A computer program equipped with sensors tracks the movements of patients’ arms during stroke rehabilitation

A computer program equipped with sensors can accurately identify and count arm movements in people participating in stroke rehabilitation, a new study has found. Now that it can do this, the next step, according to the study authors, is to use the tool to define the intensity of movements that lead to the greatest recovery in patients’ ability to move independently. and to take care of themselves after a stroke.

The urgency of labor stems from the fact that the mobility of the arms, as well as the mobility of the other limbs, is seriously reduced in more than half of stroke survivors. Each year, nearly 800,000 Americans suffer a stroke, according to estimates by the US Centers for Disease Control and Prevention.

Led by researchers at NYU Grossman School of Medicine, the study showed that the tool, developed at New York University and called PrimSeq, was 77% effective in identifying and counting the number of prescribed arm movements during rehabilitation exercises for stroke patients. Sensors attached to the arms and back were used to track movements in three dimensions. The developers say they plan further testing on more stroke patients to refine their computer model, reduce the number of sensors needed, and then develop a smaller prototype that could be worn on the arm and upper body. .

Our study demonstrates that a digital tool, which is designed to perform the same function as a smartwatch, is highly accurate in tracking patients’ movement intensity during stroke rehabilitation therapy.”

Heidi Schambra, MD, Co-Principal Investigator, Associate Professor in the Departments of Neurology and Rehabilitation Medicine at NYU Langone

“Such help is desperately needed because counts from video recordings or other wearable sensors do not offer standardized measures of the precise amount of rehabilitation exercise each patient receives,” says Dr. Schambra. “Any improvement in exercise ‘dose’ received must be based on accurate, automated measurements of the type and number of arm movements involved in a given exercise.”

Previous animal research suggests that intense upper body exercise may promote recovery after stroke. However, research in humans shows that people who have had a stroke receive on average one tenth of the physical training that has been shown to be effective in animals. According to the researchers, this is mainly because there was no easy way, until the development of PrimSeq, to ​​accurately track the movements of their arms.

Published in the journal Digital Health PLOS Online June 16, the new study recorded the upper body movements of 41 adults who suffered a stroke as they performed routine rehabilitation exercises to regain use of their arms and hands. The exercises and arm movements involved patients feeding with a fork and grooming with a comb.

Over 51,616 upper body movements were recorded from 9 sensors, with digital recordings of each arm movement then associated with functional categories, such as whether the movement involved reaching for an object or holding it still .

Artificial intelligence (machine learning) software was then programmed to detect patterns in the data and link those patterns to specific movements. The resulting PrimSeq tool was then tested on a separate group of eight stroke patients who wore the sensors while performing various exercises.

PrimSeq was then used to see if it could accurately identify 12,545 of their recorded movements based on their function. The program was able to accurately assess the majority of movements in the patients, all of whom had mild to moderate arm impairments following stroke.

“PrimSeq has industry-leading performance in identifying and counting functional movements in stroke patients, and we are collecting more data to continue to increase its accuracy,” says co-lead investigator Carlos Fernandez-Granda , PhD, Associate Professor of Mathematics and Data Science at New York University.

“As our research seeks to find the optimal levels of training intensity needed for recovery, I would argue that our tool holds great promise for clinical use, as the alternative is not at all to have accurate counts,” says Dr. Schambra. “If further experiments prove successful, we will of course test the system in clinical trials.”

The authors intend to make PrimSeq freely available to stroke rehabilitation experts around the world and have already published their data used to build the program online.

Funding for the study was provided by National Institutes of Health grants R01LM013316, K02NS104207, and NCATS UL1TR001445. Additional financial support was provided by National Science Foundation grant NRT-HDR1922658 and American Heart Association-Amazon Web Service grant 19AMTG35210398.

In addition to Dr. Fernandez-Granda and Dr. Schambra, other NYU Langone and NYU researchers involved in this study are Co-Principal Investigators Avinash Parnandi and Aakash Kaku, Anita Venkatesan, Natasha Pandit, Audre Wirtanen, Haresh Rajamohan, and Kannan Venkataramanan . Another co-investigator of the study is Dawn Nilsen from Columbia University in New York.


Journal reference:

Parnandi, A. et al. (2022) PrimSeq: A deep learning-based pipeline for quantifying rehabilitation training. PLOS digital health. doi.org/10.1371/journal.pdig.0000044.

#computer #program #equipped #sensors #tracks #movements #patients #arms #stroke #rehabilitation

Leave a Comment

Your email address will not be published. Required fields are marked *