Researchers to Study Wearable Sensor Efficacy in Treating Low Back Pain

Following the receipt of a $1.2 million grant from the National Science Foundation (NSF), researchers from the University of California San Diego plan to create a suite of remote monitoring and analytics solutions to improve physical therapy treatments for patients with low back pain.

Low back pain affects up to 80 percent of people at some point in their life, according to the press release.

The grant from NSF will help researchers from UC San Diego work to improve the treatment of low back pain by developing the Multi-Sensor Adaptive Data Analytics for Physical Therapy (MS-ADAPT) system. The system will leverage machine learning analytics, wearable sensors, and a smartphone application to remotely monitor low back posture and movement. Further, it will track whether patients are keeping up with their physical therapy and patient-reported pain.

The researchers will also study the MS-ADAPT system. Study participants wear a Fitbit and various sensors that use nanotechnology and kinesiology tape, which can detect skin strains, spine movement, and muscle engagement or activity.

In addition, the researchers aim to foresee the effects of physical therapy on low back pain and personalize the treatments through machine-learning analytics.

“This research will support remote monitoring of the patient’s posture and movement throughout the day, with the ultimate goal of enabling personalized physical therapy treatments and improving health outcomes,” said Emilia Farcas, the grant’s principal investigator and an assistant research scientist with the Qualcomm Institute (QI) at UC San Diego, in a press release.

A multidisciplinary team will conduct the study, including researchers from the physical therapy, software engineering, and data science arenas.

“The highly collaborative environment and close partnership between all researchers have enabled us to pursue this highly multidisciplinary and important topic,” said Ken Loh, PhD, a co-principal investigator of MS-ADAPT and a structural engineering professor with the UC San Diego Jacobs School of Engineering, in the press release.

Pending positive study results, researchers hope they will soon be able to apply MS-ADAPT to the treatment process for other conditions like spinal cord injury and stroke.

Machine learning and wearable sensors are increasingly being used in patient treatment.

In September, Eko announced it will create a machine-learning algorithm for cardiovascular care after receiving financial support from the National Institutes of Health and the Department of Health and Human Services. The algorithm will be designed to identify pulmonary hypertension using phonocardiogram and electrocardiogram data gathered by smart stethoscopes.

Another study published in Scientific Reports in June described a mHealth wearable device that used data on movements such as neck strain and whiplash to predict concussion risk among contact sports athletes.