you use on the spot?”

The system was rated highly for its simplicity and safety by participants, who also suggested personalisation improvements. Future studies may include integrating behavioural data such as facial expressions and diverse tasks.

Amelia Cain, an assistant professor of clinical physical therapy at USC, noted differences in arm utilisation among participants. This insight could enable healthcare professionals to track a patient’s recovery more accurately.

Cain highlights the system's advantages over traditional assessment methods, which often rely on subjective observations. “This type of technology could provide rich, objective information about a stroke survivor’s arm use to their rehabilitation therapist,” she said. The therapist can then use this data to better tailor their interventions, focusing on the patient's specific areas of weakness and strength.