A new study published by JMIR found that the digital physical therapy tool Kaia was able to suggest exercise corrections with comparable accuracy to a physiotherapist.

Participants in the study used Kaia’s app, formerly called Motion Coach, which includes automated, real-time exercise feedback that is tracked with the user’s smartphone camera or tablet. The small study examined the corrections and exercise suggestions that the app gave patients against physiotherapists' evaluations. 

Participants, who were diagnosed with osteoarthritis of the knee or hip, got an iPad and headphones and were instructed to perform certain exercises using the Motion Coach suggestions and instructions. Meanwhile, two physiotherapists, who were blinded to the Motion Coach instructions, evaluated whether the exercise was performed correctly. The clinicians then evaluated the execution of the exercise on a scale from 0 to 5, with 5 being the best score. 

Researchers found that there was no “detectable difference in the levels of interrater agreement” between the app and the clinician in any of the six exercises evaluated. 

“The interrater agreement for suggesting corrections during therapeutic exercises between both physiotherapists and Motion Coach was moderate to substantial and did not differ between physiotherapists themselves and physiotherapists and Motion Coach,” researchers wrote in the study. “This finding was valid for all investigated exercises and subgroup analysis. These findings validate the ability of Motion Coach to detect form during exercise and provide audiovisual feedback to users with preexisting musculoskeletal conditions.”

TOPLINE DATA

Researchers found that the mean agreement between the app and the physiotherapists was 0.828, which means that it was not inferior to that between the two therapists, which was 0.833.

The study found no “detectable difference” between the app and the first physiotherapist, the app and the second therapist, and the two therapists when it came to interrater reliability. 

HOW IT WAS DONE

The study included 24 participants all with confirmed prior diagnosis of osteoarthritis of the hip or knee who were enrolled as outpatients in the Ludwig-Maximilians-University (LMU) Hospital in Munich, Germany. To be included, participants had to be over the age of 18. 

Each participant performed six exercises, with a total of 23 rated segments. 

“For each segment, each physiotherapist’s evaluation and Motion Coach’s evaluation (ie, whether correction was required or not) were collected after the participants completed each exercise. Furthermore, the overall form rating by physiotherapists was recorded on a 6-point Likert scale. Data were pooled for the primary analysis,” researchers wrote. 

THE LARGER TREND 

Kaia Health has been working in the musculoskeletal space for some time. In April, the company scored €62 million ($75 million) in a Series C funding round, bringing its total raise to €103 million ($125 million). 

But Kaia isn’t the only company working on digital physical therapy. Last year, chronic care management company Omada Health acquired Physera, an app-based platform that includes remote consultations with physical therapists. In April, Omada rolled out a new tool that employs computer vision to help PTs measure a patient’s movement and range of motion. Others in the virtual PT space include Hinge Health, Sword Health, Spata Science, Risalot Health and SpineZone.

Editor's note: A previous version of this story misstated that Kaia sponsored the study. Kaia employees were co-authors of the study. However, the funding was provided exclusively by the state of Bavaria.